Mu Cai's picture

6 9 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 2 months ago

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

upvoted a paper 2 months ago

Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

upvoted a paper 8 months ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

View all activity

Organizations

Collections 3

View 3 collections

Papers 4

arxiv:2410.10818

arxiv:2410.02763

arxiv:2406.20095

arxiv:2405.17430

spaces 2

No application file

Matryoshka Multimodal Models

ViP-Bench Evaluator

models 14

mucai/vip-llava-7b-refcocog-ft

Text Generation • Updated Jun 28, 2024 • 4

mucai/llava-next-vicuna-7b-m3

Text Generation • 7B • Updated Jun 3, 2024 • 8 • 3

mucai/llava-v1.5-7b-m3

Text Generation • 7B • Updated Jun 3, 2024 • 53 • 2

mucai/vip-llava-phi-3-mini-3.8B

Text Generation • 4B • Updated Apr 26, 2024 • 6

mucai/vip-llava-llama-3-8b

Text Generation • 8B • Updated Apr 26, 2024 • 6

mucai/llava-1.5-phi-3-mini-3.8B

Text Generation • 4B • Updated Apr 26, 2024 • 7

mucai/llava-1.5-llama-3-8b

Text Generation • 8B • Updated Apr 26, 2024 • 5

mucai/vip-llava-13b-base

Text Generation • Updated Apr 21, 2024 • 6

mucai/vip-llava-7b-base-vcr-ft

Text Generation • Updated Feb 23, 2024 • 26

mucai/vip-llava-7b-base

Text Generation • Updated Jan 23, 2024 • 7

datasets 2

mucai/ViP-LLaVA-Instruct

Preview • Updated Feb 26, 2024 • 52 • 10

mucai/ViP-Bench

Viewer • Updated Dec 15, 2023 • 888 • 236 • 4