🧑‍🔬 Keerthiram Murugesan

🏛️ Affiliations

🏢IBMArmonk · United States2021–2026 · 52 paperscurrent🎓Carnegie Mellon UniversityPittsburgh · United States2016–2018 · 8 papers🔬IBM Research - Thomas J. Watson Research CenterYorktown Heights · United States2022–2025 · 7 papers🎓ETH ZurichZurich · Switzerland2021 · 2 papers🔬IBM Research - ZurichRüschlikon · Switzerland2021 · 2 papers🎓University of KentuckyLexington · United States2011 · 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering (2026 · 4 citations)
   With so many LLMs and agent strategies available, it is hard to know which configuration will work best for a given QA task.
2. OjaKV: Context-Aware Online Low-Rank KV Cache Compression (2026 · 2 citations)
   Long-context LLM inference is limited by GPU memory for the key-value (KV) cache. For Llama-3.1-8B with a 32K-token prompt at batch size 4, the cache reaches about 16 GB, roughly the size of the model weights. Earlier low-rank compression methods project keys and values onto a fixed basis learned offline from…
3. Context Attribution with Multi-Armed Bandit Optimization (2026)
   In retrieval-augmented generation, it helps to know which retrieved passages actually shaped an LLM's answer.
4. NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering (2026)
   The paper tackles nutrition question answering, where a system must judge whether a food suits a particular person given their health conditions, habits and the food's nutritional profile.

All works

7 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning ↗Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetSubhajit Chaudhury et al.2023 · 5 citations
2. AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question AnsweringAnnual Meeting of the Association for Computational Linguistics (ACL)Zheyuan Zhang, Kaiwen Shi, Zhengqing Yuan, et al.2026 · 4 citations
3. OjaKV: Context-Aware Online Low-Rank KV Cache CompressionFindings of the Association for Computational LinguisticsYuxuan Zhu, David H. Yang, Mohammad Mohammadi Amiri, et al.2026 · 2 citations
4. Context Attribution with Multi-Armed Bandit OptimizationFindings of the Association for Computational LinguisticsDeng Pan, Keerthiram Murugesan, Ting Hua, et al.2026
5. NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question AnsweringConference of the European Chapter of the Association for Computational Linguistics (EACL)Kaiwen Shi, Zheyuan Zhang, Zhengqing Yuan, et al.2026
6. The Unlearning Mirage: A Dynamic Framework for Evaluating LLM Unlearning ↗arXiv (Cornell University) · no summary yetRaj Sanjay Shah et al.2026
7. ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value Retrieval ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetDavid H. Yang et al.2026

🤝 Co-authors here

12 of 13 co-authors with a page, the most papers together first.

• Chuxu Zhang ×2
• Kaiwen Shi ×2
• Vincent Galassi ×2
• Yanfang Ye ×2
• Zhengqing Yuan ×2
• Zheyuan Zhang ×2
• Nitesh V. Chawla
• Nuno Moniz
• Pin-Yu Chen
• Tejaswini Pedapati
• Tianyi Ma
• Yuxuan Zhu

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×3: ACL 2026
• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Conference of the European Chapter of the Association for Computational Linguistics (EACL): EACL 2026

🔗 Cited by

Papers of our library cite their works 7 times (of the 149,439 papers whose bibliographies we read); 2 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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