Learning to Align Multi-Faceted Evaluation: A Unified and Robust Framework Paper • 2502.18874 • Published Feb 26
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning Paper • 2506.01939 • Published Jun 2 • 185
LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling Paper • 2505.19187 • Published May 25 • 13
Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States Paper • 2505.17663 • Published May 23 • 15
Why Safeguarded Ships Run Aground? Aligned Large Language Models' Safety Mechanisms Tend to Be Anchored in The Template Region Paper • 2502.13946 • Published Feb 19 • 10
RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning Paper • 2310.13864 • Published Oct 21, 2023 • 1
ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning Paper • 2306.06466 • Published Jun 10, 2023
ICON: Improving Inter-Report Consistency of Radiology Report Generation via Lesion-aware Mix-up Augmentation Paper • 2402.12844 • Published Feb 20, 2024
When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection Paper • 2402.13276 • Published Feb 17, 2024
Integrative Decoding: Improve Factuality via Implicit Self-consistency Paper • 2410.01556 • Published Oct 2, 2024
Subtle Errors Matter: Preference Learning via Error-injected Self-editing Paper • 2410.06638 • Published Oct 9, 2024