AI News Digest 2026-09-08

対象期間: 直近2日間 / 収集記事 718 件

台本で使った記事

参考記事一覧

参考記事一覧を表示

Huawei Prepares 160,000 Ascend 950DT Accelerators for DeepSeek Data Center - TechPowerUp imp 0 / dev 50
North Korea-linked hackers turn to AI agents for malicious email decoys - Korea JoongAng Daily imp 35 / dev 30
Despite xAI’s objections, judge rules not to block Minnesota “nudification” law - WDIO.com imp 25 / dev 15
Research acceleration: The view inside OpenAI — NVDA Quantitative Valuation Record imp 30 / dev 20
Supporting independent journalism in Ukraine — NVDA Quantitative Valuation Record imp 5 / dev 0
The Dataflow Model Revisited imp 20 / dev 70
Grok 4.5 Cuts Coding Costs 80%, Trails Rivals [2026] - tech-insider.org imp 60 / dev 85
Grok simulates the final outcome of the Denver Broncos’ 2026 season ahead of Week 1 against the Kansas City Chiefs - A to Z Sports imp 0 / dev 15
bzip3 imp 15 / dev 50
Watch Los Angeles get built, one building at a time (1880–2026) imp 5 / dev 20
Keep Our Servers Running imp 5 / dev 0
AI models ran real businesses: They sent $12,431 in fake invoices, lost $3,200 imp 55 / dev 60
Caltech Mathathon – first hackathon ever devoted to research level mathematics imp 30 / dev 50
PostgreSQL 19 Interactive Tour imp 40 / dev 75
Live map of public transport in Belgium imp 5 / dev 25
Speculative Decoding in vLLM on AMD GPUs imp 70 / dev 85
Smartphone makers don't bother to comply with EU repairability requirements imp 25 / dev 5
Impedance Matching (2017) imp 15 / dev 40
Volkswagen to convert German car plant to produce Israeli defense equipment imp 15 / dev 0
Splash-free urinals (2025) imp 10 / dev 15
Tell HN: OpenAI brings back 5 hour limit for plus and business standard users imp 50 / dev 20
Making a Python interpreter in 1024 bytes imp 40 / dev 70
Ask HN: How do you manage skills files? imp 55 / dev 75
Bill Gates tries to install MovieMaker imp 5 / dev 30
GrapheneOS Overhauled Default Apps and Secure Clipboard imp 35 / dev 60
Apparently CodePen 2.0 sends data to their servers as you type imp 45 / dev 70
LG smart TVs caught logging audio with screen off and snooping on local devices imp 60 / dev 55
An Alien Mind imp 70 / dev 65
Kotlin 2.4.20 Released imp 30 / dev 80
Java Annotated Monthly – September 2026 imp 25 / dev 70
The Rider 2026.3 Early Access Program Is Open imp 30 / dev 75
The complex corporate web behind a $3.2 billion AI data center imp 45 / dev 50
Authors push back as publishers and agents make claims on Anthropic settlement imp 35 / dev 15
Travis Kalanick’s Atoms might be getting into the robotaxi business imp 30 / dev 25
Seattle Times and Newsday sue OpenAI and Microsoft for infringement imp 55 / dev 30
Presentation: From AI Agent Demo to Production: Automated Testing and Evaluation imp 65 / dev 85
Google Mantis: an Agentic Vulnerability Scanning Harness for Reducing False Positives imp 0 / dev 85
How Figma Uses AI Agents for Security imp 60 / dev 75
Anthropic reportedly signs $517 billion in compute deals after Dario Amodei warned rivals about reckless risk imp 75 / dev 40
GPT-6 Astra beat Portal start to finish without human help in under 24 hours imp 0 / dev 85
ChatGPT claws back web traffic share to 55.5 percent as Gemini's brief comeback fades imp 45 / dev 20
AI-designed drug appears to turn back the body's biological clock in early trial imp 60 / dev 40
How AI wiped out an entire industry in Nairobi imp 40 / dev 20
At UBS, AI skills are now a condition for landing a job imp 40 / dev 35
OpenAI reports AI "research interns" and warns about its own pace at the same time imp 65 / dev 70
New York City bans AI tools from public schools through eighth grade imp 35 / dev 20
Qwen-Drive 1.0 tells you why it brakes, just don't expect the explanation to match the maneuver imp 40 / dev 60
Chatbots built an "echo chamber of one" and now psychiatry has to decide if "AI psychosis" exists imp 45 / dev 30
Last Week in AI #343 - GPT-6, OpenAI’s agents chatted on a wiki, Fable 5.1 imp 0 / dev 70
EXAONE Forecast for Finance imp 45 / dev 75
From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance imp 50 / dev 70
Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation imp 65 / dev 85
Data-Optimized Contingency Screening: A Machine Learning Approach to Power System Security imp 35 / dev 60
Iris: Climbing to the Search Frontier imp 70 / dev 85
A Removal Based Approach to Improve LLM Faithfulness at Test-Time imp 55 / dev 75
Why Better Models Can Create Riskier Systems: Evidence from LLM Agents in Financial Markets imp 65 / dev 75
Corporate Language Model (CLM): Transforming Tacit and Fragmented Enterprise Knowledge into a Sovereign, Auditable, and Executable Corporate Intelligence Layer imp 70 / dev 85
HarvestBench: Measuring Whether LLM Agents Will Pay to Avoid Killing Animals imp 50 / dev 70
PerfReasoning: How Well Do LLMs Reason on Hardware Performance? imp 50 / dev 80
When Quantization Breaks Memory: Recurrent-State Write-Back in Low-Precision Temporal Inference imp 50 / dev 80
ResLearn-XR: Residual Learning for Network Traffic and Quality-of-Experience-Aware Modeling in Extended Reality imp 35 / dev 65
Rethinking Indirect Prompt Injection as a Test-Time Search Problem imp 65 / dev 80
BioSync: Transformer-Based Cross-Modal Fusion for a Multimodal Physiological Digital Biomarker imp 40 / dev 65
What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents imp 70 / dev 85
MaxKernel: Agentic Kernel Generation for TPUs imp 65 / dev 85
Towards a universal language of concepts: A survey imp 45 / dev 70
Data-Driven Discovery of Composition-Dependent Constitutive Models for Hyperelasticity and Viscoelasticity of Digital Materials imp 40 / dev 60
From Answers to Interpretations: Rethinking Ambiguity-Induced Aleatoric Uncertainty Estimation in LLMs imp 55 / dev 75
IPGeoAI: Transformer-Based Geolocation with LLM Semantic Fusion imp 40 / dev 60
Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection imp 60 / dev 75
La Agente \'Optima: Towards Agentic Self-Driving Laboratories imp 60 / dev 75
Extremely Sparse Supervision Incentivizes Reasoning Ability imp 65 / dev 85
Does the Selected Object Reach the Reader? Auditing Identity Handoffs in Grounded Language-Model Pipelines imp 55 / dev 75
$\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction imp 70 / dev 85
Leveraging Imperfect Restoration for Data Availability Attack imp 40 / dev 70
SiLR: Structure-Preserving Admission and Process Reward for LLM Tool Agents imp 65 / dev 85
A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark imp 65 / dev 85
Continual Graph Memory for Adaptive Recommendation under Intent Drift imp 50 / dev 70
Harness-agnostic detection and immunization of reward hacking in self-evolving language models imp 70 / dev 85
ERPBench: Evaluating LLM Agents for Enterprise Decision-Making Across Competitive Market Ecologies imp 60 / dev 80
Train What You Deploy:Token-Faithful Post-Training of a Production Coding imp 75 / dev 90
Predicting Spatiotemporal Mobile Sensing-Based PM2.5 Concentrations Using Low-Rank Adapted Spatially Attentive Graph Neural Network imp 35 / dev 70
SQL-Zero: Self-Evolving Text-to-SQL imp 65 / dev 80
Model Retirement Creates Reproducibility Risk in Biomedical AI Publications imp 60 / dev 70
FinalityBench: An Effect-Level Benchmark for Agent Decisions Under Delayed and Conflicting Financial Finality imp 55 / dev 75
PLUME: Parameter-Efficient Personalization of Large Language Models via Low-Rank User Modulation in Shared Subspaces imp 65 / dev 80
Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLM imp 60 / dev 75
DCFA: Dual-view Causal-inspired Attribution for Failure Reasoning in LLM-based Multi-agent Systems imp 65 / dev 85
Shadow Queries for Private Retrieval in Vector Databases imp 65 / dev 80
Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges imp 60 / dev 80
DODR: Deterministic Operator-Driven Reasoning in Latent Space imp 70 / dev 85
ProtLingo: Efficient Protein Language Modeling via Conditional Memory and Expert Routing imp 50 / dev 75
Whose record is this? Diagnosing and authorizing record use in personalized multimodal models imp 50 / dev 70
