AI News

Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh (arxiv.org)

Epistemic Norms for AI Safety and Alignment Research (arxiv.org)

MixQuant: Adaptive Mixed-Precision Quantization for Large Language Models (arxiv.org)

DeepLook: Deeper Thinking with Lookahead (arxiv.org)

Adaptive Multi-Scale Forecasting and Gate-Localized Conformal Prediction for Multivariate Nonstationary Time Series (arxiv.org)

Reasoning or Memorization: Can LLMs Understand and Generate Chinese Xiehouyu Riddles? (arxiv.org)

Hierarchical Reinforcement Learning with Optimal Level Synchronization Based on Flow-Based Deep Generative Model (arxiv.org)

Robust Conformalized Selection with Noisy Responses (arxiv.org)

Learning to Optimize: Joint Routing and Flow Allocation on Sparse Non-Euclidean Networks (arxiv.org)

Hierarchical Group-Conditional Conformal Risk Control for Selective Prediction in Language Models (arxiv.org)

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

Hybrid Advantage Estimation with Unified Critic for VLM Agentic Reinforcement Learning (arxiv.org)

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

TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law (arxiv.org)

Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses (arxiv.org)

Certified Parallel-in-Time Sinkhorn for Dynamic Entropic Optimal Transport (arxiv.org)

Cross-Attention Calibrated Deduplication for Retrieval-Augmented Generation System (arxiv.org)

Choosing a Text Embedding Model: A Practical Benchmarking and Decision Framework (arxiv.org)

The Equalizer: Introducing Shape-Gain Decomposition in Neural Audio Codecs (arxiv.org)

Group Preference Collapse in Personalized Multimodal Large Language Models (arxiv.org)

Online Policy Evaluation for MDPs with Dynamic UBSR Measures (arxiv.org)

Real2Sim2Real for Vision-Language-Action Manipulation: An AMD ROCm-Based Pipeline (arxiv.org)

Distribution-Specific Curvature Control with Finite-Sample Guarantees for Open-Weight Safety (arxiv.org)

Short-Term Pain for Long-Term Gain: Adaptive Experiment with Post-Commitment Reward Shift (arxiv.org)

An Explicit Counterexample to Stanley's Rankwise Lower-Bound Conjecture for Differential Posets (arxiv.org)

HALLELUAI: A Hallucination-Aware AI System for Ultra-Realistic Image-to-Video Generation at Scale (arxiv.org)

Beyond ICA: Identifiability by Symmetry Breaking (arxiv.org)

A Fixed-Effects Causal Forest for Staggered Adoption, with an Application to Medicaid Expansion (arxiv.org)

Context-Adaptive Inference: A Unified Statistical and Foundation-Model View (arxiv.org)

Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions (arxiv.org)

A Vocabulary for Multi-Agent Automated Research Systems (arxiv.org)

TLRNet: Estimating Individual Treatment Effect based on Local Information and Single Learner Structure (arxiv.org)

A New Kind of Adversarial Example: Measuring the Human-Model Gap, and Its Relationship to OOD Detection (arxiv.org)

Logit-Coordinate Generative Models for Mixed Continuous-Categorical Tabular Data (arxiv.org)

Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV (arxiv.org)

Minimax Lower Bounds of Kernel Discrepancy Estimation: MMD, HSIC, KSD (arxiv.org)

Separating Capability from Permission: A Governance Framework for Agentic AI Autonomy Levels (arxiv.org)

Do LLMs Know Their Vulnerable Scenarios? (arxiv.org)

Discrepancy-Rounded Fair Bandits with Static and Time-Varying Exposure Floors (arxiv.org)

Delegation Intelligence in Deep Search: A Controllable Framework for Disentangled Capability Diagnosis (arxiv.org)

Context-Aware Concept Distillation for Trustworthy Flood Prediction (arxiv.org)

StageGuard: Physiologically Constrained Sleep Staging (arxiv.org)

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

SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problems (arxiv.org)

Verification-Notebook Learning for Source-Aware Multimodal Misinformation Detection (arxiv.org)

Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents (arxiv.org)

On Non-Stationary Dynamic Pricing: Adaptivity and Optimality (arxiv.org)

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

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

Label-free Industrial Fault Detection via Adversarial Inverse Reinforcement Learning: A System for Run-to-Failure Prognostics (arxiv.org)