Elamur Research⌕
☰
home / authors / Jin Song Dong

Jin Song Dong

Jin Song Dong has 2 papers in our library, in 2026, most of them on GPU & parallel computing, Bias, fairness & safety; often with Jiahao Liu, Xiaoyue Lu, Yan Xiao.

2 papers in our library · 2026

OpenAlex · h-index 1 · 4 works · 1 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 2 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #10931

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

🎓National University of SingaporeSingapore · Singapore2026 · 2 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

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

📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksHardware and Architecture · 1 workSafety Research · 1 workSocial Sciences · 1 workSoftware · 1 work

🧭 Topics 2Research subjects and languages the work is about.GPU & parallel computing · 1 workBias, fairness & safety · 1 work

 Works by year

2020s

20262 papers

 Papers

The most cited first (OpenAlex and our library).

  1. CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention Kernels (2026 · 3 citations)
    Fast CUDA kernels for new attention variants, such as custom masks, altered score functions or different normalization, are hard to build.
  2. Inverting the Shield: Systematically Generating Safety Tests from Policy Specifications (2026)
    Current LLM safety evaluation depends on two approaches. Static benchmarks are costly, prone to contamination, and age quickly. Red-teaming is heuristic, and neither can show which policy clauses were actually tested. The authors propose POLARIS, which borrows specification-based testing from software engineering. It…

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. CuBridge: An LLM-Based Framework for Understanding and Reconstructing High-Performance Attention KernelsAnnual Meeting of the Association for Computational Linguistics (ACL)Xing Ma, Yangjie Zhou, Wu Sun, et al.2026 · 3 citations
  2. Inverting the Shield: Systematically Generating Safety Tests from Policy SpecificationsAnnual Meeting of the Association for Computational Linguistics (ACL)Xiaoyue Lu, Xianglin Yang, Haijun Liu, et al.2026
  3. Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetYuan Xiao et al.2026

 Co-authors here

4 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 2 times (of the 149,439 papers whose bibliographies we read).

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jin-song-dong/