Kaixuan Ji

activity

20212026

most citedP-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

266 citations · 298 across the 14 of their papers we have counts for

collaborators

Showing 2025Show all

2 papers · 1 filter

cs.LG2025

Best-of-Majority: Minimax-Optimal Strategy for Pass@ $k$ Inference Scaling

Qiwei Di, Kaixuan Ji, Xuheng Li +2

LLM inference often generates a batch of candidates for a prompt and selects one via strategies like majority voting or Best-of- N (BoN). For difficult tasks, this single-shot sele…

cs.LG2025

Towards a Sharp Analysis of Offline Policy Learning for $f$ -Divergence-Regularized Contextual Bandits

Qingyue Zhao, Kaixuan Ji, Heyang Zhao +2

Many offline reinforcement learning algorithms are underpinned by $f$ -divergence regularization, but their sample complexity *defined with respect to regularized objectives* still…

Best-of-Majority: Minimax-Optimal Strategy for Pass@k Inference Scaling

Towards a Sharp Analysis of Offline Policy Learning for f-Divergence-Regularized Contextual Bandits

Best-of-Majority: Minimax-Optimal Strategy for Pass@ $k$ Inference Scaling

Towards a Sharp Analysis of Offline Policy Learning for $f$ -Divergence-Regularized Contextual Bandits