Langlin Huang | 黄浪林

I am a second-year PhD student at Washington University in St. Louis (WUSTL), luckily advised by Prof. Jiaxin Huang.

Before that, I received my Master degree at Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS) in Jul. 2024, where I studied at ICT Natural Language Processing (ICTNLP) group. I received my B.E. degree in Data Science and Big Data Technology from University of International Business and Economics (UIBE) in Jun. 2021.

Email: h.langlin [at] wustl.edu

[ CV ] | Google Scholar   /    DBLP   /    Github

profile photo
Research

My research interests mainly lie in Natural Language Processing and Large Language Models. Particularly, I am interested in:

  • Large Language Model Reasoning.
  • Efficient language model generation, Speculative Decoding, Efficient in-context learning.
  • Multilingual large language model, Machine Translation.

News

[2025/07] Our CrossWordBench is accepted by COLM 2025. Thanks to all collaborators!

[2025/06] We released PosS, an effective Speculative Decoding method that reaches the highest draft predicton accuracy.

[2025/04] We released CrossWordBench, a challenging multimodal Benchmark that requires continuous reasoning ability.

[2025/02] One paper about Adaptive Heterogeneous MoE for flexible tokenization is accepted by NAACL 2025 as oral representation. Thanks to all collaborators!

[2025/02] We released Efficient Test-Time Scaling via Self-Calibration, finding self-calibration efficiently improves test-time scaling method which saves up to 94% sampling.

[2024/10] We released LARA, A logit aggregation approach for In-Context Learning!

[2024/08] My new journey set sail on Washington University in St. Louis, I love the peaceful campus and welcoming people!

[2024/06] One paper about Byte-based Language Model is accepted to ACL 2024! Thanks to all collaborators!

[2024/05/21] I successfully defended my dissertation for Master degree! My dissertation name is "A Study of Neural Machine Translation on Multiple Semantic Granularities (基于多语义粒度的神经机器翻译研究)".

[2023/10] One paper about Compositional Phrase Representationis accepted to EMNLP 2023! Thanks to all collaborators!

[2023/06] Our LLM BayLing (百聆) is released! BayLing is an instruction-following LLM with advanced language alignment and multi-turn interaction capability. Read our paper and try our online demo! Thanks to all collaborators!

[2022/07] We won first place in the Chinese-Thai track and second place in the Mongolian-Chinese track in the 18th China Conference on Machine Translation (CCMT 2022)! Thanks to all collaborators! The technical report is accessible to public, check here for Chinese-Thai track and here for Mongolian-Chinese track.

[2021/09] I start my M.S. life at University of Chinese Academy of Sciences (UCAS).

[2021/06] I obtain my B.E. degree from University of International Business and Economics (UIBE).

[2020/06] One paper about automatic construction of depression-domain lexicon is published on JMIR Medical Informatics! Thanks to all collaborators!
Publications

LLM Reasoning

POSS: Position Specialist Generates Better Draft for Speculative Decoding
Langlin Huang, Chengsong Huang, Jixuan Leng, Di Huang, Jiaxin Huang
Paper / Code

CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
Jixuan Leng, Chengsong Huang, Langlin Huang, Bill Yuchen Lin, William W. Cohen, Haohan Wang, Jiaxin Huang
COLM 2025
Paper / Code / Dataset

Efficient Test-Time Scaling via Self-Calibration
Chengsong Huang, Langlin Huang, Jixuan Leng, Jiacheng Liu, Jiaxin Huang
Paper / Code

Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
Chengsong Huang, Langlin Huang, Jiaxin Huang
Paper / Code

Multilingual

MoCE: Adaptive Mixture of Contextualization Experts for Byte-based Neural Machine Translation
Langlin Huang, Mengyu Bu, Yang Feng
NAACL 2025 (oral)
Paper / Code

Integrating Multi-scale Contextualized Information for Byte-based Neural Machine Translation
Langling Huang, Yang Feng
ACL 2024
Paper / Code

Enhancing Neural Machine Translation with Semantic Units
Langling Huang, Shuhao Gu, Zhuocheng Zhang, Yang Feng
EMNLP 2023
Paper / Code

BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
Shaolei Zhang, Qingkai Fang, Zhuocheng Zhang, Zhengrui Ma, Yan Zhou, Langlin Huang, Mengyu Bu, Shangtong Gui, Yunji Chen, Xilin Chen, Yang Feng
Paper / Code / Demo / Project Page

Ohters

Automatic Construction of a Depression-Domain Lexicon Based on Microblogs: Text Mining Study
Genghao Li, Bing Li, Langlin Huang, Sibing Hou
JMIR Medical Informatics
Paper
Awards

Second Academic Scholarship, at UCAS, Sep. 2023

Outstanding Graduates, at UIBE, Jun. 2021

First Academic Scholarship, at UIBE, 2018, 2019, 2020

Merit Student of UIBE, 2018, 2019, 2020

Honorable Mention of Mathematical Contest In Modeling, Apr. 2020

First Prize of Asia and Pacific Mathematical Contest in Modeling, Jan. 2020

First Prize of Chinese Mathematical Contest In Modeling, Beijing Area, Sep. 2018
Services

Reviewer: NeurIPS 2025, COLM 2025, ICLR 2025, ACL Rolling Review, ACL 2023, TALLIP



Updated at Aug. 2025