Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
Paper • 2608.00782 • Published • 14
fan xyz
fanzh03
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 19 hours ago
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance upvoted a paper about 19 hours ago
FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory upvoted a paper about 19 hours ago
HelloWorld: Enabling Socially Interactive Characters in Video World ModelsOrganizations
None yet
upvoted 7
papers about 19 hours ago
FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory
Paper • 2608.04530 • Published • 10
HelloWorld: Enabling Socially Interactive Characters in Video World Models
Paper • 2608.05070 • Published • 17
WorldCycle: Self-Verifiable Reinforcement Learning for Long-Horizon Video World Models
Paper • 2608.04964 • Published • 10
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Paper • 2608.05131 • Published • 8
BridgeVLA++: A Data-Efficient, Generalizable, and Memory-Augmented Vision-Language-Action Framework for 3D Manipulation
Paper • 2608.05042 • Published • 7
K-EXAONE 2.0 Technical Report
Paper • 2608.04505 • Published • 16
upvoted a paper 2 days ago
upvoted a paper 8 days ago
upvoted a paper 14 days ago
upvoted a paper 24 days ago
upvoted a paper about 1 month ago
upvoted a paper about 2 months ago
upvoted 3
papers 7 months ago
Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models
Paper • 2512.24618 • Published • 155
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper • 2512.16093 • Published • 96
DreaMontage: Arbitrary Frame-Guided One-Shot Video Generation
Paper • 2512.21252 • Published • 35