11 papers
Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation
Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3
Outcome verifiers score completed reasoning traces but do not assign credit to intermediate tokens. Privileged self-distillation attempts to fill this gap by rescoring a model's ow…
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Ye Liu, Srijan Bansal, Bo Pang +6
Reinforcement learning with verifiable rewards (RLVR), along with recent selfdistillation variants such as SDPO, evaluates each rollout against a verifier and updates the policy fr…
Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning
Xuanzhi Feng, Zhengyang Li, Zeyu Liu +6
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced Large Language Model (LLM) reasoning; however, it faces a fundamental optimization instability: uni…
ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models
Liyan Tang, Grace Kim, Xinyu Zhao +12
Chart understanding presents a unique challenge for large vision-language models (LVLMs), as it requires the integration of sophisticated textual and visual reasoning capabilities.…
LingLanMiDian: Systematic Evaluation of LLMs on TCM Knowledge and Clinical Reasoning
Rui Hua, Yu Wei, Zixin Shu +33
Large language models (LLMs) are advancing rapidly in medical NLP, yet Traditional Chinese Medicine (TCM) with its distinctive ontology, terminology, and reasoning patterns require…
A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
Siyang Jiang, Mu Yuan, Xiang Ji +12
Multimodal human action recognition (HAR) leverages complementary sensors for activity classification. Beyond recognition, recent advances in large language models (LLMs) enable de…