Donghwan Kim

donghwan-kim's activity

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

upvoted 2 papers 3 days ago

AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation

Paper • 2605.13724 • Published 19 days ago • 101

Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers

Paper • 2605.06169 • Published 25 days ago • 231

upvoted 5 papers 4 days ago

Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction

Paper • 2605.26230 • Published 7 days ago • 39

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

Paper • 2605.27365 • Published 6 days ago • 128

ResearchMath-14K: Scaling Research-Level Mathematics via Agents

Paper • 2605.28003 • Published 5 days ago • 46

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

Paper • 2605.28816 • Published 5 days ago • 405

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published 5 days ago • 79

upvoted 2 papers 9 days ago

WorldKV: Efficient World Memory with World Retrieval and Compression

Paper • 2605.22718 • Published 11 days ago • 41

FlowLong: Inference-time Long Video Generation via Manifold-constrained Tweedie Matching

Paper • 2605.20910 • Published 12 days ago • 29

upvoted 2 papers 13 days ago

RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models

Paper • 2603.21341 • Published Mar 22 • 24

SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models

Paper • 2602.04208 • Published Feb 4 • 20

upvoted a paper 14 days ago

DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo

Paper • 2605.16257 • Published 17 days ago • 52

upvoted 2 papers 24 days ago

MolmoAct2: Action Reasoning Models for Real-world Deployment

Paper • 2605.02881 • Published 28 days ago • 347

RLDX-1 Technical Report

Paper • 2605.03269 • Published 27 days ago • 125

upvoted 2 papers about 2 months ago

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision

Paper • 2604.04934 • Published Apr 6 • 46

Token Warping Helps MLLMs Look from Nearby Viewpoints

Paper • 2604.02870 • Published Apr 3 • 34