LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-Training Paper • 2605.29888 • Published 25 days ago • 34
Revisiting the Uniform Information Density Hypothesis in LLM Reasoning Traces Paper • 2510.06953 • Published Oct 8, 2025 • 9
Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs Paper • 2506.09522 • Published Jun 11, 2025 • 21