6 papers
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt +2
Computer-use agents, which leverage multimodal large language models (MLLMs) to operate computers and complete tasks, have attracted significant attention for their utility and ver…
V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
Bingda Tang, Yuhui Zhang, Xiaohan Wang +3
Aligning denoising generative models with human preferences or verifiable rewards remains a key challenge. While policy-gradient online reinforcement learning (RL) offers a princip…
Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models
Dhruba Ghosh, Yuhui Zhang, Ludwig Schmidt
Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and mul…
Data or Language Supervision: What Makes CLIP Better than DINO?
Yiming Liu, Yuhui Zhang, Dhruba Ghosh +2
CLIP outperforms self-supervised models like DINO as vision encoders for vision-language models (VLMs), but it remains unclear whether this advantage stems from CLIP's language sup…
Closing the Modality Gap for Mixed Modality Search
Binxu Li, Yuhui Zhang, Xiaohan Wang +3
Mixed modality search -- retrieving information across a heterogeneous corpus composed of images, texts, and multimodal documents -- is an important yet underexplored real-world ap…
Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation
Yuhui Zhang, Yuchang Su, Yiming Liu +9
The rapid development of vision language models (VLMs) demands rigorous and reliable evaluation. However, current visual question answering (VQA) benchmarks often depend on open-en…