Elamur Research⌕
☰
home / authors / Zhengxin Zhang

Zhengxin Zhang

Zhengxin Zhang has 3 papers in our library, in 2023–2026, most of them on Language models & pretraining, Reasoning; often with Chengyu Huang, Claire Cardie, Dan Zhao.

3 papers in our library · 2023–2026

OpenAlex · ORCID · h-index 5 · 10 works · 163 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 113 times in our library · ⭐ Paper Stars ranking: #6216

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓PLA Rocket Force University of EngineeringXi'an · China2026 · 1 papercurrent🎓Carnegie Mellon UniversityPittsburgh · United States2024 · 3 papers🎓Tsinghua Shenzhen International Graduate SchoolShenzhen · China2024 · 3 papers🎓Tsinghua UniversityBeijing · China2023–2024 · 3 papers🔬Peng Cheng LaboratoryShenzhen · China2023–2024 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksHardware and Architecture · 1 work

🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 3 worksReasoning · 2 works

 Works by year

2020s

20262 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification (2023 · 220 citations)
    Serving generative LLMs is slow and expensive because autoregressive decoding emits one token per step, which leaves GPUs underused and makes key-value caches costly in memory.
  2. Better LLM Reasoning via Dual-Play (2026 · 3 citations)
    Reinforcement learning with verifiable rewards (RLVR) has improved LLM reasoning, but it depends on large sets of curated problems with correct answers.
  3. GSM-Noise: Exploring and Enhancing Large Language Models' Reasoning under Noisy Inputs (2026)
    LLMs that score well on clean math benchmarks often fail when real users send messy prompts. The authors first examined long English prompts from WildChat-1M, using QwQ-32B as a checker. Grammar slips, symbol errors, misordered statements and irrelevant content were all common, and longer prompts contained more of…

 Co-authors here

8 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 113 times (of the 149,439 papers whose bibliographies we read); 23 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/zhengxin-zhang/