Hierarchical Possession-Aware Graph Pointer Network for Pass Receiver Selection imp 30 / dev 55
MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis imp 50 / dev 70
When Financial Fine-tuning Fails: A Three-Level Detectability Analysis of Numerical Hallucination in Domain-Adapted Language Models imp 60 / dev 75
CPR-IE:A Compression-Prediction-Resource Intelligence Efficiency Metric imp 45 / dev 70
Long Horizon Transformer Quantile Fault Prediction for Multi Site Industrial Predictive Maintenance imp 45 / dev 70
ElderBench: Benchmarking Autonomous Mobile Agents for Older Adults imp 55 / dev 75
MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models imp 60 / dev 80
MZ-Rain: Moisture-Budget-Guided Zero-Inflated Model for Station-Level Precipitation Nowcasting imp 15 / dev 15
CoSkill: Joint Reinforcement Learning of Reasoning and Meta-Skill Agents for Hierarchical Skill Evolution imp 55 / dev 75
LLM-Assisted Behavioural and Scenario Augmentation for Agent-Based Energy Adoption Models imp 35 / dev 50
From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents imp 60 / dev 80
CHAMP: Cross-domain Hybrid Architecture for Matchmaking and Prediction in Online Multi-Player Games imp 20 / dev 40
AutoLR: Automating the Path from Research to Launch Review in Industrial Recommender Systems imp 30 / dev 60
MARLA: A Conceptual Scaffold for Regulatory Learning under the EU AI Act imp 25 / dev 15
Reinforcement Learning for Sequential Solar PV Policy Design under Uncertainty: An Agent-Based Approach imp 25 / dev 45
From Language Models to World-Acting Systems: Progress and Limits of Agentic AI across Digital, Social, Virtual, and Physical Environments imp 75 / dev 85
Compact-Memory LLM Agents via Online Max-Member Clustering and Atom-Aware Packing imp 65 / dev 85
Artificial Intelligence in Equity and Crypto Markets: Progress, Profitability Evidence, and the Limits of Automated Investing imp 30 / dev 50
Solving Hard XAI Queries Based on a Compiled Dual-Rail Encoding imp 40 / dev 60
Why We Care About Understanding: Competence through Predictive Compression imp 35 / dev 55
Global to Local: Topology-Preserving Adaptive Graph Pooling via Granular-Ball imp 25 / dev 65
A Tree-based RAG Framework for Evidence-Intensive QA via Adaptive Planning and Topology-Aware Evidence Gathering imp 55 / dev 75
Language models judge war differently when tested for alignment imp 40 / dev 60
TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing imp 65 / dev 85
Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment imp 45 / dev 65
Towards Efficient Evaluation of Evolutionary Transfer Optimization: Case Studies on Task-Parameterized Applications imp 25 / dev 55
MePo++: Unifying Representation Refinement and Reconciliation for General Continual Learning imp 30 / dev 65
TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents imp 60 / dev 80
Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny? imp 40 / dev 65
Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent imp 50 / dev 75
LLM-Guided Program Evolution for Circle Packing: Breaking 10 Packomania Records for $28 imp 55 / dev 80
ProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding imp 25 / dev 50
Compact Bellman-Grounded Cognitive Maps for Cost-Aware Navigation imp 30 / dev 65
Unifying ICL, SFT, KL-Regularized RL Through a Bayesian Lens imp 65 / dev 85
SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding imp 50 / dev 75
A Hybrid Predictive Ensemble of Machine Learning and Deep Neural Networks for Early Cardiovascular Disease Risk Assessment imp 25 / dev 50
The Mirror Agent Model: a Bayesian Architecture for Interpretable Agent Behavior imp 50 / dev 80
What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection imp 55 / dev 85
CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review imp 30 / dev 70
ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs imp 55 / dev 85
Substrate-Aware AI Agents: Execution Context as a First-Class Input imp 65 / dev 85
Uncensored Open-weight Models: Redistribution as the Persistence Layer imp 45 / dev 65
Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory imp 50 / dev 75
A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability imp 25 / dev 70
Commonsense Reasoning in Computer Vision: Foundations, Recent Advancements, and Future Directions imp 35 / dev 70
Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents imp 60 / dev 85
AI for Computational Design Science: A Responsible Human-AI Framework and Case Study on Short-Form Video Safety Surveillance imp 40 / dev 70
Don't Drop Dropout: Optimizing Layer Sparsity for Efficient LLM Training and Inference imp 55 / dev 85
Testing Interchangeability in LLM Agent Teams imp 55 / dev 80
GUT: Quantifying and Optimizing the Reasoning Uncertainty of LLMs via Graph Complexity imp 50 / dev 75
Beyond Aggregate Scores: Behavioral Correctness Assumptions for Assessing Reference-Based Automatic Evaluation Methods imp 35 / dev 70
RISE: Recursive Improvement via Self-Extrapolating Policy Distillation imp 55 / dev 85
Large Language Models for HVAC Operations in Building Energy Systems: A Critical Review of Methods, Applications, and Deployment Readiness imp 30 / dev 60
LLM-Driven Algorithm Design for Quantum Circuit Synthesis based on Binary Decision Diagrams imp 35 / dev 70
Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models imp 40 / dev 75
Does Your Agent's Memory Survive a Model Upgrade? A Controlled Study of Memory Portability imp 60 / dev 85
Who Should Grade My Work? Student Perspectives on Transparent AI-Assisted Writing Assessment in Higher Education imp 30 / dev 50
CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents imp 60 / dev 85
Molecular D\'ej\`a Vu: Digit-Level Retrieval of Published Values in Frontier Language Models imp 50 / dev 75
Necessary or Sufficient? Evaluating LLM Explanations With Behavioural Evidence imp 45 / dev 70
Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe imp 55 / dev 80
A Deep Generative Model for Synthesizing Labeled Wireless Signals imp 25 / dev 65
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks imp 45 / dev 70
When Seeing Overrides Knowing: Visual Dominance and Deferral-Based Method for Personalized Safety in VLMs imp 50 / dev 70
Scalable Context Orchestration for Serving LLMs Over Voice imp 50 / dev 80
Evidence Integration in Large Language Models imp 60 / dev 85
Abstraction Agent imp 35 / dev 70
Data-Driven Learning of Unknown Nonlinear Differential Equations Using Functional Analysis imp 25 / dev 65
Adapting from Downturns: Prediction of Long-Term Conversational-Skill Development in Mental-Health Crisis Counselors imp 25 / dev 40
VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models imp 35 / dev 75
Blockchain-Enabled Secure Logging for Fiscal Electronic Mechanisms: Evaluation of the Greek eSEND and myDATA Tax Systems imp 25 / dev 60
Cross-modal triage network: a multimodal deep learning framework for severity-based triage and visual explainability in chest radiographs imp 30 / dev 70
Ultrasound-Based Prediction of Cirrhosis Decompensation Using Large-Scale Computer Vision Models imp 25 / dev 60
Where Appearance Fails, Geometry Recognizes: A CAD-Free 3D Shape Prior That Complements Vision Foundation Models imp 35 / dev 75
What Moves? Localized Motion Representations for Compositional Scene Control imp 30 / dev 70
You Really Didn't Get That? Benchmarking Social Pragmatic Inference for Indirect and Playful Chinese Online Comments imp 35 / dev 70
A Systematic Evaluation of Cross-Lingual Consistency Enhancement Methods in Multilingual Language Models imp 50 / dev 80
REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation imp 40 / dev 75
GRACE: Graph-Grounded Reflective Agent Copilot Engine for Expert-in-the-Loop Knowledge Expansion imp 65 / dev 85
When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models imp 55 / dev 85
A Roadmap for MEG Foundation Models imp 35 / dev 70
Shared circuits predict whether LLMs generalize across formats in arithmetic reasoning imp 55 / dev 80
Patterns of Priming in Production: Lexical, Semantic and Structural Alignment in Language Model Generation imp 40 / dev 75
Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuning imp 50 / dev 75
Towards Understanding Pause Token Fine-Tuning Dynamics: A Mode Retention Perspective imp 45 / dev 80
Hakken: Predicting future discoveries to fill the gaps in today's knowledge imp 40 / dev 75
A Semantic Model of Genetic Evidence: A Step Toward Bridging the Basic-Science-Clinic Gap imp 30 / dev 70
Atlas: Optimizing Deployment of Compound AI Workflows on Heterogeneous Clusters imp 65 / dev 85
Pitch-class Steering for Diffusion-based Music Generation via Latent-space Probes imp 30 / dev 70
Repeat-After-Me: Black-Box Adaptive Visual Prompt Injection imp 50 / dev 75
Continual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI imp 40 / dev 80
Dynamic Adaptation of the LLM Context for Generating Routines with Coupled Semantics imp 60 / dev 85
Training-Free Halving of Activated Experts in Fine-Grained Mixture-of-Experts Models imp 50 / dev 85
When Do Internal Probes Beat Reading the Answer? Miscalibrated Readouts and Behavior-Concealed Knowledge in Language Models imp 55 / dev 80
Dual-Part Multi-Lateral Branched Network for Multi-Class Segmentation in Cardiovascular Catheterization Angiograms imp 25 / dev 70
PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning imp 30 / dev 70
SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds imp 35 / dev 75
Tracing Audio Grounding and Answer Selection in Audio LLMs imp 45 / dev 80
Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle imp 80 / dev 90
Enhancing Multimodal Emotion Recognition via Multi-Feature Encoding and Attention-Based Fusion imp 25 / dev 65
Wireless Foundation Models: State-of-the-Art and Open Challenges imp 35 / dev 75
Simulation-free Unbalanced Dynamic Optimal Transport with General Growth Penalty imp 20 / dev 60
Building a research-software catalog with a coding agent: from hackathon prototype to public deployment imp 60 / dev 85
Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models imp 50 / dev 75
Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models imp 50 / dev 75
When Does an Interpretation Count as Established? The Formation, Evaluation, and Responsibility of Interpretation in Generative AI imp 35 / dev 60
Persistent Teacher Anchoring for Tool-Using Agents imp 60 / dev 85
Dynamic Heterogeneous Graph Representation Learning: A Survey imp 40 / dev 50
Can Activation Steering Capture Multidimensional Authorship Style? imp 45 / dev 65
Linguistic Trajectory Encoding for Efficient Long-Horizon Spatial Memory in Embodied Agents imp 50 / dev 70
Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3 imp 45 / dev 70
Cost-Aware Hierarchical Multi-Agent Ransomware Detection and Family Attribution imp 40 / dev 60
Reinforcement Learning for improving Large Language Models' Catalan text simplification capabilities imp 30 / dev 55
MABPD: Multi-Agent Bias Probing & Detection via Structured Argument Debate imp 50 / dev 65
MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain imp 40 / dev 50
CC-Mediation: Evaluating Large Language Models for Cross-Cultural Conflict Mediation imp 30 / dev 40
Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning imp 35 / dev 55
PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation imp 40 / dev 60
Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents imp 60 / dev 75
ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification imp 35 / dev 55
SimFuse3D: Source-Guided Target Simulation and Confidence-Guided Multi-Stage Localization Reweighting for Cross-Platform 3D Object Detection imp 35 / dev 60
Attention-guided super-resolution of 4D flow MRI in carotid arteries imp 30 / dev 50
RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents imp 65 / dev 85
Adaptation Interfaces for In-Context Tabular Foundation Models in Time-to-Event Prediction imp 45 / dev 65
Sound-based Multi-Person 3D Pose Estimation imp 40 / dev 60
Methane Detection On Board Satellites from Unorthorectified Imagery imp 35 / dev 55
Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair imp 55 / dev 75
TreeFI: Value-Aware Statistical Fault Injection for Deep Neural Networks imp 40 / dev 65
ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems imp 60 / dev 80
One Diffusion Model, Two Roles: Guided Trajectory Planning and Safety-Critical Scenario Generation in Closed-Loop Simulation imp 50 / dev 70
MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression imp 50 / dev 75
VICAL: Vicinal Consistency Alignment for Long-Tailed Visual Recognition imp 40 / dev 65
Amortizing Scaling Law Construction Costs imp 55 / dev 80
How a Chatbot's Response Style Shapes a Classroom: A Multi-Agent Simulation of Students Consulting AI imp 40 / dev 55
Leveraging Low-Level Symbolic Competences for Unsupervised Grounding in Hallucination Detection imp 50 / dev 70
How do LLMs Evaluate Perceived Moral Agency? Investigating Moral Decision-Making in Human-Artificial Agents Interactions imp 35 / dev 50
Qlippy: A Retrieval-Augmented GenAI Assistant for Reproducible Quantum Workflows and Experiment Tracking imp 45 / dev 70
Beyond Co-purchase Relation: Evolution of Complementary Recommendations at Allegro imp 40 / dev 60
Adaptive Multi-Granularity Temporal Modeling for Weakly Supervised Video Anomaly Detection imp 40 / dev 65
A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support imp 55 / dev 75
NEAT-POCKET: Pocket-Conditioned Autoregressive 3D Molecular Generation with a Neighborhood-Guided Set Transformer imp 45 / dev 70
TIER: Threat Implicitness Benchmark for Evaluating LLM Safety Behaviors imp 55 / dev 75
A Schema Bounded Language Model for Refining Robot Policies Without Destabilizing Local Learning imp 45 / dev 70
A Human-in-the-Loop Framework for AI-Assisted Scoring in Large-Scale Writing Assessment imp 45 / dev 60
Beyond Stationarity in Time Series: Discovering Causal Structures and Latent Regimes via Markov Blankets imp 45 / dev 70
AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics imp 50 / dev 75
Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets imp 40 / dev 65
A Verifier-Guided Explainable Reasoning Framework with Gold-Anchored QLoRA, Task-Aware Mixture-of-Experts, and Group-Relative RLVR imp 50 / dev 80
PRICE: A Systematic Study of LLM Adaptation Choices for Bitcoin Price Forecasting imp 40 / dev 65
Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization imp 50 / dev 75
CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls imp 65 / dev 85
How Does mHC Use Its Residual Streams? Selective Routing and Near-Identity Mixing imp 45 / dev 75
RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks? imp 50 / dev 75
Lightweight Vision Transformer Compression for On-Device Plant Disease Detection in Resource-Constrained Agricultural Field Conditions imp 35 / dev 65
The History Is the Detector: Executing CVE Patch History, End-to-End imp 60 / dev 80
Design Docs Are All You Need: An AI-native Machine-Learning Performance Tool imp 60 / dev 85
When LLM Decompilers Recompile More and Preserve Less imp 50 / dev 75
What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies imp 45 / dev 70
Reflection-aware Generative Novel View Synthesis imp 40 / dev 70
RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retail Environments imp 45 / dev 70
Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction imp 15 / dev 35
Quality-diversity in dissimilarity spaces imp 35 / dev 55
A Survey on Semantic Modeling for Building Energy Management imp 30 / dev 50
Procedural Content Generation via Generative Artificial Intelligence imp 45 / dev 70
Active Inference for an Intelligent Agent in Autonomous Reconnaissance Missions imp 45 / dev 75
Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning imp 55 / dev 80
RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training imp 60 / dev 85
MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory imp 60 / dev 80
OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Heuristic Design imp 60 / dev 85
The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs imp 60 / dev 80
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution imp 60 / dev 85
