Elamur Research⌕
☰
home / authors / Rajiv Mathews

Rajiv Mathews

Rajiv Mathews has 2 papers in our library, in 2026, most of them on Language models & pretraining, Speech & spoken language; often with Soheil Feizi, Vinu Sankar Sadasivan.

2 papers in our library · 2026

OpenAlex · h-index 13 · 51 works · 1,923 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 12 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #11249

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

🏢GoogleMountain View · United States2018–2026 · 27 paperscurrent🎓University of Maryland, College ParkCollege Park · United States2026 · 1 papercurrent🎓Vanderbilt UniversityNashville · United States2026 · 1 papercurrent🏢Google DeepMindLondon · United Kingdom2024–2025 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 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 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 2Research subjects and languages the work is about.Language models & pretraining · 1 workSpeech & spoken language · 1 work

 Works by year

2020s

20262 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World (2026 · 2 citations)
    The paper examines whether audio-based LLMs (ALLMs) can be steered by sound an attacker plays nearby. Most jailbreak work only produces harmful output for the attacker. Here the concern is attacks that reach innocent users through their microphones. Working in a white-box setting with the instruction-tuned…
  2. We Are What We Repeatedly Do: Improving Long Context Instruction Following (2026)
    LLM context windows have grown enormously, but models tend to drift away from user instructions as conversations get longer.

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. Federated Learning of N-Gram Language Models ↗Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL) · no summary yetMingqing Chen et al.2019 · 67 citations
  2. Attacker's Noise Can Manipulate Your Audio-based LLM in the Real WorldConference of the European Chapter of the Association for Computational Linguistics (EACL)Vinu Sankar Sadasivan, Soheil Feizi, Rajiv Mathews, et al.2026 · 2 citations
  3. We Are What We Repeatedly Do: Improving Long Context Instruction FollowingFindings of the Association for Computational LinguisticsPreston K Robinette, Andrew Hard, Swaroop Ramaswamy, et al.2026

 Co-authors here

2 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 12 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated

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