How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate?
Paper • 2611.11450 • Published • 12
Jiaxin
clementinegjx
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate? upvoted a paper about 1 month ago
QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via
Agentic RL upvoted a paper about 1 month ago
Nereus: Adaptive Parallelism for LLM Post-TrainingOrganizations
None yet
upvoted a paper about 18 hours ago
upvoted 6
papers about 1 month ago
QUASAR: Quantum Assembly Code Generation Using Tool-Augmented LLMs via Agentic RL
Paper • 2510.00967 • Published • 13
Nereus: Adaptive Parallelism for LLM Post-Training
Paper • 2609.34645 • Published • 12
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Paper • 2608.09819 • Published • 113
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget
Paper • 2607.14952 • Published • 77
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
Paper • 2605.13779 • Published • 183
NeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter Scale
Paper • 2610.08430 • Published • 21
liked a
dataset 2 months ago