Dongzhan Zhou

8

Papers

65

Total Citations

Papers (8)

Critic-V: VLM Critics Help Catch VLM Errors in Multimodal Reasoning

Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes

Scaling Physical Reasoning with the PHYSICS Dataset

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search

SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning

CMT: A Cascade MAR with Topology Predictor for Multimodal Conditional CAD Generation

MokA: Multimodal Low-Rank Adaptation for MLLMs

ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area