5 papers
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation
Haoyu Zhao, Xingyue Zhao, Hangyu Li +6
Scaling robot learning requires massive, diverse trajectory data, yet collection is currently bottlenecked by physical teleoperation, where every demonstration binds operator time…
Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis
Hengyuan Cao, Yutong Feng, Biao Gong +4
Video generative models can be regarded as world simulators due to their ability to capture dynamic, continuous changes inherent in real-world environments. These models integrate…
Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
Fengyuan Dai, Siteng Huang, Min Zhang +2
To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classifica…
Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight
Ziyuan Huang, Kaixiang Ji, Biao Gong +6
This paper introduces Chain-of-Sight, a vision-language bridge module that accelerates the pre-training of Multimodal Large Language Models (MLLMs). Our approach employs a sequence…
Learning Disentangled Identifiers for Action-Customized Text-to-Image Generation
Siteng Huang, Biao Gong, Yutong Feng +4
This study focuses on a novel task in text-to-image (T2I) generation, namely action customization. The objective of this task is to learn the co-existing action from limited data a…