Communities
Connect sessions
AI calendar
Organizations
Join Slack
Contact Sales
Search
Open menu
Home
Papers
2508.15044
Cited By
v1
v2
v3 (latest)
Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner
20 August 2025
Bolian Li
Yanran Wu
Xinyu Luo
Ruqi Zhang
Re-assign community
ArXiv (abs)
PDF
HTML
Github (12★)
Papers citing
"Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligner"
1 / 1 papers shown
Structure-R1: Dynamically Leveraging Structural Knowledge in LLM Reasoning through Reinforcement Learning
Junlin Wu
Xianrui Zhong
Jiashuo Sun
Bolian Li
Bowen Jin
Jiawei Han
Qingkai Zeng
OffRL
AI4TS
LRM
114
1
0
16 Oct 2025
1
Page 1 of 1
