AI News

Evaluating Large Language Models for Symbolic Security Protocol Analysis (arxiv.org)

Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS (arxiv.org)

Covariance Last-Layer Ensembles: Function-Space Diversity for Efficient Uncertainty Quantification (arxiv.org)

Masked Distillation: Internalizing the Chain-of-Thought in Language Models (arxiv.org)

Same Question, Different Answers: Evaluating LLM Reliability Beyond Accuracy (arxiv.org)

Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems (arxiv.org)

SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads (arxiv.org)

Recycling computational processes of dynamic programming for combinatorial optimization problems: a reservoir computing approach (arxiv.org)

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding (arxiv.org)

Physics-Guided Generative AI for Property-Targeted 3D Porous Media Design (arxiv.org)

ObsDriveBench: Benchmarking Multimodal Understanding under Adverse Weather with Observability Awareness (arxiv.org)

Multi-Agent Privacy Game in Federated Learning: A Unified Mean-Field View (arxiv.org)

Fisher Information based Stochastic Gradient Ascent for Online Learning of Dirichlet Process Mixture and Theory (arxiv.org)

SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series (arxiv.org)

LanteRn: Latent Visual Structured Reasoning (arxiv.org)

Robust Inference Methods for Latent Group Panel Models under Possible Group Non-Separation (arxiv.org)

Low-Rank Dependence Decomposition via Accelerated Symmetric Non-negative Matrix Factorization (arxiv.org)

Risk reversal for least squares estimators under nested convex constraints (arxiv.org)

WISERouter: LLM Routing with Workload Budget Constraint (arxiv.org)

No Optimal Language Set Exists for Multilingual Instruction Tuning: Insights from a Linguistically-Informed Study (arxiv.org)

MemTX: Transactional Belief Commit for Stateful Agent Memory (arxiv.org)

Physics-Informed Neural Networks for Discovering Periodic Orbits in the Gravitational Three-Body Problem (arxiv.org)

Learning Sampling Parameters for Diffusion Models (arxiv.org)

Predicting the Outcome of rTMS Depression Therapy using EEG Signals and CNN (arxiv.org)

Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory (arxiv.org)

The Intruder Threshold: A Spectral Law for LoRA Fine-Tuning (arxiv.org)

PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation (arxiv.org)

Adaptive Data Admission and Retention for Streaming Federated Learning (arxiv.org)

Capacity-Aware Deep Learning for Generalizable Traffic Volume Estimation Across Links and Cities (arxiv.org)

How LLM Task-Adaptation Reshapes Alignment: A Multi-dimensional Study of Behavioral and Representational Drift (arxiv.org)

Variable Importance Identification Through Lazy Training for Binary Classification (arxiv.org)

Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries (arxiv.org)

Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness (arxiv.org)

DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models (arxiv.org)

EmotionAI: A Privacy-Preserving Computational Intelligence Pipeline for Speech-Emotion-Grounded Conversational Analysis (arxiv.org)

In-Context Learning as Implicit Policy Gradient (arxiv.org)

XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Space (arxiv.org)

Bit-Accurate FPGA Evaluation of Learned Feature Gating in a Fixed-Point Fourier-Feature Automatic Modulation Classifier (arxiv.org)

Real-time Reconstruction of Human Visual Perception from fMRI (arxiv.org)

StanceFlip: A Comprehensive Multi-Dimensional Benchmark for Multimodal Conversational Stance Flipping Forecasting (arxiv.org)

Synthetic Scenario Generation for Evaluation of Industry 4.0 Agents (arxiv.org)

Success Is Not Self-Explanatory: Auditing Success Provenance in Agent Evaluation (arxiv.org)

GFLAN: Generative Functional Layouts (arxiv.org)

Scaling GUI Agents with Visual State Transitions (arxiv.org)

Self-Supervised Consistency Enhanced Disentangled Learning for Neural Decoding Generalization in Brain-Machine Interface (arxiv.org)

MiSS: A Logic-Driven Explanation of Minimal Sufficient Coalitions for Point Cloud Classifiers (arxiv.org)

Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning (arxiv.org)

Neural Network-Driven Volatility Drag Mitigation under Aggressive Leverage (arxiv.org)

FlowCTS: On-policy Continuous Trajectory Supervision of Flow Models (arxiv.org)

On the Impossibility of Unbiased and Length-Invariant Policy Optimization with Outcome Rewards (arxiv.org)