Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
Paper • 2606.12370 • Published • 21
zuijiang
zuijiang
AI & ML interests
None yet
Recent Activity
upvoted a paper 20 days ago
Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling upvoted a paper 22 days ago
Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination upvoted a paper 23 days ago
dots.tts Technical ReportOrganizations
upvoted a paper 20 days ago
upvoted a paper 22 days ago
upvoted a paper 23 days ago
upvoted a paper 28 days ago
upvoted 5
papers about 1 month ago
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
Paper • 2605.29559 • Published • 17
MetaphorVU: Towards Metaphorical Video Understanding
Paper • 2605.25461 • Published • 8
MolmoAct2: Action Reasoning Models for Real-world Deployment
Paper • 2605.02881 • Published • 355
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment
Paper • 2605.19577 • Published • 59
Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding
Paper • 2605.20104 • Published • 7
upvoted 2
papers about 2 months ago
upvoted a paper 2 months ago
upvoted an article 3 months ago
Article
Releasing LiteCoder-Terminal-SFT
Lite-Coder
• • 4 upvoted 5
papers 3 months ago
RAGEN-2: Reasoning Collapse in Agentic RL
Paper • 2604.06268 • Published • 69
Composer 2 Technical Report
Paper • 2603.24477 • Published • 20
Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Paper • 2603.24472 • Published • 57
Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation
Paper • 2603.19220 • Published • 70
Complementary Reinforcement Learning
Paper • 2603.17621 • Published • 37
upvoted 2
papers 4 months ago