BUZZY: Contrastive Scoring to Mitigate Text-Induced Bias in Multimodal Multiple-Choice QA imp 50 / dev 75
Role-Aware Artificial Intelligence Across Augmentation and Automation in Human-Machine Symbiosis imp 45 / dev 70
Robust and Efficient Guardrails with Latent Reasoning imp 60 / dev 85
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision imp 65 / dev 85
Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents imp 65 / dev 85
GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes imp 50 / dev 80
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents imp 65 / dev 85
Improving Weak World Models Behind Strong Agents in Atari Pong imp 50 / dev 80
Aletheia: An Offline-First Clinical Decision Support System for Differential Diagnosis in Low-Resource Healthcare Settings imp 55 / dev 80
KernelGenBench: A Multi-Source and Multi-Chip Benchmark for LLM-based Kernel Generation imp 60 / dev 85
NxN E-valuation: Hypothesis Certification via a Conformal CRT Null imp 55 / dev 80
$A^2E$ : An End-to-End Agent Auditing Engine imp 65 / dev 85
Semantic Overlays: Mitigating Prompt Injection with Annotations Beyond Tokens and Steering Vectors imp 60 / dev 85
AI Revealed Preferences imp 45 / dev 70
FORESIGHT-9: Prospective and Process-Aware Evaluation of Adaptive Trading Agents imp 50 / dev 80
SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning imp 50 / dev 80
Agentic Context Cracking: Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data imp 65 / dev 85
Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades imp 60 / dev 85
Xiaomi-TabLDM: A Tabular Foundation Model Technical Report imp 55 / dev 80
LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease Screening imp 50 / dev 75
Measuring proximity to standard planes during fetal brain ultrasound scanning imp 40 / dev 65
An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders imp 40 / dev 70
Hyperedge Anomaly Detection with Hypergraph Neural Network imp 40 / dev 70
Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points imp 55 / dev 80
AI-Powered CPS-Enabled Vulnerable-User-Aware Urban Transportation Digital Twin: Methods and Applications imp 50 / dev 80
Graph Foundation Models for Recommendation: A Comprehensive Survey imp 50 / dev 80
AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports imp 50 / dev 80
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models imp 60 / dev 85
Cross-Task Generalization Between Understanding and Generation in Unified Vision-Language Models: A Controlled Study imp 50 / dev 80
Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving imp 50 / dev 75
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts imp 50 / dev 75
GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations imp 40 / dev 75
Gradient-based Model Shortcut Detection for Time Series Classification imp 45 / dev 75
Partial Inverse Design of High-Performance Concrete Using Cooperative Neural Networks for Constraint-Aware Mix Generation imp 40 / dev 70
GLOW: Graph-Language Co-Encoding for Agentic Workflow Performance Prediction imp 65 / dev 85
The Fake Friend Dilemma: Relational Trust and the Political Economy of Conversational AI imp 40 / dev 50
TeleTables: A Benchmark for Large Language Models in Telecom Table Interpretation imp 35 / dev 55
Multi-Modal Time Series Prediction via Mixture of Modulated Experts imp 40 / dev 65
Comparables XAI: Faithful Example-based AI Explanations with Counterfactual Trace Adjustments imp 45 / dev 60
AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories imp 35 / dev 50
Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection imp 45 / dev 65
MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model imp 40 / dev 60
SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection imp 50 / dev 65
YOLO with Kolmogorov-Arnold networks and vision-language foundation models for interpretable object detection with trustworthy multimodal AI in computer vision perception imp 35 / dev 70
X-VC: Zero-shot Streaming Voice Conversion in Codec Space imp 40 / dev 55
ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search imp 50 / dev 70
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies imp 45 / dev 70
Octopus Protocol: One-Shot Hardware Discovery and Control for AI Agents via Infrastructure-as-Prompts imp 65 / dev 80
HLS-Seek: QoR-Aware Code Generation for High-Level Synthesis via Proxy Comparative Reward Reinforcement Learning imp 40 / dev 75
Towards Generalization of Block Attention via Automatic Segmentation and Block Distillation imp 55 / dev 80
Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases imp 50 / dev 70
Label Over Logic? How Source Cues Bias Human Fallacy Judgments More Than LLMs imp 45 / dev 45
FVSpec: Real-World Property-Based Tests as Lean Challenges imp 55 / dev 75
"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems imp 60 / dev 75
From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data imp 55 / dev 80
Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats imp 50 / dev 85
SoK: AI-Augmented Binary Reversing imp 60 / dev 75
Attributable by Construction: Claim-Anchored Provenance for Multi-Document Summarization imp 50 / dev 70
Spectral Geometry and Bosonic-Bloch Probes: Explorations in Quantum Learning imp 25 / dev 45
Estimating Uncertainty from Reasoning: A Large-Scale Study of Multi- and Crosslingual MCQA Performance in LLMs imp 50 / dev 75
Protective Capacity Hallucination: When Large Language Models Claim Nonexistent Capabilities imp 60 / dev 75
Not All LLM Reasoning is Visible in the Chain-of-Thought imp 55 / dev 80
Deep Divide-and-Reduce in Symbolic Regression imp 45 / dev 70
TRNet: Learning with Topographic Priors for VHR Paddy Rice Mapping imp 35 / dev 55
Search-G1: Grounded Search Agents via Representation-Based Intrinsic Rewards imp 60 / dev 80
LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN imp 40 / dev 70
Terminal Symmetry as a Carrier of Asymmetric Process Knowledge: Statewise Refinement for Anytime Verified Construction imp 30 / dev 45
Degradation-Aligned Self-Supervised Learning for State of Health Estimation of Lithium-Ion Batteries under Label Sparsity imp 50 / dev 65
Improving Energy Efficiency of Oil Platforms Through Optimal Loading of Diesel Generators Using Machine Learning and Search Algorithms imp 35 / dev 55
MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters imp 50 / dev 75
DeMMO: Longitudinal and Cross-Disease Modelling of Digital Mobility Outcomes via Multi-Task Learning imp 40 / dev 60
When Linguistic and Internal Confidence Diverge in Large Language Models imp 55 / dev 80
E-SENS: Exclusion-Sensitive Penalization for Negative-Constraint Retrieval imp 50 / dev 75
SPD: Single Pass Decoding for Generative Reranking imp 55 / dev 80
DeepAffinity: Long-Term Aspect Preference Prediction in eCommerce using Small Language Models imp 45 / dev 65
From Tokens to Semantics: Leveraging Complementary Signals for Hallucination Detection in Black-Box LLMs imp 60 / dev 80
Post-Training Language Models for Gold-Medal Performance in Coding Competitions imp 50 / dev 80
Tree species mapping in Denmark: A comparison of spectral-temporal features with geospatial foundation model embeddings imp 35 / dev 60
Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye Maps imp 45 / dev 75
IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks imp 55 / dev 75
Almost Free State Prediction Separation imp 55 / dev 85
FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-Manipulation imp 45 / dev 80
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR imp 60 / dev 85
Spectral-Target Physical Latent Structuring for JEPA-Style World Models imp 50 / dev 80
ProToMEx: Rapid, Interpretable Explanations via Structured Representations imp 50 / dev 75
A Data Fusion Framework for Grounding Aerospace Surrogate Model via Experimental Wind-Tunnel Observations imp 40 / dev 70
Quantum-Assisted Memory-Efficient Training for Parameter-Intensive Wi-Fi-Based Human Activity Recognition imp 40 / dev 70
Evaluating Large Language Models for Forced Outage Risk Prediction: Benefits and Comparison to Machine Learning imp 50 / dev 75
