arxiv:2501.03271
Vasu Sharma
vasusharma55
AI & ML interests
None yet
Recent Activity
authored
a paper
28 days ago
DINOv2: Learning Robust Visual Features without Supervision
authored
a paper
28 days ago
Demystifying CLIP Data
authored
a paper
28 days ago
E-ViLM: Efficient Video-Language Model via Masked Video Modeling with
Semantic Vector-Quantized Tokenizer
Organizations
None yet
Papers
12
models
None public yet
datasets
None public yet