5 papers · 1 filter
Support Operation Factorization: Compositional Readout of Frozen Vision Encoders under Controlled Interventions
Zhongyao Wang, Wanli Ouyang, Taoyong Cui +1
Compositional analysis of frozen vision encoders should determine both what changed and where it changed. Standard factor probes score these axes separately, however, and can rewar…
PolyReal: A Benchmark for Real-World Polymer Science Workflows
Wanhao Liu, Weida Wang, Jiaqing Xie +12
Multimodal Large Language Models (MLLMs) excel in general domains but struggle with complex, real-world science. We posit that polymer science, an interdisciplinary field spanning…
A CLIP-Powered Framework for Robust and Generalizable Data Selection
Suorong Yang, Peng Ye, Wanli Ouyang +2
Large-scale datasets have been pivotal to the advancements of deep learning models in recent years, but training on such large datasets invariably incurs substantial storage and co…
AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Use
Yaotian Yang, Yiwen Tang, Yizhe Chen +14
Reconstructing atomistic crystal structures from a single noisy STEM projection is an ill-posed inverse problem: multiple lattices can explain similar contrast, and purely feed-for…
Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning
Di Zhang, Junxian Li, Jingdi Lei +10
Vision-language models (VLMs) have shown remarkable advancements in multimodal reasoning tasks. However, they still often generate inaccurate or irrelevant responses due to issues…