oh sehun

sehun's activity

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

upvoted a paper about 4 hours ago

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Paper • 2512.05150 • Published 6 days ago • 44

upvoted a paper 1 day ago

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published 7 days ago • 181

upvoted an article 1 day ago

view article

Article

Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand

• 

5 days ago

•

53

upvoted a paper 5 days ago

DiP: Taming Diffusion Models in Pixel Space

Paper • 2511.18822 • Published 15 days ago • 25

upvoted 3 papers 6 days ago

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published 7 days ago • 57

Rectifying LLM Thought from Lens of Optimization

Paper • 2512.01925 • Published 7 days ago • 23

Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning

Paper • 2511.20549 • Published 13 days ago • 24

upvoted 6 papers 7 days ago

DualVLA: Building a Generalizable Embodied Agent via Partial Decoupling of Reasoning and Action

Paper • 2511.22134 • Published 12 days ago • 21

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Paper • 2512.01374 • Published 8 days ago • 80

Decoupled DMD: CFG Augmentation as the Spear, Distribution Matching as the Shield

Paper • 2511.22677 • Published 11 days ago • 22

Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Paper • 2511.22699 • Published 11 days ago • 163

OmniRefiner: Reinforcement-Guided Local Diffusion Refinement

Paper • 2511.19990 • Published 14 days ago • 3

Agentic Learner with Grow-and-Refine Multimodal Semantic Memory

Paper • 2511.21678 • Published 12 days ago • 10

upvoted 2 papers 10 days ago

Canvas-to-Image: Compositional Image Generation with Multimodal Controls

Paper • 2511.21691 • Published 12 days ago • 32

Soft Adaptive Policy Optimization

Paper • 2511.20347 • Published 13 days ago • 33

upvoted 3 papers 11 days ago

Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens

Paper • 2511.19418 • Published 14 days ago • 26

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Paper • 2511.20714 • Published 14 days ago • 45

Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs

Paper • 2511.19773 • Published 14 days ago • 9

upvoted 2 papers 12 days ago

GigaEvo: An Open Source Optimization Framework Powered By LLMs And Evolution Algorithms

Paper • 2511.17592 • Published 21 days ago • 118

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation

Paper • 2511.20256 • Published 13 days ago • 26