Xu Jiahao

XUJIh3's activity

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

upvoted a paper 13 days ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 15 days ago • 150

upvoted a paper 20 days ago

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

Paper • 2608.07468 • Published 25 days ago • 107

upvoted a paper 21 days ago

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published 22 days ago • 342

upvoted a paper 25 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 25 days ago • 251

upvoted 2 papers 28 days ago

Beyond Geometric Complementarity: Coherent Overlap in Sparse Mixture-of-Experts Routing

Paper • 2607.28308 • Published Jul 30 • 5

3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering

Paper • 2608.01185 • Published about 1 month ago • 18

upvoted 3 papers about 1 month ago

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published Jul 21 • 312

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Paper • 2607.17977 • Published Jul 20 • 198

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published Jul 16 • 212

upvoted 5 papers about 2 months ago

X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras

Paper • 2607.12993 • Published Jul 14 • 131

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published Jul 14 • 235

EgoSteer: A Full-Stack System Towards Steerable Dexterous Manipulation from Egocentric Videos

Paper • 2607.09701 • Published Jun 21 • 17

RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation

Paper • 2607.06558 • Published Jul 7 • 79

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

Paper • 2606.29513 • Published Jun 28 • 53

upvoted 3 papers 2 months ago

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Paper • 2606.17162 • Published Jun 15 • 178

Looped World Models

Paper • 2606.18208 • Published Jun 16 • 486

DreamX-World 1.0: A General-Purpose Interactive World Model

Paper • 2606.16993 • Published Jun 15 • 114

upvoted 2 papers 3 months ago

GRAIL: Generating Humanoid Loco-Manipulation from 3D Assets and Video Priors

Paper • 2606.05160 • Published Jun 3 • 9

Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players

Paper • 2605.28816 • Published May 27 • 433