Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System
Paper • 2609.01607 • Published • 23
AI & ML interests
Feeling and building the multimodal intelligence.
Recent Activity
Papers
SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe
ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning
Paranioar
authored a
paper 3 days ago
kcz358
authored a
paper 8 days ago
yl-1993
authored a
paper 8 days ago
pufanyi
authored a
paper 9 days ago
Paranioar
authored a
paper 9 days ago
caizhongang
authored a
paper 9 days ago
Paranioar
authored a
paper 9 days ago
caizhongang
authored 2
papers 9 days ago
kcz358
authored a
paper 15 days ago
mwxely
authored a
paper 16 days ago
xiangan
authored a
paper 18 days ago
xiangan
submitted a
paper to Daily Papers 18 days ago
xiangan
submitted a
paper to Daily Papers 22 days ago
KairuiHu
authored 5
papers about 1 month ago
HippoCamp: Benchmarking Contextual Agents on Personal Computers
Paper • 2604.01221 • Published • 30
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
Paper • 2604.04901 • Published • 40
Apple-$π$: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence
Paper • 2607.16401 • Published • 44
HumanCLAW: Can Vision-Language Models Act Through a Body?
Paper • 2607.27180 • Published • 77
OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe
Paper • 2511.16334 • Published • 96
xiangan
authored a
paper about 1 month ago