AI News

Theoretical and Practical Advances in Hierarchical Bayesian Deep Learning Methodology (arxiv.org)

Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models (arxiv.org)

Refined Topology-Pass Scheduling: Damped Trust-Region Compensation for Dynamic k-NN Graphs in SE(3)-Equivariant Structure Prediction (arxiv.org)

Does a Governed Confidence Score Know When a Text-to-SQL Answer Is Right? An Exploratory Study on BIRD and a Pre-registered Confirmation on Spider (arxiv.org)

Beyond Aggregate Accuracy: Item-Level Transitions in Prompt Optimization (arxiv.org)

TRACER: Trace-Regularized Training Against Indirect Prompt Injection (arxiv.org)

Contextual Credit Policy Optimization (arxiv.org)

Genesis Steering: Better Activation Steering Through Training Data (arxiv.org)

Which Metadata Matters for LLM Tool Selection in MCP? Evidence from Controlled Factor-Level Interventions (arxiv.org)

Harness^2: Recursive Agent Harnessing for an Open World (arxiv.org)

Echo: Error-Compensated 4-Bit Tensor-Parallel Communication for LLM Training and Inference (arxiv.org)

Controllable Diverse Sampling through Pullback Directions (arxiv.org)

ConicFlow: constrained Inference-time optimal control for flow matching models (arxiv.org)

Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP Trimming (arxiv.org)

Actionable Meta-Requirements for AI Robustness Auditing (arxiv.org)

MA-Bench: Measuring Operational Planning in Language Models (arxiv.org)

Towards Training and Inference of Graph Neural Networks in Graph Databases (arxiv.org)

Demystifying On-Policy Distillation: Where Does the Teacher's Advantage Live? (arxiv.org)

Diagnosing Low-Confidence Patient Profiles via Localized Harmful Covariate Shift Detection (arxiv.org)

PairIT: Autoregressive Transformers for Low-Data Molecule Optimization (arxiv.org)

When Pleasing the User Compromises Care: AI Sycophancy in Caregiver-Mediated Healthcare (arxiv.org)

ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence (arxiv.org)

ANASSA: From High-Level Framework to Low-Level Architecture for Spatial Agentic AI (arxiv.org)

Variance-Optimal State Resampling for Reinforcement Learning with Verifiable Rewards (arxiv.org)

ProtModernBERT: Compute-Efficient Protein Language Modeling (arxiv.org)

CAST: History-Adaptive Spectral Clipping for LLM Pretraining (arxiv.org)

Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers (arxiv.org)

FinGREAT: Evaluating LLMs on Financial Graph-guided Retrieval And Typing (arxiv.org)

One Size Does Not Fit All: Curvature-Aware Adaptive Perturbation for SAM (arxiv.org)

OrionMoE-v1.0: A Mixture-of-Experts Foundation Model for Tabular In-Context Learning (arxiv.org)

Continual Learning for Reliable In-Sequence Molecular Communication (arxiv.org)

Can We Trust This Evaluation? Instance-Level Reliability of LLM-as-a-Judge (arxiv.org)

Rotate the Loop: Blockwise Conformality for Looped Transformers (arxiv.org)

The Accuracy Well: Nonmonotone Accuracy Dynamics at Vanishing Initialization (arxiv.org)

EarthAlign: Learning Language-Aligned Representations of Earth System Data (arxiv.org)

Prospective Forcing: Learning to Look Ahead for Autoregressive Long Video Diffusion (arxiv.org)

DexCast: Learning Real-World Dexterous Control from Human Videos (arxiv.org)

AlignAudio: A Unified Dual-Alignment Framework for Noise-Robust Speech-Conditioned Generation (arxiv.org)

Self-improving data synthesis can scale embedding models across domains and tasks (arxiv.org)

Learning by Examples: Power Grid Steady State Analysis with a Tabular Foundation Model (arxiv.org)

Selective Growing Q-Networks (SGQN): An Analysis of Adaptive Action Grids in Decoupled Q-Learning (arxiv.org)

Decoupled Marginal Sharpening for Training-Free Inference-Time Scaling (arxiv.org)

Hindsight-Privileged RLVR: Single-Rollout Token Credit Without Group Sampling (arxiv.org)

Graph-Enhanced Disease Trajectory Discovery and Temporal Endpoint Forecasting from Longitudinal Electronic Health Records (arxiv.org)

A Two-Level Clinical Novelty Prioritization Framework for Disease Trajectories Discovered from Longitudinal Electronic Health Records (arxiv.org)

Towards Merging-conditional Backdoor Unalignment against Large Language Models (arxiv.org)

Lingdan-V2: Large language models for clinically grounded reasoning in traditional Chinese medicine (arxiv.org)

Vela: User Behavior as Supervision Sparks LLM Intelligence (arxiv.org)

Integrating AIRL-Based Reward Estimation into a Control Method Using Fuzzy Inference and Policy Gradient (arxiv.org)

Forget About It: Mitigating Forgetting Without Replay or Auxiliary Objectives (arxiv.org)