Elamur Research⌕
☰
home / authors / Bhaskar Ramasubramanian

Bhaskar Ramasubramanian

Bhaskar Ramasubramanian has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Reasoning, Bias, fairness & safety; often with Fengqing Jiang, Luyao Niu, Radha Poovendran.

2 papers in our library · 2024–2025

OpenAlex · ORCID · h-index 8 · 73 works · 255 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 132 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #7193

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

🎓Western Washington UniversityBellingham · United States2021–2026 · 30 papersEmployment since 2021 · Assistant Professor, Engineering and Designcurrent🎓University of WashingtonSeattle · United States2018–2026 · 12 papersEmployment 2018–2022 · Postdoctoral Research Associate, Electrical and Computer Engineeringcurrent🎓Washington University in St. LouisSt Louis · United States2025–2026 · 2 paperscurrent🎓University of Maryland, College ParkCollege Park · United States2015–2017 · 4 papers
🏛️University of MarylandCollege Park · United StatesEducation · Ph.D., Electrical and Computer Engineering

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 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 3Research subjects and languages the work is about.Reasoning · 1 workBias, fairness & safety · 1 workLanguage models & pretraining · 1 work

 Works by year

2020s

20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMs (2024 · 83 citations)
    Current safety alignment methods for LLMs, such as supervised fine-tuning, RLHF and red-teaming, assume that text is understood only through the meaning of its tokens. Text can also carry visual information, as in ASCII art. The authors test whether this blind spot can be exploited.
  2. Small Models Struggle to Learn from Strong Reasoners (2025 · 61 citations)
    Distilling reasoning traces from powerful LLMs into compact models is commonly assumed to help more as the teacher gets stronger.

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. ArtPrompt: ASCII Art-based Jailbreak Attacks against Aligned LLMsarXiv:2402.11753Fengqing Jiang, Zhangchen Xu, Luyao Niu, et al.2024 · 83 citations
  2. Small Models Struggle to Learn from Strong ReasonersFindings of the Association for Computational LinguisticsYuetai Li, Xiang Yue, Zhangchen Xu, et al.2025 · 61 citations
  3. JobBench: Aligning Agent Work With Human Will ↗arXiv (Cornell University) · no summary yetYuetai Li et al.2026 · 1 citation

 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 132 times (of the 149,439 papers whose bibliographies we read); 44 citing papers with a page here →.

Updated

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