5 papers
RADAR: Closed-Loop Robotic Data Generation via Semantic Planning and Autonomous Causal Environment Reset
Yongzhong Wang, Keyu Zhu, Yong Zhong +3
The acquisition of large-scale physical interaction data, a critical prerequisite for modern robot learning, is severely bottlenecked by the prohibitive cost and scalability limits…
On Data Synthesis and Post-training for Visual Abstract Reasoning
Ke Zhu, Yu Wang, Jiangjiang Liu +3
This paper is a pioneering work attempting to address abstract visual reasoning (AVR) problems for large vision-language models (VLMs). We make a common LLaVA-NeXT 7B model capable…
Enhancing Descriptive Captions with Visual Attributes for Multimodal Perception
Yanpeng Sun, Jing Hao, Ke Zhu +6
Training Large Multimodality Models (LMMs) relies on descriptive image caption that connects image and language. Existing methods for generating such captions often rely on distill…
Continual SFT Matches Multimodal RLHF with Negative Supervision
Ke Zhu, Yu Wang, Yanpeng Sun +4
Multimodal RLHF usually happens after supervised finetuning (SFT) stage to continually improve vision-language models' (VLMs) comprehension. Conventional wisdom holds its superiori…
Self-Supervised Visual Preference Alignment
Ke Zhu, Zheng Ge, Liang Zhao +1
This paper makes the first attempt towards unsupervised preference alignment in Vision-Language Models (VLMs). We generate chosen and rejected responses with regard to the original…