Xiaoji Zheng

Student-Xiaoji's activity

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

upvoted 3 papers 2 days ago

RELIC: Interactive Video World Model with Long-Horizon Memory

Paper • 2512.04040 • Published 3 days ago • 20

CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation

Paper • 2512.03540 • Published 3 days ago • 11

Qwen3-VL Technical Report

Paper • 2511.21631 • Published 10 days ago • 106

upvoted 4 papers 4 days ago

OpenREAD: Reinforced Open-Ended Reasoing for End-to-End Autonomous Driving with LLM-as-Critic

Paper • 2512.01830 • Published 5 days ago • 3

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

Paper • 2512.01031 • Published 6 days ago • 22

GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation

Paper • 2512.01801 • Published 5 days ago • 22

What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards

Paper • 2512.00425 • Published 7 days ago • 45

upvoted a paper 7 days ago

Video Generation Models Are Good Latent Reward Models

Paper • 2511.21541 • Published 10 days ago • 44

upvoted 5 papers 9 days ago

UniGame: Turning a Unified Multimodal Model Into Its Own Adversary

Paper • 2511.19413 • Published 12 days ago • 19

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Paper • 2511.20714 • Published 12 days ago • 45

MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots

Paper • 2511.17889 • Published 15 days ago • 5

Block Cascading: Training Free Acceleration of Block-Causal Video Models

Paper • 2511.20426 • Published 11 days ago • 8

Latent Collaboration in Multi-Agent Systems

Paper • 2511.20639 • Published 11 days ago • 110

upvoted 5 papers 10 days ago

Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion

Paper • 2511.18734 • Published 12 days ago • 6

PhysChoreo: Physics-Controllable Video Generation with Part-Aware Semantic Grounding

Paper • 2511.20562 • Published 11 days ago • 4

MagicWorld: Interactive Geometry-driven Video World Exploration

Paper • 2511.18886 • Published 12 days ago • 17

Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path Forward

Paper • 2511.20561 • Published 11 days ago • 31

GigaWorld-0: World Models as Data Engine to Empower Embodied AI

Paper • 2511.19861 • Published 12 days ago • 30

upvoted 2 papers 11 days ago

Target-Bench: Can World Models Achieve Mapless Path Planning with Semantic Targets?

Paper • 2511.17792 • Published 15 days ago • 3

One4D: Unified 4D Generation and Reconstruction via Decoupled LoRA Control

Paper • 2511.18922 • Published 12 days ago • 10