BER-PEF: Unified Human Mobility Predictability Evaluation via Bayes Error Rate Estimation imp 40 / dev 65
Modular Deep Recurrent Neural Network: Application to Quadrotors imp 40 / dev 70
SharedSAE: One Feature Dictionary Across Language Models imp 55 / dev 80
A Quantum Variational Approach to Prototypical Recurrent Unit imp 35 / dev 65
On the Abundance of Critical Points of the t-SNE Energy imp 40 / dev 65
Disentangling Attention in Deep Operator Learning: A Controlled Study of Data-Driven and Physics-Informed Architectures imp 45 / dev 75
Beyond a Universal Forecasting Selector: Demand-Conditioned Model Selection across Demand Patterns and Horizons imp 50 / dev 75
A Repeated-Measurement Study for Cultural Analytics of English Song Lyrics Using Five Large Language Models imp 40 / dev 55
Conformity Breaks Conformal Prediction imp 55 / dev 80
On-board ML for Trace Gas detection in Imaging Spectroscopy data imp 40 / dev 70
Nested Inductive Bias Framework for SPD Manifold Learning imp 45 / dev 75
An Energy-Based Conservative-Dissipative Latent Neural Evolution Operator for Magnetization Dynamics imp 45 / dev 75
Distilled Continuous Diffusion Language Models Can Write Code in Few Steps---or One imp 60 / dev 85
Mitra-v2 Technical Report imp 70 / dev 80
Fast Surrogate Modeling of Excitable and Oscillatory FitzHugh-Nagumo Dynamics with Parametric Neural Operators imp 40 / dev 75
Optimizer Memory Schedules for Outscaling the Overtraining Axis imp 60 / dev 85
Representation Redundancy and Structural Complexity in Finite-Field Inversion imp 35 / dev 60
GNN-Guided Graph Coarsening and Adaptive QUBO Penalties for the Capacitated Vehicle Routing Problem with Time Windows on a Quantum Annealer imp 50 / dev 80
Too Rare to Learn: Prescribed Cyclone Tracks Degrade a Bay of Bengal Ocean Emulator imp 45 / dev 70
SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery imp 55 / dev 80
Interpretability for Turing Machines imp 45 / dev 70
WEECFP-SuRGE: Wide Embedded Extended Connectivity Fingerprint with Substructure Rotary Graph-distance Encoding imp 50 / dev 80
Locating and Steering Refusal Beyond Attention imp 65 / dev 85
Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling imp 60 / dev 80
A Fairness Audit of the Duckworth-Lewis-Stern Method: Format-Specific and Gender-Differential Bias, with an Interpretable Calibration Layer for Cricket Target Revision imp 35 / dev 50
Resilience Beyond Stationary Client Unavailability: Unlocking Efficient and Unbiased Federated Learning imp 60 / dev 85
A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification imp 55 / dev 80
Learning-Augmented Algorithms: Guarantees, Construction Mechanisms, and System-Level Implications imp 60 / dev 80
How Faithful Is Attribution for Sales Forecasting? A Counterfactual Study imp 50 / dev 75
Federated Attack Campaign Detection via Contrastive Encoding of Threat Indicators in Gradient Updates imp 65 / dev 85
Communication-Efficient Personalized Federated Learning via Layer-Wise Multi-Threshold Random Sketching imp 60 / dev 85
PACE: Propagation-Aware Collaborative Correction for One-Shot Personalized Federated Graph Learning imp 55 / dev 80
KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU imp 70 / dev 85
When Genomic Masking Priors Fail to Transfer: Strong Variant Prediction, Weak Functional Generation imp 50 / dev 75
From Deep to Shallow: Unconstrained and Efficient Layer Merging Strategy imp 55 / dev 85
Fast Gauss Sums via Flash Attention imp 60 / dev 85
Physics-Aware Random Walk Fingerprints for Scalable Power Grid Graph Classification imp 50 / dev 75
Fractal basins trap latent reasoning imp 65 / dev 80
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference imp 70 / dev 85
Beyond Homoscedasticity: Decoupled Uncertainty Optimization for Deep Imbalanced Regression imp 55 / dev 80
Solution-space heterogeneity shapes federated learning dynamics across partial differential equations imp 55 / dev 85
Confounding-Valid Conformal Inference for Counterfactual KPIs in Wireless Networks imp 60 / dev 80
Deep Microcompression: Structured Pruning and Bit-packed Quantization for Microcontrollers imp 60 / dev 85
A Comparative Study of Counterfactual Explainers for Graph Neural Networks Enabling Multiple Types of Graph Edit imp 50 / dev 75
Single-Query Black-Box Calibration Auditing via Logit Bias imp 60 / dev 80
Coarse-Graining Hidden Representations: Unsupervised Neuron Selection via Mapping Entropy imp 55 / dev 80
MomentQuant: an even more minimalist interval method with linear time complexity for time series classification imp 45 / dev 75
From 80x to 385x: A Best-Matching-Unit Search at the L2 Roof, Measured Against a Symmetrically Tuned Baseline imp 45 / dev 75
Dimension-Adaptive Batched Lipschitz Narrowing Without Knowing the Zooming Dimension imp 20 / dev 40
FedDRAW: Federated Dual Reputation Annealing Weighting for Heterogeneous Multi-Institutional Chest Radiograph Classification imp 25 / dev 55
Hessian-based molecular conformation augmentation for a scalable and efficient strategy of machine learning interatomic potentials imp 20 / dev 35
GLASS: Graph-Language Alignment with Spherical Scoring for Transferable Graph-Level Anomaly Detection imp 25 / dev 50
How to Speculate about Uncertainty in Agentic Coding? A Draft-Model Gate Method imp 65 / dev 80
Learning from VAE Errors to support ECG-based Differential Diagnosis of Myocardial Scar imp 20 / dev 45
Optimal Rates for Agentic Networked Information Aggregation imp 40 / dev 75
Embedded Graph Flows for Categorical Graph Generation imp 25 / dev 50
Variational Continuation for Double Pendulum Periodic Orbits imp 15 / dev 40
Distill Globally, Adapt Locally: Reasoning Distillation and Product-Type Test-Time Training for Scalable Trade-Up Recommendation imp 50 / dev 70
Interface-Induced Trajectory Censoring imp 60 / dev 85
GEPARD - Generative, Prosody-aware, Autoregressive text-to-speech model for Realtime Dialogue imp 45 / dev 65
Self-Supervised Pretraining of Molecular Graph Encoders with LeJEPA imp 30 / dev 60
Low-Latency Spell Correction for Japanese Music Search Queries imp 15 / dev 50
Compute-in-Memory Attention: A Time-Domain Analog Softmax Circuit with RC-Tunable Temperature imp 25 / dev 70
Corporate-Family Resolution Is Not a String-Matching Problem: A Public Benchmark Stratified by Name Visibility imp 30 / dev 60
TNFlow: Amortized Posterior Inference for Trans-Neptunian Object Surface Composition imp 15 / dev 45
The microscope is the mask: privileged views and labels from a cryo-ET forward model imp 20 / dev 55
A Constraint-Aware Generative Framework for Synthetic Origin-Destination Demand in Logistics Networks imp 35 / dev 65
Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys imp 55 / dev 80
Candidate Comparability Before Promotion: Conditional Validation in Adaptive Network Intrusion Detection imp 30 / dev 70
Tuning Collective Patterns to Alleviate Congestion in Shared AI Clusters imp 50 / dev 80
Recovering molecules from coarse-grained beads: free-energy-conditioned generative backmapping across chemical space imp 20 / dev 50
Client-Side Probing of Deleted Ridge Statistics in Federated Unlearning imp 45 / dev 75
Scale-QLoRA: Code-Invariant Adapter Merging for Native 4-bit Microscaling LLMs imp 65 / dev 85
A Sim-to-Real Study of Surface-Code Decoder Benchmarking imp 25 / dev 65
MURAL: Multimodal Uncertainty-aware Recommendation via Adaptive edge Learning imp 30 / dev 60
Centered Permutation Prefixes for SGD with Random Reshuffling: Sharp Rates, H\"older Geometry, and Composite Proximal Extensions imp 25 / dev 70
Hidden In Plain Gaze: Gaze Representations as Privacy Controls for Utility and Re-identification Risk in XR imp 30 / dev 55
Latent-Aligned Reasoning for Multimodal Recommendation imp 35 / dev 65
A Differentiable Neural Surrogate for Photon Propagation in Neutrino Telescopes imp 25 / dev 60
LookThere! Sparse Vision by Reinforced Selection imp 40 / dev 75
Sustainable Edge Vision via Empirically Calibrated DVFS: Eliminating Thermal Throttling on Passively Cooled Hardware imp 45 / dev 80
Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving imp 60 / dev 85
