VISTA: A Test-Time Self-Improving Video Generation Agent
Paper • 2510.15831 • Published • 24
Li Xiaohao
xiaohaonlp
AI & ML interests
Multimodal Learning
Recent Activity
upvoted a paper 3 days ago
VISTA: A Test-Time Self-Improving Video Generation Agent upvoted a paper 3 days ago
A^2RD: Agentic Autoregressive Diffusion for Long Video Consistency upvoted a paper 3 days ago
Heterogeneous Scientific Foundation Model CollaborationOrganizations
None yet
upvoted 8
papers 3 days ago
A^2RD: Agentic Autoregressive Diffusion for Long Video Consistency
Paper • 2605.06924 • Published • 15
Heterogeneous Scientific Foundation Model Collaboration
Paper • 2604.27351 • Published • 212
Let ViT Speak: Generative Language-Image Pre-training
Paper • 2605.00809 • Published • 32
Hallucinations Undermine Trust; Metacognition is a Way Forward
Paper • 2605.01428 • Published • 23
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 287
ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration
Paper • 2605.03042 • Published • 112
Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
Paper • 2605.03849 • Published • 122