SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
Paper • 2605.15178 • Published • 75
Haoyu Guo
ghy0324
AI & ML interests
None yet
Recent Activity
View all activity
Organizations
upvoted 2
papers 4 days ago
upvoted 10
papers 3 months ago
PyVision-RL: Forging Open Agentic Vision Models via RL
Paper • 2602.20739 • Published • 31
BitDance: Scaling Autoregressive Generative Models with Binary Tokens
Paper • 2602.14041 • Published • 53
Experiential Reinforcement Learning
Paper • 2602.13949 • Published • 74
GLM-5: from Vibe Coding to Agentic Engineering
Paper • 2602.15763 • Published • 149
RynnBrain: Open Embodied Foundation Models
Paper • 2602.14979 • Published • 46
Mobile-Agent-v3.5: Multi-platform Fundamental GUI Agents
Paper • 2602.16855 • Published • 51
Unified Latents (UL): How to train your latents
Paper • 2602.17270 • Published • 60
Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control
Paper • 2602.18422 • Published • 30
A Very Big Video Reasoning Suite
Paper • 2602.20159 • Published • 523
Unified Personalized Reward Model for Vision Generation
Paper • 2602.02380 • Published • 20
upvoted 8
papers 4 months ago
Kimi K2.5: Visual Agentic Intelligence
Paper • 2602.02276 • Published • 270
PaperBanana: Automating Academic Illustration for AI Scientists
Paper • 2601.23265 • Published • 227
DeepSeek-OCR 2: Visual Causal Flow
Paper • 2601.20552 • Published • 69
Advancing Open-source World Models
Paper • 2601.20540 • Published • 135
Your Group-Relative Advantage Is Biased
Paper • 2601.08521 • Published • 158
STEP3-VL-10B Technical Report
Paper • 2601.09668 • Published • 195
Action100M: A Large-scale Video Action Dataset
Paper • 2601.10592 • Published • 31
Transition Matching Distillation for Fast Video Generation
Paper • 2601.09881 • Published • 34