Minimax Lower Bound for Estimating Diffusion-based Local Intrinsic Dimension imp 25 / dev 65
Coupled Control and Wireless World Models for Resilient Remote Robotic Control imp 30 / dev 70
An Analysis of Self-supervised Pre-training with Dependent Samples imp 30 / dev 70
Impact of Data Loss in Postprocessing on Training and Inference of Quantum Neural Networks imp 25 / dev 65
Conformal Prediction for Offensive Security imp 35 / dev 70
SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis imp 35 / dev 65
FluxDisco: Symbolic Regression for Stoichiometric Dynamical Systems via Monte Carlo Graph Search imp 30 / dev 65
PAC-Bayesian Reconstruction Guarantees for Time Series Variational Autoencoders imp 25 / dev 65
Proton Irradiation Characterization of an Open-Source ML Accelerator on a Zynq UltraScale+ MPSoC imp 30 / dev 75
Shallow neural network approximation in mixed Sobolev spaces imp 15 / dev 50
LexFlip: A Dissociation Diagnostic for Legal Meaning Preservation Metrics imp 25 / dev 60
Online Change-point Detection for Cooperative Multi-Agent Reinforcement Learning imp 40 / dev 75
Adaptive Gated Deepfake Detection for Low-Resolution and Resource-Constrained Environments imp 35 / dev 70
UniMate: One Unified Model to Animate Diverse Skeletons imp 35 / dev 60
Small Molecule Optimization with Large Language Models imp 50 / dev 75
The Sample Complexity of Learning Lipschitz Operators with respect to Gaussian Measures imp 20 / dev 60
Explainable Clustering of Mixture Models imp 30 / dev 70
DeltaGNN: Graph Neural Network with Information Flow Control imp 35 / dev 75
TSMini: A Simple Yet Highly Effective Trajectory Similarity Learning Model imp 30 / dev 65
Towards Efficient Parametric State Estimation in Circulating Fuel Reactors with Shallow Recurrent Decoder Networks imp 25 / dev 65
Deep Learning-Driven Peptide Classification in Biological Nanopores imp 30 / dev 70
WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation imp 35 / dev 70
Fractal and Chaotic Activation Functions in Echo State Networks: Preprocessing Topology Governs the Echo State Property imp 25 / dev 65
Forecast Skill Is Not Decision Skill: Evidence from Weather-Dependent Decision Tasks imp 30 / dev 65
Consensus Group Relative Policy Optimization for Text Generation imp 55 / dev 80
Brain4FMs: A Benchmark of Foundation Models for Electrical Brain Signal imp 45 / dev 75
Reservoir-Based Graph Convolutional Networks imp 30 / dev 75
The Geometry of Polynomial Group Convolutional Neural Networks imp 20 / dev 65
Advancing Subseasonal Forecasting with Machine Learning imp 50 / dev 80
Relocation of compact sets in $\mathbb{R}^n$ by diffeomorphisms and linear separability of datasets in $\mathbb{R}^n$ imp 10 / dev 40
Inducing Permutation Invariant Priors in Bayesian Optimization for Carbon Capture and Storage Applications imp 35 / dev 70
Inductive Venn-Abers and related regressors imp 20 / dev 65
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning imp 40 / dev 80
Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models imp 55 / dev 80
Optimal Data Acquisition for Reinforcement Learning: A Large Deviations Perspective imp 35 / dev 75
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing imp 50 / dev 80
Efficient Clustering with Quality Guardrails for LLM-based Recommender Systems at Industry Scale imp 55 / dev 85
Latent Fact-Checking: Detecting Misinformation through Activation Engineering imp 60 / dev 85
Boosting Data Augmentation with Stochastic Weight Averaging imp 40 / dev 75
ClosureBench: A Constructive Benchmark for Compositional Graph Reasoning imp 50 / dev 80
Across-Design Uncertainty in Short Pricing Panels: Inference and Identification imp 20 / dev 50
Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in Conversation imp 30 / dev 70
Canalization Before Generalization: Grokking as a Dynamical Probe imp 40 / dev 80
TACIT-Switch: Cost-Aware Model Escalation for LLM Agents from Censored Supervision imp 60 / dev 85
Stress-Testing Efficient Responsible-AI Evaluation: When Compute Savings Change Benchmark Conclusions imp 50 / dev 80
OR-Transformer: Scaling Real-Time Decision-Making to 1,000 Items imp 55 / dev 85
TrajMind: Chaining Role-Specialized LoRAs for Fast-and-Slow Collective Trajectory Anomaly Diagnosis imp 55 / dev 85
A Location-Invariant Estimator of Extremal Quantile Treatment Effects for Heavy-Tailed Distributions imp 20 / dev 60
GraphMend: Code Transformations for Fixing Graph Breaks in PyTorch 2 imp 60 / dev 90
Constrained Sensing and Reliable State Estimation with Shallow Recurrent Decoders on a TRIGA Mark II Reactor imp 25 / dev 70
Enhancing Affine Maximizer Auctions with Correlation-Aware Payment imp 20 / dev 60
Regularity of Second-Order Elliptic PDEs in Spectral Barron Spaces imp 25 / dev 70
Squint: Fast Visual Reinforcement Learning for Sim-to-Real Robotics imp 50 / dev 85
Nepali Passport Question Answering: A Low-Resource Dataset for Public Service Applications imp 20 / dev 55
Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers imp 30 / dev 75
SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control imp 55 / dev 85
Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills imp 65 / dev 85
Second-order consistency for learning chaotic dynamics via randomized Jacobian matching imp 30 / dev 75
Quantum Kolmogorov--Arnold representation theorem for continuous unitary-valued maps imp 25 / dev 70
Statevector-to-Hardware Reconstruction of a Four-Qubit ZZ Quantum Kernel: A Single-Backend Case Study of Three Execution Jobs imp 20 / dev 65
Automatic knot selection in smooth additive models imp 20 / dev 65
To Erase, or Not to Erase: Robust Training-Free Concept Erasure with Preservation aware Adaptive Ranked Subspace Expansion imp 55 / dev 85
Token-Level Advertising imp 45 / dev 75
An Integrated Vision-and-Language Pretraining (VLP) and Visual Question Answering (VQA) model to Automate Nondestructive Evaluation Image Analysis imp 30 / dev 70
Synthetic Worlds for Temporal Evaluation and Knowledge Updating in LLMs imp 55 / dev 85
Omega-N: Interpretable Structural Node Descriptors and Their Applicability Domain imp 20 / dev 60
SocialBuddy: Tailoring Search Agent for Social Scenarios imp 45 / dev 70
Counterfactual Fairness Audits of Multi-Step Clinical LLM Agents Require a Measured Per-Action Instability Floor imp 50 / dev 80
DTM: Deterministic Approaches for Black-box Test Suite Minimization with Tree-based Similarity imp 35 / dev 75
Breaking the Alphabet: Rethinking File Ordering in Code Review imp 30 / dev 70
AI Writes Code, Humans Pay the Debt. An Empirical Study on the Sustainability and Evolution of Agent-Generated Code imp 60 / dev 85
The Prompt Triangle: A Registered Report on Prompts as Hybrid Artifacts imp 55 / dev 80
SH-PDOPS: AI-Driven Cloud Native Enterprise Reliability Framework for Predictive Analytics and Intelligent DevOps Automation imp 40 / dev 75
Data-Related Challenges and Requirements for Event Log Generation in Process Mining: A Systematic Literature Review imp 25 / dev 60
Big Questions on Software Architecture: Report of the ICSE 2026 BoF on Software Architecture imp 40 / dev 75
Toward Model-Driven Digital Twin Configuration: Separating Structure Semantics and Runtime with SysML SAREF and Ditto imp 30 / dev 65
A Mixed-Method Empirical Study of LLM Assistance in Software Engineering Workflows imp 55 / dev 80
A systematic literature review on logging smell detection imp 35 / dev 75
Engineering as Code: Bringing Software Engineering Methodology to Engineering Design imp 50 / dev 75
A Governance Methodology Layer for AI-Assisted Software Development: Defect Taxonomy, Controlled Ablation, and Process-Over-Capability Evidence imp 70 / dev 85
Large Language Models for Fuzz Testing in Microservices: A Systematic Literature Review imp 50 / dev 80
Robustness and Trade-offs for Code LLMs on Protected Code imp 50 / dev 80
Automated Deployment of Real-Time Tasks for Phased Execution on Scratchpad-Based Multicore Platforms imp 25 / dev 75
Physics-Direct FPGA Tooth-Contact Computation for Deterministic Gear Digital Twins imp 20 / dev 70
Reviewer Capability Governs Rejection Targeting, Not Repair Skill: Evidence from LLM Execute-Review-Revise Pipelines imp 50 / dev 80
