egotextvqa-group

AI & ML interests

None defined yet.

Recent Activity

DogNeverSleep  authored a paper about 12 hours ago

BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

DogNeverSleep  authored a paper about 12 hours ago

OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models

DogNeverSleep  authored a paper about 12 hours ago

Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

View all activity

Team members 2