Seungho Lee

seungho-lee's activity

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

upvoted a paper 1 day ago

Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?

Paper • 2610.28763 • Published 5 days ago • 27

upvoted a paper 7 days ago

Multics: Generative Multi-Player World Model with Hierarchical Communication

Paper • 2610.17201 • Published 13 days ago • 70

upvoted 2 papers 8 days ago

LEGO: A Lifting-Free Approach for Exocentric-to-Egocentric Video Generation

Paper • 2610.12442 • Published 17 days ago • 46

FlashVSR+: Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching

Paper • 2610.17552 • Published 12 days ago • 37

upvoted a paper 9 days ago

LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards

Paper • 2602.05758 • Published 13 days ago • 24

upvoted a paper 15 days ago

DistScene: Object-to-Scene Distillation for 3D Scene Generation

Paper • 2610.06960 • Published 22 days ago • 18

upvoted a paper 18 days ago

Decoding Looped Transformers Better for (Almost) Free

Paper • 2610.02185 • Published 24 days ago • 48

upvoted 11 papers about 1 month ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 535

The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks

Paper • 2609.25804 • Published Sep 22 • 166

DeformSmith: Physics Harness-Guided Hierarchical Generation of Deformable Assets for Robot Manipulation

Paper • 2609.18620 • Published Sep 17 • 24

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Paper • 2609.20519 • Published Sep 17 • 142

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Paper • 2609.17488 • Published Sep 15 • 318

StepAudio 3 Realtime Technical Report

Paper • 2609.14005 • Published Sep 12 • 130

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published Sep 15 • 159

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 371

PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control

Paper • 2609.17521 • Published Sep 15 • 10

Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models

Paper • 2609.08418 • Published Sep 8 • 120

Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models

Paper • 2609.12641 • Published Sep 11 • 80