Qiwei Di

activity

20232026

most citedUnified Convergence Analysis for Score-Based Diffusion Models with Deterministic Samplers

1 citations · 1 across the 11 of their papers we have counts for

collaborators

Showing 2025Show all

2 papers · 1 filter

cs.LG2025

On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference

Yue Yu, Qiwei Di, Quanquan Gu +1

Test-time compute (TTC) has become an increasingly prominent paradigm for enhancing large language models (LLMs). Despite the empirical success of methods such as best-of- $n$ (BoN)…

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…

On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference

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

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