The 2026 PNPL Competition： Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100

RISE： Recursive Improvement via Self-Extrapolating Policy Distillation

Refuse without Refusal： A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models

WorldSculpt： Generating Compositional Worlds from Grounded Videos

UniMate： One Unified Model to Animate Diverse Skeletons

Knowing What Not to Answer： Selective Non-Compliance in Vision-Language Models

Don't Drop Dropout： Optimizing Layer Sparsity for Efficient LLM Training and Inference

Beneath the Surface of Chains-of-Thought： A Mechanistic Interpretation of Reasoning Operations in LLMs

Ask Before You Optimize： Dynamic Pre-Formulation Clarification for Interactive Optimization

MaxKernel： Agentic Kernel Generation for TPUs

When Models Edit Too Much： On the Fidelity of Minimal Code Edits