5 papers
SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
Yang Zhou, Zixuan Huang, Sunzhu Li +10
Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions based on that r…
RubricHub: A Comprehensive and Highly Discriminative Rubric Dataset via Automated Coarse-to-Fine Generation
Sunzhu Li, Jiale Zhao, Miteto Wei +6
Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation rem…
Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment
Zhiyu Lin, Jingwen Yang, Jiale Zhao +3
Recent speech-to-speech (S2S) models generate intelligible speech but still lack natural expressiveness, largely due to the absence of a reliable evaluation metric. Existing approa…
ThinkPilot: Steering Reasoning Models via Automated Think-prefixes Optimization
Sunzhu Li, Zhiyu Lin, Shuling Yang +2
Large Reasoning Models (LRMs) are powerful, but they still suffer from inefficient and off-target reasoning. Currently, training-free methods are limited to either rigid heuristics…
Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning
Yang Zhou, Sunzhu Li, Shunyu Liu +11
Recent advances in Large Language Models (LLMs) have underscored the potential of Reinforcement Learning (RL) to facilitate the emergence of reasoning capabilities. Despite the enc…