A fine-grained visual reasoning benchmark (V2 is an extended dataset, we keep updating)
Sicheng Feng
FSCCS
yanghong21240's profile picture
Huan-WhoRegisteredMyName's profile picture
Alrightlone's profile picture
·
AI & ML interests
None yet
Recent Activity
authored
a paper
about 15 hours ago
When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token
Compression across Images, Videos, and Audios
upvoted
a
paper
about 19 hours ago
When Tokens Talk Too Much: A Survey of Multimodal Long-Context Token
Compression across Images, Videos, and Audios
updated
a dataset
3 days ago
FSCCS/ReasonMap-V2
Organizations
models
0
None public yet