oh sehun

sehun's activity

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

upvoted 3 papers about 16 hours ago

RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling

Paper • 2609.22947 • Published 7 days ago • 23

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

Paper • 2609.27901 • Published 3 days ago • 7

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

Paper • 2609.26780 • Published 4 days ago • 83

upvoted a collection 2 days ago

🎲 Decision 1.0

Collection

Open Decision Foundation Models • 7 items • Updated 4 days ago • 16

upvoted 4 papers 3 days ago

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

Paper • 2609.24983 • Published 5 days ago • 54

Bellman Policy Optimization

Paper • 2609.15987 • Published 12 days ago • 38

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

Paper • 2609.15126 • Published 12 days ago • 12

VideoGen-Agent: Reinforcing Video Generation Agents

Paper • 2609.24997 • Published 5 days ago • 67

upvoted 4 papers 4 days ago

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

Paper • 2609.24984 • Published 5 days ago • 149

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

Paper • 2609.22000 • Published 8 days ago • 77

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

Paper • 2609.22086 • Published 8 days ago • 33

Transferring the Intelligence of VLMs to Robotic Control

Paper • 2609.22966 • Published 7 days ago • 117

upvoted a collection 4 days ago

MiMo-V2.6

Collection

3 items • Updated 4 days ago • 93

upvoted a paper 5 days ago

Self-Evolving Search Index

Paper • 2609.19656 • Published 9 days ago • 60

upvoted 3 papers 7 days ago

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

Paper • 2609.18487 • Published 10 days ago • 47

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

Paper • 2609.20519 • Published 9 days ago • 131

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 9 days ago • 86

upvoted 2 papers 8 days ago

Disentangling Representation Evolution in Transformers through Directional Decomposition

Paper • 2609.15975 • Published 12 days ago • 9

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published 10 days ago • 80

upvoted a paper 9 days ago

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

Paper • 2609.08418 • Published 18 days ago • 135