DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models
Paper • 2610.12572 • Published • 319
Taekyung Ki
taekyungki
AI & ML interests
Ph.D. Student at KAIST
Recent Activity
upvoted a paper 5 days ago
DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models upvoted a paper 5 days ago
Reflex: Visually Grounded Reactive Humanoid Control upvoted a paper 10 days ago
RunningTab: Direct Workspace Interaction with Environment-Side TabsOrganizations
upvoted 2
papers 5 days ago
upvoted a paper 10 days ago
upvoted a paper 11 days ago
upvoted 4
papers 16 days ago
Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge
Paper • 2609.34327 • Published • 41
Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning
Paper • 2609.33781 • Published • 46
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery
Paper • 2609.40340 • Published • 112
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents
Paper • 2609.39982 • Published • 119
upvoted 4
papers 17 days ago
What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling
Paper • 2609.34981 • Published • 139
Adversarial Training for Pixel Diffusion
Paper • 2609.38170 • Published • 22
In-Context Learning for Robots: Methods and Applications
Paper • 2609.36012 • Published • 411
Follow the Entities: A Corpus Map for Agentic Search
Paper • 2609.37226 • Published • 101
upvoted 4
papers 22 days ago
EvolveTrade: Experience-Driven Policy Refinement for Self-Evolving LLM Trading Agents
Paper • 2609.17632 • Published • 46
VideoGen-Agent: Reinforcing Video Generation Agents
Paper • 2609.24997 • Published • 73
On the Diffusibility of High-Dimensional Latents
Paper • 2609.28473 • Published • 19
The Past Frames the Future: Memory for Autoregressive Video Generation
Paper • 2609.28466 • Published • 66
upvoted a paper 26 days ago
upvoted 3
papers about 1 month ago