FSMBench

AI & ML interests

Evaluating and Benchmarking Large Multimodal Models

Recent Activity

taesiri  submitted a paper about 14 hours ago

ReToken: One Token to Improve Vision-Language Models for Visual Retrieval

taesiri  submitted a paper about 14 hours ago

Chimera: Designing and Chinchilla-Scaling Hybrid Visual Diffusion Transformers

taesiri  submitted a paper about 14 hours ago

ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine

View all activity

Team members 5