Haiquan Lu
haiquanlu
AI & ML interests
AI efficieny and VisualGen
Recent Activity
upvoted a paper 6 days ago
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment upvoted a paper about 2 months ago
Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention TransformersOrganizations
None yet