Weijie Wang

lhmd's activity

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

upvoted 2 papers 1 day ago

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published 6 days ago • 27

Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision

Paper • 2608.16812 • Published 9 days ago • 47

upvoted a paper 2 days ago

EviRank: Structured Relevance Evidence for Multimodal Image Re-ranking

Paper • 2608.20886 • Published 5 days ago • 11

upvoted a paper 19 days ago

EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning

Paper • 2608.06197 • Published 20 days ago • 46

upvoted a paper 26 days ago

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

Paper • 2607.27919 • Published 27 days ago • 59

upvoted a paper about 1 month ago

Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking

Paper • 2607.19747 • Published Jul 22 • 30

upvoted 10 papers 3 months ago

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

Paper • 2606.09426 • Published Jun 8 • 107

WorldOlympiad: Can Your World Model Survive a Triathlon?

Paper • 2606.11129 • Published Jun 9 • 32

Latent Spatial Memory for Video World Models

Paper • 2606.09828 • Published Jun 8 • 71

MMAE: A Massive Multitask Audio Editing Benchmark

Paper • 2606.07229 • Published Jun 5 • 45

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published Jun 1 • 142

Streaming Communication in Multi-Agent Reasoning

Paper • 2606.05158 • Published Jun 3 • 30

LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding

Paper • 2605.27365 • Published May 26 • 147

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

Paper • 2605.26115 • Published May 25 • 53

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization

Paper • 2605.15980 • Published May 15 • 36

Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video

Paper • 2605.15182 • Published May 14 • 39

upvoted 4 papers 4 months ago

MARBLE: Multi-Aspect Reward Balance for Diffusion RL

Paper • 2605.06507 • Published May 7 • 40

Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis

Paper • 2604.24198 • Published Apr 27 • 23

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

Paper • 2604.24764 • Published Apr 27 • 120

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

Paper • 2604.14025 • Published Apr 15 • 15