AI News

FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement (arxiv.org)

When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models (arxiv.org)

Attention Calibration for Position-Fair Dense Information Retrieval (arxiv.org)

OpenAgenet/OAN: Technical Architecture for Trust-Governed Agent Identity and Discovery (arxiv.org)

Formalizing the Binding Problem (arxiv.org)

Attribution via Distributional Paths for Information Revelation (arxiv.org)

MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency (arxiv.org)

Reproducibility is the New Copyleft: Defining AGI-oriented Reproducible Builds (arxiv.org)

Multi-component Causal Tracing in Large Language Models (arxiv.org)

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis (arxiv.org)

Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing (arxiv.org)

Fast and Expressive Multi-Byte Prediction with Probabilistic Circuits (arxiv.org)

VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring (arxiv.org)

R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks (arxiv.org)

DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting (arxiv.org)

Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery (arxiv.org)

Outsmarting the Chameleon: Counterfactual Decoupling for Tactical OOD Shifts in Live Streaming Risk Assessment (arxiv.org)

Curriculum-Adapted Robust Reinforcement Learning for UAV Deconfliction in Adversarial Environments (arxiv.org)

Building Trust in Black-box Optimization: A Comprehensive Framework for Explainability (arxiv.org)

Scalable On-Hardware Training of Quantum Neural Networks and Application to Clinical Data Imputation (arxiv.org)

State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation (arxiv.org)

Planning with Uncertainty: Symmetries, Policy Inference, and Solution Compression (arxiv.org)

PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models (arxiv.org)

DiffUNet^2: Bidirectional Prediction, Probabilistic Generation and Collaborative Visual Discovery for Scientific Data (arxiv.org)

Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs (arxiv.org)

Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors (arxiv.org)

EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement (arxiv.org)

Trans GAN-WT: A Feature Extraction and Interactive Learning-Based Anomaly Detection Model for Wind Turbine Time Series Data (arxiv.org)

LAMP: Data-Efficient Linear Affine Weight-Space Models for Parameter-Controlled 3D Shape Generation and Extrapolation (arxiv.org)

Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing (arxiv.org)

Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-Judge (arxiv.org)

Correcting Neural Operator Spectral Bias via Diffusion Posterior Sampling with Sparse Observations (arxiv.org)

Learn from Your Mistakes: Tree-like Self-Play for Secure Code LLMs (arxiv.org)

FlowGuard: Flow Matching for Identity-Independent Detection of Data-Free Model Stealing Attacks on Energy System Intrusion Detection Systems (arxiv.org)

SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation (arxiv.org)

AirDreamer: Generalist Drone Navigation with World Models (arxiv.org)

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs (arxiv.org)

Finding Kissing Numbers with Game-theoretic Reinforcement Learning (arxiv.org)

Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in Multiple Sclerosis (arxiv.org)

From 'What' to 'How' and 'Why': Sharing LLM-Generated Retrospective Summaries of Older Adults' Passive Tracking Data with Remote Family Members (arxiv.org)

BotDirector: Robot Storytelling Across the Symmetrical Reality with Multi-modal Interactions (arxiv.org)

Resource-Constrained Adaptive Inference for Sequential Pricing (arxiv.org)

OpenAgenet/OAN: Open Infrastructure for Trusted Agent Interconnection (arxiv.org)

ParaBlock: Communication-Computation Parallel Block Coordinate Federated Learning for Large Language Models (arxiv.org)

Bregman meets L\'evy: Stochastic mirror descent with heavy-tailed noise in continuous and discrete time (arxiv.org)

Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories (arxiv.org)

FlashbackCL: Mitigating Temporal Forgetting in Federated Learning (arxiv.org)

TIDFormer: Exploiting Temporal and Interactive Dynamics Makes A Great Dynamic Graph Transformer (arxiv.org)

LEAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks (arxiv.org)

Online Learning with Gradient-Variation Interval Regret (arxiv.org)