4 citations · 8 across the 18 of their papers we have counts for
20 papers
AutoMem: Automated Learning of Memory as a Cognitive Skill
Shengguang Wu, Hao Zhu, Yuhui Zhang +2
Memory expertise is a learned skill: knowing what to encode, when to retrieve, and how to organize knowledge--a capacity known in cognitive science as metamemory. We bring this per…
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…
Fine-tuning MLLMs Without Forgetting Is Easier Than You Think
He Li, Yuhui Zhang, Xiaohan Wang +2
The paper demonstrate that simple adjustments of the fine-tuning recipes of multimodal large language models (MLLM) are sufficient to mitigate catastrophic forgetting. On visual qu…
RadDiff: Describing Differences in Radiology Image Sets with Natural Language
Xiaoxian Shen, Yuhui Zhang, Sahithi Ankireddy +5
Understanding how two radiology image sets differ is critical for generating clinical insights and for interpreting medical AI systems. We introduce RadDiff, a multimodal agentic s…
Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning
Shengguang Wu, Xiaohan Wang, Yuhui Zhang +2
Spatial reasoning in 3D scenes requires precise geometric calculations that challenge vision-language models. Visual programming addresses this by decomposing problems into steps c…
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…
A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI
Alejandro Lozano, Min Woo Sun, James Burgess +16
Despite the excitement behind biomedical artificial intelligence (AI), access to high-quality, diverse, and large-scale data - the foundation for modern AI systems - is still a bot…
Video Action Differencing
James Burgess, Xiaohan Wang, Yuhui Zhang +5
How do two individuals differ when performing the same action? In this work, we introduce Video Action Differencing (VidDiff), the novel task of identifying subtle differences betw…
SurgiSAM2: Fine-tuning a foundational model for surgical video anatomy segmentation and detection
Devanish N. Kamtam, Joseph B. Shrager, Satya Deepya Malla +5
Background: We evaluate SAM 2 for surgical scene understanding by examining its semantic segmentation capabilities for organs/tissues both in zero-shot scenarios and after fine-tun…
Temporal Preference Optimization for Long-Form Video Understanding
Rui Li, Xiaohan Wang, Yuhui Zhang +3
Despite significant advancements in video large multimodal models (video-LMMs), achieving effective temporal grounding in long-form videos remains a challenge for existing models.…
BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature
Alejandro Lozano, Min Woo Sun, James Burgess +13
The development of vision-language models (VLMs) is driven by large-scale and diverse multimodal datasets. However, progress toward generalist biomedical VLMs is limited by the lac…
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…
Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration
Mark Endo, Xiaohan Wang, Serena Yeung-Levy
Recent works on accelerating Vision-Language Models achieve strong performance across a variety of vision-language tasks despite highly compressing visual information. In this work…
Zero-shot Action Localization via the Confidence of Large Vision-Language Models
Josiah Aklilu, Xiaohan Wang, Serena Yeung-Levy
Precise action localization in untrimmed video is vital for fields such as professional sports and minimally invasive surgery, where the delineation of particular motions in record…
Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
Orr Zohar, Xiaohan Wang, Yonatan Bitton +2
The performance of Large Vision Language Models (LVLMs) is dependent on the size and quality of their training datasets. Existing video instruction tuning datasets lack diversity a…
Why are Visually-Grounded Language Models Bad at Image Classification?
Yuhui Zhang, Alyssa Unell, Xiaohan Wang +4
Image classification is one of the most fundamental capabilities of machine vision intelligence. In this work, we revisit the image classification task using visually-grounded lang…
VideoAgent: Long-form Video Understanding with Large Language Model as Agent
Xiaohan Wang, Yuhui Zhang, Orr Zohar +1
Long-form video understanding represents a significant challenge within computer vision, demanding a model capable of reasoning over long multi-modal sequences. Motivated by the hu…
Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models
Elaine Sui, Xiaohan Wang, Serena Yeung-Levy
Advancements in vision-language models (VLMs) have propelled the field of computer vision, particularly in the zero-shot learning setting. Despite their promise, the effectiveness…
Describing Differences in Image Sets with Natural Language
Lisa Dunlap, Yuhui Zhang, Xiaohan Wang +5
How do two sets of images differ? Discerning set-level differences is crucial for understanding model behaviors and analyzing datasets, yet manually sifting through thousands of im…