Publications

You can also find my articles on my Google Scholar profile.

Conference Papers

Learning to Generate Rules for Realistic Few-Shot Relation Classification: An Encoder-Decoder Approach

Published in Findings of the Association for Computational Linguistics: EMNLP, 2024

We propose a neuro-symbolic approach for realistic few-shot relation classification via rules. Instead of building neural models to predict relations, we design them to output straightforward rules that can be used to extract relations. The rules are generated using custom T5-style Encoder-Decoder Language Models. Crucially, our rules are fully interpretable and pliable (i.e., humans can easily modify them to boost performance). Through a combination of rules generated by these models along with a very effective, novel baseline, we demonstrate a few-shot relation-classification performance that is comparable to or stronger than the state of the art on the Few-Shot TACRED and NYT29 benchmarks while increasing interpretability and maintaining pliability.

Recommended citation: Mayank Singh and Eduardo Blanco. 2024. Learning to Generate Rules for Realistic Few-Shot Relation Classification: An Encoder-Decoder Approach. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 5907–5921, Miami, Florida, USA.
Download Paper

Journal Articles

Cloud-Based Collaborative 3D Mapping in Real-Time With Low-Cost Robots

Published in IEEE Transactions on Automation Science and Engineering, 2015

This paper presents an architecture, protocol, and parallel algorithms for collaborative 3D mapping in the cloud with low-cost robots. The robots run a dense visual odometry algorithm on a smartphone-class processor. Key-frames from the visual odometry are sent to the cloud for parallel optimization and merging with maps produced by other robots. After optimization the cloud pushes the updated poses of the local key-frames back to the robots. All processes are managed by Rapyuta, a cloud robotics framework that runs in a commercial data center. This paper includes qualitative visualization of collaboratively built maps, as well as quantitative evaluation of localization accuracy, bandwidth usage, processing speeds, and map storage.

Recommended citation: G. Mohanarajah, V. Usenko, M. Singh, R. D'Andrea and M. Waibel, Cloud-Based Collaborative 3D Mapping in Real-Time With Low-Cost Robots, in IEEE Transactions on Automation Science and Engineering, vol. 12, no. 2, pp. 423-431, April 2015
Download Paper

Preprints

Error Taxonomy-Guided Prompt Optimization

Published in arXiv, 2026

Automatic Prompt Optimization (APO) is a powerful approach for extracting performance from large language models without modifying their weights. Many existing methods rely on trial-and-error, testing different prompts or in-context examples until a good configuration emerges, often consuming substantial compute. Recently, natural language feedback derived from execution logs has shown promise as a way to identify how prompts can be improved. However, most prior approaches operate in a bottom-up manner, iteratively adjusting the prompt based on feedback from individual problems, which can cause them to lose the global perspective. In this work, we propose Error Taxonomy-Guided Prompt Optimization (ETGPO), a prompt optimization algorithm that adopts a top-down approach. ETGPO focuses on the global failure landscape by collecting model errors, categorizing them into a taxonomy, and augmenting the prompt with guidance targeting the most frequent failure modes. Across multiple benchmarks spanning mathematics, question answering, and logical reasoning, ETGPO achieves accuracy that is comparable to or better than state-of-the-art methods, while requiring roughly one third of the optimization-phase token usage and evaluation budget.

Recommended citation: Mayank Singh, Vikas Yadav, and Eduardo Blanco. 2026. Error Taxonomy-Guided Prompt Optimization. arXiv:2602.00997 [cs.AI].
Download Paper

Grammar Search for Multi-Agent Systems

Published in arXiv, 2025

Automatic search for Multi-Agent Systems has recently emerged as a key focus in agentic AI research. Several prior approaches have relied on LLM-based free-form search over the code space. In this work, we propose a more structured framework that explores the same space through a fixed set of simple, composable components. We show that, despite lacking the generative flexibility of LLMs during the candidate generation stage, our method outperforms prior approaches on four out of five benchmarks across two domains: mathematics and question answering. Furthermore, our method offers additional advantages, including a more cost-efficient search process and the generation of modular, interpretable multi-agent systems with simpler logic.

Recommended citation: Mayank Singh, Vikas Yadav, Shiva Krishna Reddy Malay, Shravan Nayak, Sai Rajeswar, Sathwik Tejaswi Madhusudhan, and Eduardo Blanco. 2025. Grammar Search for Multi-Agent Systems. arXiv:2512.14079 [cs.AI].
Download Paper