Xiong Xuyuan

xjxyys's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 13 hours ago

Can World and Action Modeling Benefit Each Other under Unified Causal Training?

Paper • 2610.21095 • Published 1 day ago • 16

upvoted a paper 2 days ago

Multics: Generative Multi-Player World Model with Hierarchical Communication

Paper • 2610.17201 • Published 5 days ago • 62

upvoted 3 papers 3 months ago

SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation

Paper • 2607.21553 • Published Jul 23 • 40

Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing

Paper • 2607.19064 • Published Jul 21 • 78

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks

Paper • 2607.08768 • Published Jul 9 • 35

upvoted 3 papers 4 months ago

MemLearner: Learning to Query Context memory for Video World Models

Paper • 2606.31734 • Published Jun 30 • 29

Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots

Paper • 2606.28133 • Published Jun 26 • 41

Thinking with Imagination: Agentic Visual Spatial Reasoning with World Simulators

Paper • 2606.06476 • Published Jun 4 • 16

upvoted 2 papers 5 months ago

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory

Paper • 2605.31336 • Published May 29 • 11

Representation Forcing for Bottleneck-Free Unified Multimodal Models

Paper • 2605.31604 • Published May 29 • 62

upvoted a paper 6 months ago

OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

Paper • 2604.04707 • Published Apr 6 • 199

upvoted a paper 7 months ago

Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing

Paper • 2601.04575 • Published Jan 8 • 13

upvoted a paper 9 months ago

GARDO: Reinforcing Diffusion Models without Reward Hacking

Paper • 2512.24138 • Published Dec 30, 2025 • 30

upvoted a paper about 1 year ago

CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards

Paper • 2510.08529 • Published Oct 9, 2025 • 19