Researcher — paper.dinq.me

2026 顶会论文

作者位次 #4/6OSDI 2026Oral· Operating Systems & Distributed Systems

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

Shuzhang Zhong · Haochen Huang · Shengxuan Qiu · Pengfei Zuo · Runsheng Wang · Meng Li

摘要

Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving complex mathematical and programming tasks. However, its efficiency is constrained by the _reward dependency barrier_—a synchronization bottleneck cau...

效率与系统推理代码OpenReview

作者位次 #4/5ICML 2026Poster· Deep Learning / Large Language Models

HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction

Shengxuan Qiu · Haochen Huang · Shuzhang Zhong · Pengfei Zuo · Meng Li

推理OpenReview

作者位次 #2/6ICML 2026Poster· Deep Learning / Attention Mechanisms

TileSparse: Arithmetic-Intensity-Aware Sparse Attention for Compute-Bound LLM Decoding

Chao Wang · Pengfei Zuo · Zhangyu Chen · Qihui Zhou · Tsung-Yi Ho · Ming-Chang Yang

可解释性代码OpenReview

Pengfei Zuo

获取完整研究档案

联系方式

2026 顶会论文

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration

HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction

TileSparse: Arithmetic-Intensity-Aware Sparse Attention for Compute-Bound LLM Decoding

常见合作者