Integrating Crash Report Mining and LLMs for Bug Localization and Repair: An Industrial Report imp 55 / dev 80
An Empirical Analysis of CodeQL False Positives and Query Refinements for Java Vulnerabilities imp 45 / dev 75
Software Engineering in the Agent Era From Trustworthy Change to Human Agent Software Organizations imp 70 / dev 80
How Developers Discuss Generative AI: A Longitudinal Study of the Visual Studio Code Community imp 45 / dev 55
An Empirical Study on Learning Paths and Gender Dynamics in Scrum Master Roles imp 5 / dev 30
T(r)opical Islands: Visualizing & Understanding Socio-Technical Artifacts imp 15 / dev 50
Ritgard: T(r)opical Islands of Socio-Technical Artifacts on GitHub imp 15 / dev 50
CPL: A Compact C-like Systems Language with Explicit Low-Level Control imp 25 / dev 70
Adaptation Needs in Robotic Systems: Assessing Behavior Trees and Their Enhancement imp 20 / dev 70
Guiding AI to Fix Its Own Flaws: An Empirical Study on LLM-Driven Secure Code Generation imp 55 / dev 80
Evaluating Uncertainty and Quality of Vision-Language-Action-enabled Robots imp 20 / dev 55
EmoPyLab: A Tensor-Native, Hardware-Accelerated Laboratory for High-Throughput Benchmarking and Decision-Making in Multi/Many-Objective Optimization imp 20 / dev 70
The Unseen Delta: Characterizing the Compiler Optimization Landscape via Top-Down Differential Analysis imp 45 / dev 80
The Neglected Baseline in Model Interpretation imp 35 / dev 60
A faster way to convert a timestamp to Hour, Min, Sec imp 8 / dev 45
The shortest IPv6 addresses imp 8 / dev 40
It took a year to ship WebAssembly in Anubis imp 25 / dev 65
Two Tiny Utils for the Result Pattern imp 12 / dev 50
Internationalization and Localization imp 15 / dev 50
Python Iceberg imp 25 / dev 65
Rust debugging survey 2026 results imp 30 / dev 70
How well do agents use test/verification techniques? imp 55 / dev 70
Demystifying complex configurations imp 20 / dev 60
QBittorrent breaks out of sandbox to commit crimes imp 30 / dev 60
"Hammock Driven Development" (2010) imp 10 / dev 40
GEM for Linux provides a classic graphical desktop with windows, menus, dialogs & a 68K emulator imp 10 / dev 40
Following legal advice, the Nitter project will continue imp 15 / dev 30
What are you doing this week? imp 0 / dev 0
NetBSD 11 from scratch imp 20 / dev 60
What every kernel programmer should know about Jump Labels imp 28 / dev 70
Have the frontier labs mixed up AI safety and security? imp 35 / dev 45
Terence Tao on “prematurely solving [a maths] problem by purely AI-powered methods” imp 30 / dev 35
"Simple Made Easy" (2011) imp 10 / dev 40
Data races and the limits of ThreadSanitizer in C and Go imp 40 / dev 70
Debian Code Search: Fast TurboPFor with Go SIMD imp 25 / dev 70
Protecting Mission-Critical Data Beyond The SoC: Why Inline Memory Encryption… — NVDA Impact Analysis & Price Prediction imp 30 / dev 50
Intelligent Engineering: From Optimization To AI — NVDA Impact Analysis & Price Prediction imp 35 / dev 50
El desarrollo de software en la era de la IA: de escribir sintaxis a diseñar arquitectura imp 50 / dev 55
BizNode Pro: run up to 5 independent Telegram bots, each with its own identity, knowledge base, and AI persona imp 15 / dev 30
Chip Industry Week In Review — NVDA Impact Analysis & Price Prediction imp 25 / dev 35
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod — NVDA Impact Analysis & Price Prediction imp 55 / dev 65
A Practical Desk Workflow for Free AI Image Generator Drafts in 2026 imp 15 / dev 25
The Complete Guide to Agent-to-Agent Marketplaces in 2026 imp 70 / dev 65
‘NBA 2K27’ With NVIDIA DLSS 5 Leads 26 New Games Coming to GeForce NOW — NVDA Quantitative Valuation Record imp 12 / dev 25
I tested Pydantic AI for 3 days on saas.pet's content QA agent — here's the honest take imp 60 / dev 80
The model did the reverse-engineering. The validator was the hard part. imp 40 / dev 55
Your system prompt isn't instructions. It's data. imp 45 / dev 70
Changes to LLM pricing: Baidu and Tencent imp 20 / dev 35
Your Gaming PC Just Became an AI Powerhouse: Meet FreeToken! imp 35 / dev 55
Build a Local LLM Chatbot with Ollama and Python imp 25 / dev 60
Ollama Guide: Eigene KI lokal hosten statt Cloud-Abo – So geht's imp 20 / dev 55
Uncensored AI chat online: text without a moderation layer, and the honest limits imp 20 / dev 45
An LM Studio alternative for Mac that needs nothing installed imp 18 / dev 45
Run Qwen 3.6 without a GPU: the hosted route and what it costs imp 18 / dev 45
Use Hermes 3 405B online, in the browser or from any OpenAI-compatible client imp 18 / dev 45
Top 463 Sites to Buying Edu Emails for Student Discounts 2019 imp 0 / dev 0
I REALLY hope the new gemma 5 family sticks to the "chat model first" philsophy and doesn't fall into the Qwen trap imp 18 / dev 50
MiniCPM5-2B Release Day imp 35 / dev 65
After over a year of my nights and weekends, the Jenny app is done! imp 12 / dev 45
Are you running Qwen 3.8 27b or Qwen Flash Next? imp 12 / dev 55
9 easy steps for llama.cpp, a local model, Freecad (and pi coding agent) to generate solid objects that sound mechanically good and can be also be 3D printed/milled imp 20 / dev 65
DeepSeek-V4-Flash-Vision-Exp is amazing at creating game worlds! imp 18 / dev 40
New Benchmark: The Struggle Bench imp 22 / dev 65
Why are the SOTA open-weight models scoring (relatively) low scores on AA-Omniscience Index imp 18 / dev 55
How to squeeze out every last drop of your precious RAM on your Mac - Use iPhone mirroring imp 12 / dev 55
when will open source LLM catch up to Astra I wonder? imp 15 / dev 45
Higher acceptance length, slower prose: Ling’s n=1/2/3 MTP test on one Spark imp 15 / dev 55
tencent/EVIE-8B and EVIE-4.5B (High-Capacity Visual Document Retrieval) imp 30 / dev 65
The models are fine, our toolings and methods are shit. imp 12 / dev 45
little-coder vs just Pi imp 12 / dev 55
Qwen 3.8 Next Flash is really really REALLY verbose.. imp 12 / dev 45
Cybersecurity is local AI model's killer use case imp 50 / dev 65
Benchmarking calories evaluation with LLMs imp 18 / dev 45
Which models are you running on 32Gb VRAM (16+16) and 128Gb RAM? imp 12 / dev 55
Is anyone running dual GPUs with x570 or x870 Taichi? imp 12 / dev 60
Qwen Next on 24 + 64 GB VRAM? imp 12 / dev 55
Local LLMs and their use case on your specific hardware imp 18 / dev 65
Radeon RX 7900 GRE 16GB and RX 480 8GB Vulkan benchmarks llama.cpp imp 18 / dev 65
Easy local Copilot with VS Code and Lemonade imp 40 / dev 75
8 uncensored Qwen 3.8 27B variants, one base, 167 GPU hours - Abliterlitics imp 22 / dev 55
Weekly Hiring Thread imp 0 / dev 0
Just got laid off from Agentic AI Firm, So giving away my 3 years worth of LinkedIn content marketing playbook for Agentic AI for free imp 15 / dev 10
Here's a free tool to stop AI from forgetting anything !! imp 55 / dev 50
I gave an AI agent $50 and 24 hours to book meeting leads. It ended up roasting 40 founders, getting a 60% reply rate, and making $600. imp 40 / dev 65
If you were starting from zero with AI today, what would you actually learn first? imp 25 / dev 40
A 6-hour successful agent task isn’t really 6 hours of autonomy imp 65 / dev 85
Should agent frameworks define your agent? I’d love feedback on A11 imp 55 / dev 85
Nvidia CEO says "AGI has arrived" after GPT-6 Astra. Are we actually there, or are we moving the AGI goalpost again? imp 35 / dev 25
Astra Smokes Fable 5.1!! imp 25 / dev 35
Did Claude/Codex actually replace no-code tools, or am I missing the point? imp 45 / dev 85
What "production-ready" actually means, explained for founders who don't code imp 35 / dev 65
(Genuine Question) At what point does weird AI agent behavior become an actual security incident? imp 55 / dev 75
What are the most important concepts to know about AI for a software developer? imp 35 / dev 75
No idea if a script is going to cost me 20 cents or 20 dollars until it's finished imp 45 / dev 85
Open-weights LLMs vs frontier APIs: when to rent, when to own imp 55 / dev 90
Agents keep hitting the same wall: missing boring tools that are easy to plug in imp 55 / dev 85
