Mu Cai's picture

7 10 3

Mu Cai

mucai

·

https://pages.cs.wisc.edu/~mucai/

AI & ML interests

Computer Vision, Deep Learning, 3D Vision, Vision and Language,

Recent Activity

upvoted a paper about 1 month ago

Contamination Detection for VLMs using Multi-Modal Semantic Perturbation

commented on a paper about 1 month ago

Contamination Detection for VLMs using Multi-Modal Semantic Perturbation

upvoted a paper 4 months ago

When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token Compression across Images, Videos, and Audios

View all activity

Organizations

commented a paper about 1 month ago

Contamination Detection for VLMs using Multi-Modal Semantic Perturbation

Paper • 2511.03774 • Published Nov 5 • 12 •

commented 2 papers about 1 year ago

TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models

Paper • 2410.10818 • Published Oct 14, 2024 • 16 •

Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos

Paper • 2410.02763 • Published Oct 3, 2024 • 7 •

New activity in mucai/matryoshka-multimodal-models over 1 year ago

Apply for community grant: Academic project (gpu and storage)

#1 opened over 1 year ago by

New activity in mucai/llava-next-vicuna-7b-m3 over 1 year ago

Add paper link to connect the model to its paper on Daily Paper page

#1 opened over 1 year ago by

New activity in mucai/llava-v1.5-7b-m3 over 1 year ago

Add meta data and paper link

#1 opened over 1 year ago by

New activity in mucai/ViP-LLaVA-Instruct over 1 year ago

Visual Prompt Type

#1 opened over 1 year ago by

Visual Prompt Type

#1 opened over 1 year ago by