VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images
Paper • 2604.09531 • Published • 8 •
2
Guanyu Zhou
TheMartyr
AI & ML interests
None yet
Recent Activity
authored a paper about 15 hours ago
Mitigating Modality Prior-Induced Hallucinations in Multimodal Large
Language Models via Deciphering Attention Causality authored a paper about 15 hours ago
OmniDPO: A Preference Optimization Framework to Address Omni-Modal
Hallucination authored a paper about 15 hours ago
CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts GenerationOrganizations
commented a
paper 20 days ago