Chenyang Wan's picture

3 2

Chenyang Wan

cywan

·

https://bryce-wan.github.io/

AI & ML interests

Embodied AI, Navigation

Recent Activity

updated a dataset 2 days ago

cywan/StreamVLN-Trajectory-Data

upvoted a paper 5 days ago

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

upvoted a paper 16 days ago

OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding

View all activity

Organizations

liked a dataset 26 days ago

nvidia/dynpose-100k

Updated May 12 • 668 • 40

liked a model 7 months ago

liuhaotian/llava-v1.6-vicuna-7b

Image-Text-to-Text • 7B • Updated May 9, 2024 • 21.2k • 131