activity
20242026
collaborators

5 papers

cs.CV2026

HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining

Juncheng Ma, Jianxin Bi, Yufan Deng +19

Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remai…

cs.LG2026

Simulus: Combining Improvements in Sample-Efficient World Model Agents

Lior Cohen, Kaixin Wang, Bingyi Kang +2

World models (WMs) represent the frontier of sample-efficient reinforcement learning, but their complexity leaves many promising improvements unrealized due to the significant expe…

cs.CV2025

How Far is Video Generation from World Model: A Physical Law Perspective

Bingyi Kang, Yang Yue, Rui Lu +5

OpenAI's Sora highlights the potential of video generation for developing world models that adhere to fundamental physical laws. However, the ability of video generation models to…

cs.CV2024

Classification Done Right for Vision-Language Pre-Training

Zilong Huang, Qinghao Ye, Bingyi Kang +2

We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text…

cs.RO2024

DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution

Yang Yue, Yulin Wang, Bingyi Kang +5

MLLMs have demonstrated remarkable comprehension and reasoning capabilities with complex language and visual data. These advances have spurred the vision of establishing a generali…