Donghwan Kim

donghwan-kim's activity

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

upvoted a paper 6 days ago

ENPIRE: Agentic Robot Policy Self-Improvement in the Real World

Paper • 2606.19980 • Published 7 days ago • 14

upvoted a paper 17 days ago

Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach

Paper • 2512.02834 • Published Dec 2, 2025 • 42

upvoted 2 papers 20 days ago

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

Paper • 2606.05160 • Published 22 days ago • 8

Cosmos 3: Omnimodal World Models for Physical AI

Paper • 2606.02800 • Published 24 days ago • 134

upvoted 7 papers 28 days ago

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

Paper • 2605.13724 • Published May 13 • 105

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

Paper • 2605.06169 • Published May 7 • 237

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

Paper • 2605.26230 • Published about 1 month ago • 41

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

Paper • 2605.27365 • Published 30 days ago • 144

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

Paper • 2605.28003 • Published 29 days ago • 50

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

Paper • 2605.28816 • Published 29 days ago • 431

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published 29 days ago • 93

upvoted 5 papers about 1 month ago

WorldKV: Efficient World Memory with World Retrieval and Compression

Paper • 2605.22718 • Published May 21 • 42

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

Paper • 2605.20910 • Published May 20 • 29

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

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

Paper • 2605.16257 • Published May 15 • 55

authored 4 papers about 1 month ago

PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions

Paper • 2605.09538 • Published May 10

FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow

Paper • 2307.08100 • Published Jul 16, 2023

Dense Hand-Object(HO) GraspNet with Full Grasping Taxonomy and Dynamics

Paper • 2409.04033 • Published Sep 6, 2024

Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images

Paper • 2409.18364 • Published Oct 29, 2024