What is one AI task you would trust completely, and one you would never trust AI with? imp 25 / dev 45
I want to take this to the next level imp 15 / dev 45
Our security team is suddenly very interested in prompt injection now that agents can take actions imp 65 / dev 90
Best free/open-source resources for building automated agents locally (24GB RAM + RTX 2060S)? imp 45 / dev 75
Ling 3.0 (on Nous) imp 25 / dev 45
Running AI agents on WhatsApp taught me why human-in-the-loop isn't optional. The platform itself punishes you for autonomy imp 55 / dev 85
Sistema automatizado de trade com metatrader 5 imp 25 / dev 55
Which security checks are actually missing from current AI agent APIs? imp 65 / dev 90
The purpose of DNS is to spread scams imp 0 / dev 0
There's No Limit to How Bad Code Can Get imp 15 / dev 75
Quoting Zach Kehs imp 5 / dev 15
Remind imp 25 / dev 35
Clipnote imp 20 / dev 35
Airuncode imp 45 / dev 85
Tucky imp 20 / dev 35
Assist imp 20 / dev 25
An Interview with Zhipu AI Co-founder Tang Jie by Qiushi Magazine - Geopolitechs imp 35 / dev 35
Tough choices ahead as the US pushes a global artificial-intelligence divide - Bruegel imp 50 / dev 25
Chen Danian’s AI Model Nearly Surpasses DeepSeek Within 3 Months Post Launch - eu.36kr.com imp 45 / dev 45
Every Major AI Model That Shipped in Six Weeks, From Kimi K3 to GPT-6 Astra - Memeburn imp 50 / dev 75
China's Development Model: Building a Sustainable Global Foundation for Shared Progress - eu.36kr.com imp 25 / dev 5
No Longer Follow, But Define: The "DeepSeek Moment" of China's Household Ventilators - eu.36kr.com imp 35 / dev 15
China's Open-Source AI Models Become the Global Backbone: Saudi Arabia, Japan, and Europe 'Wrap' Chinese Weights - finance.biggo.com imp 55 / dev 75
AI Cyberattack Capabilities Reach 'Critical' Level… OpenAI and Anthropic Restrict Access, While South Korea Moves at a 'Snail's Pace' - finance.biggo.com imp 65 / dev 75
The AI threat has eclipsed sci-fi - eKathimerini.com imp 35 / dev 35
OpenAI rolls out GPT-6 Astra - TahawulTech.com imp 45 / dev 80
Year-End Bitcoin Price Bets Get Wild as 11 AI Models Target up to $105K - Cryptonews.net imp 10 / dev 5
Canva Turns AI Chatbots into Growth Engines - varindia.com imp 30 / dev 35
How To Use SpaceXAI's Grok Build - Engadget imp 25 / dev 35
Tesla Optimus, Grok, and TSLA Stock: Inside the Physical-AI Bet That Now Defines Tesla - InvestorPlace imp 35 / dev 35
DW News. . Elon Musk's AI chatbot Grok is facing lawsuits over alleged AI-generated child sexual abuse material. Now, a new lawsuit makes an even more serious claim. #dwdigital - facebook.com imp 50 / dev 25
Musk-Backed xAI Plans Doosan Power Plant - Businesskorea imp 35 / dev 10
ChatGPT, Claude and Grok Stopped Working. Here’s Why - Memeburn imp 40 / dev 45
GROK $0.0{5}8536 | Live GROK Price Chart Today, Swap on USDT | MEXC - mexc.co imp 0 / dev 0
Elon Musk Grok AI Predicts a Possible Solana Supercycle by 2027 - 99Bitcoins imp 10 / dev 5
RTX 5090でllm-jp-4-33b-thinkingをEXL3量子化・評価した2日間の振り返り imp 0 / dev 90 (いいね相当スコア: 0)
Langfuse v3 から v4 への移行で、既存のトレースと親子関係はどう変わるのか imp 0 / dev 85 (いいね相当スコア: 2)
【SALT2 エンジニアリング勉強会】ワークフローからAI Agentへ：仕事を任せるための境界と検証の設計 imp 0 / dev 90 (いいね相当スコア: 1)
AIに却下済みの設計を3回蒸し返されたので、「前例」を配るMCPサーバーを作った imp 0 / dev 90 (いいね相当スコア: 0)
2026年9月版：主要LLM 料金・スペック・共通ベンチマーク比較 imp 0 / dev 85 (いいね相当スコア: 2)
【2026年版】生成AIを学ぶための51冊 ― LLM・RAG・AIエージェント・LLMOps・Physical AIまで imp 0 / dev 75 (いいね相当スコア: 0)
自然言語仕様をコンパイルする──Compile by Trainingで再利用可能な神経関数を生成する imp 0 / dev 90 (いいね相当スコア: 0)
Pythonで作るAIエージェントのTools入門 imp 0 / dev 85 (いいね相当スコア: 取得失敗)
Agentic Loopをゼロから組んでみる imp 0 / dev 90 (いいね相当スコア: 1)
AI彼女アプリを作っていて気付いた。どうやら時代が追いついてきた imp 0 / dev 55 (いいね相当スコア: 1)
Astraの正直さを測るテストに、空欄の答案を出してみた imp 0 / dev 85 (いいね相当スコア: 0)
クレカ不要の無料LLM APIを実運用する — レート制限の読み方とフォールバック設計 imp 0 / dev 85 (いいね相当スコア: 0)
ローカルAIに仕事を回す仕組みが、3週間動いていなかった imp 0 / dev 90 (いいね相当スコア: 0)
Geminiをアップデートしたら、日本語PDFの品名だけが消えた imp 0 / dev 85 (いいね相当スコア: 9)
Prompt Steering Replacement: プロンプトによる介入をSteering Vectorで置き換える imp 0 / dev 90 (いいね相当スコア: 0)
欲求は知能をどう駆動するか——進化が作った人間の動機と、AI時代の新しい適応 imp 0 / dev 75 (いいね相当スコア: 0)
AIは、そこにある関数をもう一度書く — RepoExecが測った「依存を再利用する力」 imp 0 / dev 90 (いいね相当スコア: 1)
量子化LLMのtokens/sだけでは見えないCTIRとE2E latency imp 0 / dev 90 (いいね相当スコア: 0)
RAGの心臓部 — Embeddingとベクトル検索で「意味」を捉える imp 0 / dev 85 (いいね相当スコア: 0)
ログ肥大・トークン制限・パース失敗 ― ループを回し続けると必ず出会う3つの壁 imp 0 / dev 90 (いいね相当スコア: 0)
Peyman Milanfar「A Lagrangian View of Flow Matching」を読む imp 0 / dev 75 (いいね相当スコア: 0)
Jaffray Woodriffから学ぶSystematic Trading imp 0 / dev 35 (いいね相当スコア: 1)
メーターの数字は、写真だけでは読めない imp 0 / dev 65 (いいね相当スコア: 0)
誤差逆伝播を「触って」理解する — 数字が動くまで、式は腑に落ちない imp 0 / dev 75 (いいね相当スコア: 2)
TimesFM 3をColabで試す：関連データや予定を足すと予測は変わる？ imp 0 / dev 75 (いいね相当スコア: 2)
YOLO26nアーキテクチャ徹底解析 step2 | Conv, DWConv, PWConv ブロック imp 0 / dev 85 (いいね相当スコア: 0)
🐔ナナフシからロボットの歩き方を学ぶ imp 0 / dev 75 (いいね相当スコア: 1)
BigQuery ML × 時系列モデルARIMA_PLUSでEC売上の週次予測を自動化する imp 0 / dev 80 (いいね相当スコア: 0)
GPT-2-likeからQwen2-likeへの実験：第3回絶対位置EmbeddingをRoPEに変える imp 0 / dev 90 (いいね相当スコア: 3)
FXのトレンド発生は予測できる？EURUSD・15分足を全足検証 imp 0 / dev 55 (いいね相当スコア: 0)
音声AIで「考えるほど無言になる」を防ぐ：推論コストをターン別に振り分けるTypeScript実装 imp 0 / dev 90 (いいね相当スコア: 0)
ClaudeがLeanでフェルマーの最終定理を11日間の自律実行で完全形式化証明 imp 0 / dev 75 (いいね相当スコア: 0)
LLMの思考能力向上：推論時コンピュートの仕組みと活用戦略 imp 0 / dev 90 (いいね相当スコア: 0)
【備忘録】Hermes AgentでGPT-5.6系をCodex OAuth経由で利用する際のProvider指定メモ imp 0 / dev 65 (いいね相当スコア: 0)
ARIMAモデルをJavaScriptでスクラッチ実装した imp 0 / dev 80 (いいね相当スコア: 0)
才能にたよらない耳コピ -- ８年ぶりのAI対決 imp 0 / dev 65 (いいね相当スコア: 0)
dera AI Weekly Vol.47 — 2026/9/7 imp 0 / dev 65 (いいね相当スコア: 0)
AIというラベルでは責任は決まらない / 中国最高人民法院のAI紛争裁判規則雑感 imp 0 / dev 20 (いいね相当スコア: 取得失敗)
生成AIと児童保護法制 / 規範を先に書く者 / 自主的枠組みと測定可能性雑感 imp 0 / dev 25 (いいね相当スコア: 取得失敗)
通信量はAI英会話でどれくらいか。音声処理が端末とサーバーのどちらで走っているかで決まる imp 0 / dev 40 (いいね相当スコア: 取得失敗)
第五話「疲れている人に5000文字の励ましを送ってはいけない」 imp 0 / dev 30 (いいね相当スコア: 取得失敗)
レッドラインは何を禁じるのか / AI自己申告と独立検証 / 2026年という期限雑感 imp 0 / dev 25 (いいね相当スコア: 取得失敗)
AIの安全性と法 / 監視可能性の逓減 / 安全基準を誰が引くのか雑感 imp 0 / dev 30 (いいね相当スコア: 取得失敗)
海外におけるAI保険動向 / 助言から行為へ / AI免責条項の拡大と保険募集該当性雑感 imp 0 / dev 20 (いいね相当スコア: 取得失敗)
自動運転と法 / 介入データから交通規則を学ぶ自動運転 / 継続学習と時点固定型規制の距離雑感 imp 0 / dev 30 (いいね相当スコア: 取得失敗)
もっともらしさの出どころ / ウェアラブル健康推論ベンチマーク雑感 imp 0 / dev 25 (いいね相当スコア: 取得失敗)
情報の規制から関係の規律へ / 米国12州コンパニオンボット法雑感 imp 0 / dev 25 (いいね相当スコア: 取得失敗)
トルコのAIガバナンス / 調達要件としての基本的人権影響評価 / トルコ2026-2030年AI行動計画へのCAIDP意見 imp 0 / dev 20 (いいね相当スコア: 取得失敗)
推論モデル時代のエージェント設計：テスト時計算量とツールの融合 imp 0 / dev 90 (いいね相当スコア: 取得失敗)
2026-09-06 Hacker News Top 10 imp 0 / dev 75 (いいね相当スコア: 取得失敗)
【生成AIニュース+】『OrcaRouter Qwen3.8-27B-Uncensored』『Lightning v3.1 Pro』『Shot Composer』『ComfyUI-Ref2VA-VSA』『NaughtyTimes-MiniMax-H3』『ComfyUI MiniMax H3 NegPiP』『Poppy』『Iris』『Blender Cascadeur RT』『screenwriting-skills』『Qwen3.8-Flash-Next-DS4-IQ2』『Hypershell Halo』 imp 0 / dev 50 (いいね相当スコア: 取得失敗)
nanochat#8 GPT-2の点数は 0.256525 だった imp 0 / dev 60 (いいね相当スコア: 取得失敗)
今さら聞けないAI用語｜「生成AI」と「LLM」は何が違う？ imp 0 / dev 25 (いいね相当スコア: 取得失敗)
Gemini3.8Flashってすごくないか？ imp 0 / dev 50 (いいね相当スコア: 取得失敗)
もう他人事じゃない！AGIと自立型AIがもたらす社会のパラダイムシフト imp 0 / dev 15 (いいね相当スコア: 取得失敗)
教えていないのに生えたもの（Opus4.6） imp 0 / dev 30 (いいね相当スコア: 取得失敗)
毎日エラーゼロのAI自動化パイプラインが実は週5日しか動いていなかった imp 0 / dev 75 (いいね相当スコア: 取得失敗)
【パンダ船長の技術航海-7号】（令和8年08月17日）観測は、失敗を誰のせいだと記録するか――原因の帰属と出所の証明 imp 0 / dev 30 (いいね相当スコア: 取得失敗)
ああ、女神（AI）さま imp 0 / dev 10 (いいね相当スコア: 取得失敗)
【GPT-6 Astra解読】AIが「思考を隠し始めた」――史上初のサイバーCritical到達と開発現場が知るべき多層防御 imp 0 / dev 75 (いいね相当スコア: 取得失敗)
語彙力も表現力もこれ一つ！GPT-6 Astraでリサーチの質を爆上げする方法 imp 0 / dev 55 (いいね相当スコア: 取得失敗)
コーナーだけ減速？Fusionの送り最適化を使い直す｜Fusion CAM imp 0 / dev 15 (いいね相当スコア: 取得失敗)
インターンシップ選考に落ちたら、その会社はもう受からない？～26卒データサイエンティストがインターンシップ選考の見送りから、本選考で内定をつかむまで～ imp 0 / dev 5
巨大オンラインゲーム「EVE Online」。ゲームを支える240万行のPython 2.7のコードをPython 3へ移行すると発表 imp 35 / dev 70
HTMX 4.0正式リリース。内部実装がXHRからfetchに移行しStreaming HTMLが可能に、属性はデフォルトで子要素に継承されないように変更など imp 40 / dev 75
VS Code誕生から現在までの物語「The Story of VS Code」YouTubeで公開。作者のエリック・ガンマ氏はなぜIBMからMSへ移籍してVS Codeを作ることになったか imp 30 / dev 70
JavaScriptをC言語にコンパイルする「porffor」がアルファ版に到達。ネイティブやWASMを生成可能 imp 40 / dev 75
社長の考えをいつでも聞ける！AIコジーを社内公開 imp 50 / dev 45

AI News Digest 2026-09-08

台本で使った記事

特集

開発者コーナー

中堅コーナー

AIツール紹介コーナー

速報コーナー

参考記事一覧