oh sehun

sehun's activity

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

upvoted a paper about 17 hours ago

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

Paper • 2603.22386 • Published 4 days ago • 48

upvoted a paper about 24 hours ago

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

Paper • 2603.23499 • Published 3 days ago • 43

upvoted 4 papers 1 day ago

Repurposing Geometric Foundation Models for Multi-view Diffusion

Paper • 2603.22275 • Published 4 days ago • 40

The Universal Normal Embedding

Paper • 2603.21786 • Published 4 days ago • 14

Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought

Paper • 2603.22847 • Published 3 days ago • 21

Generalized Discrete Diffusion from Snapshots

Paper • 2603.21342 • Published 5 days ago • 11

upvoted 3 papers 2 days ago

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Paper • 2603.20278 • Published 9 days ago • 82

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

Paper • 2603.22281 • Published 4 days ago • 13

mSFT: Addressing Dataset Mixtures Overfiting Heterogeneously in Multi-task SFT

Paper • 2603.21606 • Published 4 days ago • 35

upvoted 3 papers 3 days ago

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Paper • 2603.21065 • Published 5 days ago • 70

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published 4 days ago • 107

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

Paper • 2603.22117 • Published 4 days ago • 22

upvoted a paper 4 days ago

Beyond Single Tokens: Distilling Discrete Diffusion Models via Discrete MMD

Paper • 2603.20155 • Published 7 days ago • 7

upvoted 3 papers 5 days ago

Matryoshka Gaussian Splatting

Paper • 2603.19234 • Published 8 days ago • 11

3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model

Paper • 2603.18524 • Published 8 days ago • 56

Cubic Discrete Diffusion: Discrete Visual Generation on High-Dimensional Representation Tokens

Paper • 2603.19232 • Published 8 days ago • 33

upvoted 2 papers 6 days ago

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

Paper • 2603.19227 • Published 8 days ago • 40

SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing

Paper • 2603.19228 • Published 8 days ago • 64

upvoted 2 papers 7 days ago

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs

Paper • 2603.18004 • Published 9 days ago • 12

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published 8 days ago • 58