Skip To Main Content
Hongyin Luo on Muck Rack

Hongyin Luo

As seen in: arXiv
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work. Claim your profile

Get in touch with Hongyin

Contact Hongyin, search articles and posts on X, monitor coverage, and track replies from one place.

Learn more about Muck Rack

Actions

Share this page

Is this you?

As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile

Articles

Thought-Level Beam Search for Reasoning

|
By Lijie Yang, Hongyin Luo, Jiawei Zhao
| huggingface.co
Abstract Gambit improves reasoning model efficiency by using thought-level beam search to dynamically allocate compute to promising reasoning traces under fixed hardware budgets. Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from how much compute to spend, to where to allocate it.
Open in Who Shared Issue with article?

[2410.01769] Quantifying Generalization Complexity for Large Language Models

|
By Hongyin Luo, Zhuokai Zhao, Yibo Jiang, Xuliang Huang
| arXiv
Open in Who Shared Issue with article?

[2309.10814] Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning

|
By Jiaxin Ge, Mingye Gao, Hongyin Luo, Yung-Sung Chuang
| arXiv
arXiv:2309.10814 (cs) [Submitted on 19 Sep 2023 (v1), last revised 29 Mar 2024 (this version, v2)] View PDF HTML (experimental) Comments: Subjects: Computation and Language (cs.CL) Cite as: arXiv:2309.10814 [cs.CL] (or arXiv:2309.10814v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2309.10814 Submission history From: Hongyin Luo [ view email] [v1] Tue, 19 Sep 2023 17:54:21 UTC (366 KB) [v2] Fri, 29 Mar 2024 01:18:18 UTC (8,372 KB) Bibliographic Tools Bibliographic Explorer Toggle...
Open in Who Shared View Duplicates (247) Issue with article?
See all 3 articles