Anirudh Lakhotia

At Couchbase, I build SDKs and connectors for its distributed database.

My recent research examines how compression affects multi-vector retrieval. In Most MaxSim Winners Flip, Retrieval Survives (ReNeuIR @ SIGIR 2026), we show that sign coding changes most token-level MaxSim winners while largely preserving retrieval effectiveness.

Earlier, I worked on efficient multitask learning and conditional computation. UnoLoRA (FITML @ NeurIPS 2024) shares one low-rank adapter across tasks. Our task-sampling study examines how sampling strategies change a transformer’s internal representations. I also built Baraat, a multilingual mixture-of-experts system for code-switched Indic inputs.

I studied Computer Science at PES University, where I was advised by Dr. Gowri Srinivasa. Before university, I interned at Cisco, developing an event platform with a personalized recommendation system. I later built geospatial data infrastructure for Nokia’s cellular network data.

selected publications

ReNeuIR @ SIGIR

Most MaxSim Winners Flip, Retrieval Survives: Low-Margin Substitution in Sign-Coded Late Interaction

Anirudh Lakhotia and Nischal Helagally Shantharaju

5th Workshop on Reaching Efficiency in Neural Information Retrieval (ReNeuIR), co-located with ACM SIGIR, 2026

Extreme compression changes most token-level matches, yet retrieval remains robust through low-margin substitutions.

Abs PDF Listen Code

Late-interaction retrieval appears unusually robust to extreme compression. We study a sub-bit sign-coded ColBERT representation that stores each 128-dimensional document token as the 64 signs of a projected vector (0.5 bits per original dimension, 8 B/token). On a 100k-passage MS MARCO diagnostic slice, sign coding changes the MaxSim winner for roughly 70% of query tokens, yet relevant-document recall remains near the fp32 ceiling and MRR@10 is recoverable by a short fp32 rerank. We find that sign coding substantially disrupts token-level structure while leaving retrieval effectiveness largely intact. We trace this robustness to low-margin substitution: although sign coding frequently changes the winning document token, the replacement usually has a similar fp32 score, so the resulting loss in the MaxSim sum remains small. At full 8.8M-passage MS MARCO scale, a trained projection provides no statistically reliable advantage in MRR@10 or Recall@1000 over a random orthogonal projection at matched storage. A projection-training-free recipe using a random 64-dimensional projection, 8 B/token sign-coded document storage, and fp32 reranking of the top 100 candidates recovers fp32 MRR@10.
FITML @ NeurIPS

UnoLoRA: Single Low-Rank Adaptation for Efficient Multitask Fine-tuning

Akash Kamalesh^*, Anirudh Lakhotia^*, Nischal Helagally Shantharaju^*, Prerana Sanjay Kulkarni^*, and Gowri Srinivasa

Workshop on Fine-Tuning in Machine Learning, co-located with NeurIPS, 2024

*Equal contribution among the first four authors.

A single shared low-rank adapter supports efficient fine-tuning across multiple tasks.

Abs PDF Listen

Recent advances in Parameter-Efficient Fine-Tuning (PEFT) have shown Low-Rank Adaptation (LoRA) to be an effective implicit regularizer for large language models. Building on these findings, we propose UnoLoRA, a novel approach that leverages a single shared LoRA module for efficient multi-task learning. While existing methods typically use separate LoRA adaptations for each task, our approach demonstrates that a single shared adapter can effectively capture both task-specific and task-agnostic knowledge. We further introduce UnoLoRA*, an enhanced variant that employs a shared hypernetwork to generate task-specific embeddings, improving convergence and task adaptation. Our method significantly reduces trainable parameters to just 0.05% per task while maintaining competitive performance on the GLUE benchmark. Our analysis reveals that the A and B matrices in our shared LoRA adapter naturally develop complementary roles: A matrices capture generalizable features across tasks, while B matrices specialize in task-specific representations. Our results show that sharing a single LoRA adapter can achieve efficient multi-task learning while significantly reducing memory requirements, making it particularly valuable for resource-constrained applications.

… all publications →

news

Jul 24, 2026	Presented Most MaxSim Winners Flip, Retrieval Survives at ReNeuIR @ SIGIR 2026.
Jul 01, 2025	Joined Couchbase full-time as a Software Engineer on the SDKs & Connectors team.
Oct 10, 2024	Our undergraduate thesis, UnoLoRA, was accepted to FITML @ NeurIPS 2024.

… all news →