oh sehun

sehun's activity

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

upvoted a paper about 2 hours ago

Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering

Paper • 2601.09697 • Published 1 day ago • 5

upvoted an article about 2 hours ago

view article

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

• 

about 21 hours ago

•

19

upvoted a paper about 12 hours ago

Aligning Text, Code, and Vision: A Multi-Objective Reinforcement Learning Framework for Text-to-Visualization

Paper • 2601.04582 • Published 8 days ago • 5

upvoted a paper about 20 hours ago

User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale

Paper • 2601.08225 • Published 3 days ago • 44

upvoted 3 papers 1 day ago

SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

Paper • 2601.08303 • Published 3 days ago • 12

Motion Attribution for Video Generation

Paper • 2601.08828 • Published 2 days ago • 65

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published 3 days ago • 40

upvoted a paper 3 days ago

Can We Predict Before Executing Machine Learning Agents?

Paper • 2601.05930 • Published 6 days ago • 25

upvoted 6 papers 4 days ago

Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking

Paper • 2601.04720 • Published 8 days ago • 43

MMFormalizer: Multimodal Autoformalization in the Wild

Paper • 2601.03017 • Published 10 days ago • 101

Token-Level LLM Collaboration via FusionRoute

Paper • 2601.05106 • Published 7 days ago • 39

Chaining the Evidence: Robust Reinforcement Learning for Deep Search Agents with Citation-Aware Rubric Rewards

Paper • 2601.06021 • Published 6 days ago • 38

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

Paper • 2601.05966 • Published 6 days ago • 21

Learnable Multipliers: Freeing the Scale of Language Model Matrix Layers

Paper • 2601.04890 • Published 8 days ago • 40

upvoted a paper 6 days ago

AT^2PO: Agentic Turn-based Policy Optimization via Tree Search

Paper • 2601.04767 • Published 8 days ago • 26

upvoted a collection 6 days ago

Qwen3-VL-Embedding

Collection

2 items • Updated 7 days ago • 52

upvoted a paper 6 days ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published 7 days ago • 186

upvoted a paper 7 days ago

RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models

Paper • 2601.03699 • Published 9 days ago • 5

upvoted a collection 7 days ago

Qwen3-VL-Reranker

Collection

2 items • Updated 7 days ago • 33

upvoted a paper 7 days ago

LTX-2: Efficient Joint Audio-Visual Foundation Model

Paper • 2601.03233 • Published 9 days ago • 118