Kaijun Wang

Ka12un's activity

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

upvoted 2 papers 15 days ago

MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval Mechanism

Paper • 2606.07512 • Published 20 days ago • 39

WorldOlympiad: Can Your World Model Survive a Triathlon?

Paper • 2606.11129 • Published 16 days ago • 31

upvoted a paper 28 days ago

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

Paper • 2605.26115 • Published May 25 • 52

upvoted a paper about 2 months ago

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

Paper • 2604.24764 • Published Apr 27 • 119

authored a paper 2 months ago

Exploring Spatial Intelligence from a Generative Perspective

Paper • 2604.20570 • Published Apr 22 • 23

upvoted a paper 2 months ago

Exploring Spatial Intelligence from a Generative Perspective

Paper • 2604.20570 • Published Apr 22 • 23

upvoted a paper 3 months ago

TriAttention: Efficient Long Reasoning with Trigonometric KV Compression

Paper • 2604.04921 • Published Apr 6 • 116

upvoted 2 papers 5 months ago

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO

Paper • 2602.06422 • Published Feb 6 • 47

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

Paper • 2601.07351 • Published Jan 12 • 26

upvoted 3 papers 7 months ago

Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality

Paper • 2512.07951 • Published Dec 8, 2025 • 51

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

Paper • 2511.20714 • Published Nov 25, 2025 • 51

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks

Paper • 2508.08240 • Published Aug 11, 2025 • 45

upvoted a paper 8 months ago

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30, 2025 • 117

upvoted 3 papers 9 months ago

StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation

Paper • 2510.05057 • Published Oct 6, 2025 • 13

InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

Paper • 2509.10813 • Published Sep 13, 2025 • 31

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Paper • 2509.12201 • Published Sep 15, 2025 • 107

authored a paper 10 months ago

ODYSSEY: Open-World Quadrupeds Exploration and Manipulation for Long-Horizon Tasks

Paper • 2508.08240 • Published Aug 11, 2025 • 45

upvoted a paper 10 months ago

Time Is a Feature: Exploiting Temporal Dynamics in Diffusion Language Models

Paper • 2508.09138 • Published Aug 12, 2025 • 38