Jaemin Cho
Publications
Experience
CV
Zineng Tang
Latest
Paxion: Patching Action Knowledge in Video-Language Foundation Models
TVLT: Textless Vision-Language Transformer
Perceiver-VL: Efficient Vision-and-Language Modeling with Iterative Latent Attention
VidLanKD: Improving Language Understanding via Video-Distilled Knowledge Transfer
Cite
×