activity
20232026
most citedDivide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning

1 citations · 2 across the 10 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration

Langlin Huang, Chengsong Huang, Jinyuan Li +3

Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Mode…