oh sehun

sehun's activity

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

upvoted a paper 4 days ago

Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL

Paper • 2609.37200 • Published 8 days ago • 138

upvoted a paper 6 days ago

Just MLPs: Efficient Visual State Reconstruction for Multimodal Language Models

Paper • 2609.34972 • Published 9 days ago • 30

upvoted a paper 7 days ago

Think Before You Score: Thinking Reward Model for Visual Generation

Paper • 2609.37372 • Published 8 days ago • 101

upvoted a collection 10 days ago

Intern-Decision

Collection

4 items • Updated 11 days ago • 21

upvoted 3 papers 12 days ago

RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling

Paper • 2609.22947 • Published 18 days ago • 43

All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation

Paper • 2609.27901 • Published 14 days ago • 24

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Paper • 2609.26780 • Published 15 days ago • 103

upvoted a collection 14 days ago

🎲 Decision 1.0

Collection

Towards Open Decision Foundation Models • 7 items • Updated 6 days ago • 23

upvoted 2 papers 14 days ago

onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction

Paper • 2609.24983 • Published 16 days ago • 55

Bellman Policy Optimization

Paper • 2609.15987 • Published 23 days ago • 49

upvoted 6 papers 15 days ago

MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup

Paper • 2609.15126 • Published 23 days ago • 12

VideoGen-Agent: Reinforcing Video Generation Agents

Paper • 2609.24997 • Published 16 days ago • 73

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Paper • 2609.24984 • Published 16 days ago • 157

RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents

Paper • 2609.22000 • Published 19 days ago • 79

Designer-RSI: Evolving Procedural Memory from User Traffic for Agentic Graphic Design

Paper • 2609.22086 • Published 19 days ago • 34

Transferring the Intelligence of VLMs to Robotic Control

Paper • 2609.22966 • Published 18 days ago • 120

upvoted a collection 15 days ago

MiMo-V2.6

Collection

5 items • Updated 10 days ago • 124

upvoted a paper 16 days ago

Self-Evolving Search Index

Paper • 2609.19656 • Published 20 days ago • 63

upvoted 2 papers 18 days ago

ActionPiece: Rethinking Action Tokenization for Autoregressive Vision-Language-Action Models

Paper • 2609.18487 • Published 21 days ago • 48

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

Paper • 2609.20519 • Published 20 days ago • 139