Himanshu Singhal

B.Tech Data Science & AI

Indian Institute of Technology Guwahati

himanshu.hs918@gmail.com

Hey! I’m Himanshu, a Data Science and AI undergraduate at the Indian Institute of Technology Guwahati, passionate about Machine Learning (ML), Deep Learning (DL), Natural Language Processing (NLP), Computer Vision (CV), and Large Language Models (LLMs).My expertise lies in Agentic AI systems, Retrieval-Augmented Generation (RAG) pipelines, and diffusion models. Currently, I’m working on my Bachelor’s Thesis on Online Signature Verification using Vision Transformers. I have previously done various projects, represented my college in two Inter IIT Tech Meets as well as research internships at Arizona State University and Adobe Research.

My research interests revolve around efficient LLMs — particularly in developing resource-efficient techniques to enhance model performance and scalability.

I’m currently seeking full-time opportunities in Applied Machine Learning, Data Science, or Software Engineering. Connect with me @himanshu.hs918@gmail.com

news

Oct 06, 2025	Submitted a paper titled *REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval* to EACL 2026 for review.
May 13, 2025	Started my summer internship at Adobe Research as a Research Intern.
Oct 26, 2022	Started my Bachelors Degree at Indian Institute of Technology, Guwahati.

selected publications

ACL ARR
REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval

Himanshu Singhal, Rishita Agarwal, Peter Baile Chen, and 3 more authors

ACL ARR 2025 October Submission, 2025

Abs Bib

Answering natural language queries over relational data often requires retrieving and reasoning over multiple tables, yet most retrievers optimize only for query-table relevance and ignore table–table compatibility. We introduce REaR (Retrieve, Expand and Refine), a three-stage, LLM-free framework that separates semantic relevance from structural joinability for efficient, high-fidelity multi-table retrieval. REaR (i) retrieves query-aligned tables, (ii) expands these with structurally joinable tables via fast, precomputed column-embedding comparisons, and (iii) refines them by pruning noisy or weakly related candidates. Empirically, REaR is retriever-agnostic and consistently improves dense/sparse retrievers on complex table QA datasets (BIRD, MMQA, and Spider) by improving both multi-table retrieval quality and downstream SQL execution. Despite being LLM-free, it delivers performance competitive with state-of-the-art LLM-augmented retrieval systems (e.g., ARM) while achieving much lower latency and cost. Ablations confirm complementary gains from expansion and refinement, underscoring REaR as a practical, scalable building block for table-based downstream tasks (e.g., Text-to-SQL).
@article{agarwal2025rear, title = {{REaR: Retrieve, Expand and Refine for Effective Multitable Retrieval}}, author = {Singhal, Himanshu and Agarwal, Rishita and Chen, Peter Baile and Choudhury, Manan Roy and Roth, Dan and Gupta, Vivek}, journal = {ACL ARR 2025 October Submission}, year = {2025}, }