4 14 1

Zefan Cai

ZefanCai

AI & ML interests

None yet

Recent Activity

updated a dataset about 4 hours ago

ZefanCai/VideoReasoning

upvoted a paper about 5 hours ago

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models

upvoted a paper 17 days ago

MMGR: Multi-Modal Generative Reasoning

View all activity

Organizations

Collections 2

Papers 7

models 1

ZefanCai/MambaVL-7b-dinosiglip-vit-so-384px-falcon-mamba-7b-llava-lvis4v-lrv

Updated Oct 7, 2024

datasets 26

Zefan Cai

AI & ML interests

Recent Activity

Organizations

Collections 2

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

Do Vision and Language Models Share Concepts? A Vector Space Alignment Study

Knowledge Composition using Task Vectors with Learned Anisotropic Scaling

Papers 7

models 1

ZefanCai/MambaVL-7b-dinosiglip-vit-so-384px-falcon-mamba-7b-llava-lvis4v-lrv

datasets 26

ZefanCai/VideoReasoning

ZefanCai/Video-Reasoning-Clean

ZefanCai/VideoKV

ZefanCai/ttt-data

ZefanCai/Embeddings

ZefanCai/obo

ZefanCai/VideoBias

ZefanCai/VideoBiasEval

ZefanCai/R-KV-logs

ZefanCai/PhysicsRM

Zefan Cai

AI & ML interests

Recent Activity

Organizations

Collections 2

Papers 7

models 1

datasets 26 Sort: Recently updated

datasets 26