activity
20192026
most citedCal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

20 citations · 89 across the 15 of their papers we have counts for

collaborators

18 papers

cs.RO2026

DexHoldem: Playing Texas Hold'em with Dexterous Embodied System

Feng Chen, Tianzhe Chu, Li Sun +6

Evaluating embodied systems on real dexterous hardware requires more than isolated primitive skills: an agent must perceive a changing tabletop scene, choose a context-appropriate…

cs.CV2025★ 1 cited

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs

Chun-Hsiao Yeh, Chenyu Wang, Shengbang Tong +7

Multi-view understanding, the ability to reconcile visual information across diverse viewpoints for effective navigation, manipulation, and 3D scene comprehension, is a fundamental…

cs.AI2025★ 7 cited

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Tianzhe Chu, Yuexiang Zhai, Jihan Yang +6

Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization…

cs.AI2024★ 8 cited

Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Yuexiang Zhai, Hao Bai, Zipeng Lin +8

Large vision-language models (VLMs) fine-tuned on specialized visual instruction-following data have exhibited impressive language reasoning capabilities across various scenarios.…

cs.LG2024

Is Offline Decision Making Possible with Only Few Samples? Reliable Decisions in Data-Starved Bandits via Trust Region Enhancement

Ruiqi Zhang, Yuexiang Zhai, Andrea Zanette

What can an agent learn in a stochastic Multi-Armed Bandit (MAB) problem from a dataset that contains just a single sample for each arm? Surprisingly, in this work, we demonstrate…

cs.CV2024★ 7 cited

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Shengbang Tong, Zhuang Liu, Yuexiang Zhai +3

Is vision good enough for language? Recent advancements in multimodal models primarily stem from the powerful reasoning abilities of large language models (LLMs). However, the visu…