Sangmin Han

Sang-Min-i's activity

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

upvoted a paper 3 days ago

HuRo: Robotizing Human Videos for Scalable VLA Pretraining

Paper • 2609.10706 • Published 6 days ago • 23

upvoted a paper 27 days ago

Keep It Simple: Multi-Key Episodic Memory Retrieval for Ultra-Long Video Understanding

Paper • 2608.07663 • Published Aug 7 • 23

upvoted 7 papers about 2 months ago

APT: Improving Diffusion Models for High Resolution Image Generation with Adaptive Path Tracing

Paper • 2507.21690 • Published Jul 29, 2025 • 1

Accelerating Image Super-Resolution Networks with Pixel-Level Classification

Paper • 2407.21448 • Published Jul 31, 2024 • 2

Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning

Paper • 2303.17842 • Published Mar 31, 2023 • 1

VISAGE: Video Instance Segmentation with Appearance-Guided Enhancement

Paper • 2312.04885 • Published Dec 8, 2023 • 2

Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation

Paper • 2607.24731 • Published Jul 27 • 47

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published Jul 27 • 523

Coarse-to-fine Framework for Generative MEF via Implicit Neural Representation

Paper • 2607.17611 • Published Jul 20 • 2

upvoted 3 papers 3 months ago

Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition

Paper • 2601.16211 • Published Jul 2 • 51

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published Jul 2 • 66

Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views

Paper • 2606.29513 • Published Jun 28 • 52

upvoted 2 papers 4 months ago

Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration

Paper • 2605.17423 • Published May 17 • 31

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

Paper • 2605.27365 • Published May 26 • 143

upvoted a collection 4 months ago

RLDX-1

Collection

RLDX-1 : General-purpose robotics foundation model for dexterous manipulation. • 12 items • Updated Jul 9 • 28

upvoted 2 papers 5 months ago

Rethinking State Tracking in Recurrent Models Through Error Control Dynamics

Paper • 2605.07755 • Published May 8 • 22

EXAONE 4.5 Technical Report

Paper • 2604.08644 • Published Apr 9 • 75

upvoted a collection 6 months ago

EXAONE 4.5

Collection

LG's First Open-Weight Vision-Language Model for Industrial Intelligence • 5 items • Updated Apr 22 • 47

upvoted 2 papers 6 months ago

Attentive Illumination Decomposition Model for Multi-Illuminant White Balancing

Paper • 2402.18277 • Published Feb 28, 2024 • 1

ATTIQA: Generalizable Image Quality Feature Extractor using Attribute-aware Pretraining

Paper • 2406.01020 • Published Jun 3, 2024 • 1