Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models
Paper • 2604.10949 • Published • 36
Yang Shi
DogNeverSleep
AI & ML interests
👨🏻🎓PhD student at Peking University
Recent Activity
upvoted a paper about 13 hours ago
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models upvoted a paper about 13 hours ago
OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation upvoted a paper about 13 hours ago
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and MitigationOrganizations
upvoted 3
papers about 13 hours ago
updated a
dataset about 19 hours ago
published a
dataset 2 days ago
upvoted a paper 5 days ago
upvoted a paper 7 days ago
authored 2
papers 8 days ago
upvoted a paper 8 days ago
upvoted a paper 9 days ago
updated a
dataset 10 days ago
published a
dataset 11 days ago
authored a
paper 22 days ago
upvoted a paper 26 days ago
submitted a
paper to Daily Papers 26 days ago
authored 4
papers about 2 months ago
BrowseComp-$V^3$: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Paper • 2602.12876 • Published • 12
OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
Paper • 2602.04804 • Published • 50
Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks
Paper • 2602.01630 • Published • 50
DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models
Paper • 2601.19267 • Published