6 papers
Agentic Critical Training
Weize Liu, Minghui Liu, Sy-Tuyen Ho +3
Training large language models (LLMs) as autonomous agents often begins with imitation learning, but it only teaches agents what to do without understanding why: agents never contr…
Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding
Yongyuan Liang, Xiyao Wang, Yuanchen Ju +2
Scaling large multimodal models (LMMs) to 3D understanding poses unique challenges: point cloud data is sparse and irregular, existing models rely on fragmented architectures with…
ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
Yongyuan Liang, Wei Chow, Feng Li +7
Unified multimodal models (UMMs) have emerged as a powerful paradigm for seamlessly unifying text and image understanding and generation. However, prevailing evaluations treat thes…
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning
Zikui Cai, Andrew Wang, Anirudh Satheesh +10
Despite rapid advances in vision-language models (VLMs), current benchmarks for multimodal reasoning fall short in three key dimensions. First, they overwhelmingly rely on static i…
SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
Xiyao Wang, Zhengyuan Yang, Chao Feng +6
We introduce ThinkLite-VL, a family of visual reasoning models that achieve state-of-the-art (SoTA) performance using an order of magnitude fewer training samples, relying purely o…
Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning
Xiyao Wang, Linfeng Song, Ye Tian +5
Monte Carlo Tree Search (MCTS) has recently emerged as a powerful technique for enhancing the reasoning capabilities of LLMs. Techniques such as SFT or DPO have enabled LLMs to dis…