Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2509.21009
Cited By
RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training
25 September 2025
Wei Gao
Yuheng Zhao
Dakai An
Tianyuan Wu
Lunxi Cao
Shaopan Xiong
Ju Huang
Weixun Wang
Siran Yang
Yuchi Xu
Jiamang Wang
Lin Qu
B. Zheng
Wei Wang
OffRL
VLM
Re-assign community
ArXiv (abs)
PDF
HTML
Papers citing
"RollPacker: Mitigating Long-Tail Rollouts for Fast, Synchronous RL Post-Training"
3 / 3 papers shown
Fast LLM Post-training via Decoupled and Fastest-of-N Speculation
Rongxin Cheng
Kai Zhou
Xingda Wei
Siyuan Liu
Mingcong Han
...
Yeju Zhou
Baoquan Zhong
W. L. Xiao
Rong Chen
Haibo Chen
OffRL
LRM
436
0
0
24 Dec 2025
ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
Qiaoling Chen
Zijun Liu
Peng Sun
Shenggui Li
Guoteng Wang
Ziming Liu
Yonggang Wen
Siyuan Feng
Tianwei Zhang
104
2
0
30 Oct 2025
Part II: ROLL Flash -- Accelerating RLVR and Agentic Training with Asynchrony
H. Lu
Zichen Liu
Shaopan Xiong
Yancheng He
W. Gao
...
Wei Wang
Wenbo Su
Jiamang Wang
Lin Qu
Bo Zheng
OffRL
98
1
0
13 Oct 2025
1
