Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
Paper • 2604.26779 • Published • 12
dooho lee
BlueYellowGreen
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding upvoted a paper 5 days ago
Recursive Multi-Agent Systems upvoted a paper 7 days ago
Agentic World Modeling: Foundations, Capabilities, Laws, and BeyondOrganizations
None yet
upvoted 2
papers 5 days ago
upvoted a paper 7 days ago
upvoted 2
articles 11 days ago
Article
Gemma 4 VLA Demo on Jetson Orin Nano Super
•
9
Article
DenseOn with the LateOn: Open State-of-the-Art Single and Multi-Vector Models
•
36
upvoted a paper 13 days ago
upvoted an article 14 days ago
Article
How to Ground a Korean AI Agent in Real Demographics with Synthetic Personas
•
25
upvoted 3
papers 15 days ago
How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data
Paper • 2604.14164 • Published • 35
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
Paper • 2604.14268 • Published • 117
Qwen3.5-Omni Technical Report
Paper • 2604.15804 • Published • 57
upvoted 2
articles 15 days ago
Article
Darwin-TTS: We Gave a TTS Model 3% of an LLM's Brain — It Started Showing Emotion
•
13
Article
easyaligner: Forced alignment of text and audio, made easy
•
5
upvoted an article 21 days ago
Article
"Darwin-27B-Opus: Surpassing the Foundation Model Without Training"
•
13
upvoted 6
papers 22 days ago
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents
Paper • 2604.07430 • Published • 187
ClawBench: Can AI Agents Complete Everyday Online Tasks?
Paper • 2604.08523 • Published • 261
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
Paper • 2604.08377 • Published • 289
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
Paper • 2604.06628 • Published • 323
EXAONE 4.5 Technical Report
Paper • 2604.08644 • Published • 69
WildDet3D: Scaling Promptable 3D Detection in the Wild
Paper • 2604.08626 • Published • 245
upvoted a paper 25 days ago