arXiv subjects

Kunal Sawarkar

Publications and source records attributed to Kunal Sawarkar.

5 recordsLinked to original sources

arXiv2026

UniK: Universal Knowledge Perception for Digital and Physical AI

Two transformative classes of AI systems are reshaping how organizations operate: \textit{digital AI}, which reasons over enterprise knowledge to power chatbots and agent workflows; and \textit{physical AI}, which learns to control robots and autonomous systems from video, gameplay, and sensor telemetry. Both face the same foundational bottleneck: raw knowledge at scale, spanning heterogeneous modalities, locked in private corpora that existing AI infrastructure cannot access reliably or efficiently. We propose \textit{Universal Knowledge Perception (UniK)} as a common platform for both classes, covering the full knowledge lifecycle (ingestion, enrichment, indexing, retrieval, and continuous evaluation) across modalities from rich text and video to molecular data and sensor telemetry. We present UniK, built on Polymath Retrieval (multi-index fusion over automatically enriched indices) with no task-specific fine-tuning. Across five digital AI domains (medical literature, open-domain QA, chemistry, legal video proceedings, and government open data) UniK combined with an open-source 70-billion-parameter model consistently matches or outperforms frontier proprietary LLMs that are orders of magnitude larger: 76\% RAG accuracy on government data versus 47\% for GPT-5; 77.9\% on medical QA without fine-tuning; topping all open-source chemistry pipelines. We show that the same infrastructure directly addresses the data curation, indexing, and retrieval challenges facing physical AI world model training, where the knowledge problem is harder but structurally identical.

cs.AI↗

arXiv2025

MetaGen Blended RAG: Unlocking Zero-Shot Precision for Specialized Domain Question-Answering

Retrieval-Augmented Generation (RAG) struggles with domain-specific enterprise datasets, often isolated behind firewalls and rich in complex, specialized terminology unseen by LLMs during pre-training. Semantic variability across domains like medicine, networking, or law hampers RAG's context precision, while fine-tuning solutions are costly, slow, and lack generalization as new data emerges. Achieving zero-shot precision with retrievers without fine-tuning still remains a key challenge. We introduce 'MetaGen Blended RAG', a novel enterprise search approach that enhances semantic retrievers through a metadata generation pipeline and hybrid query indexes using dense and sparse vectors. By leveraging key concepts, topics, and acronyms, our method creates metadata-enriched semantic indexes and boosted hybrid queries, delivering robust, scalable performance without fine-tuning. On the biomedical PubMedQA dataset, MetaGen Blended RAG achieves 82% retrieval accuracy and 77% RAG accuracy, surpassing all prior zero-shot RAG benchmarks and even rivaling fine-tuned models on that dataset, while also excelling on datasets like SQuAD and NQ. This approach redefines enterprise search using a new approach to building semantic retrievers with unmatched generalization across specialized domains.

cs.CL↗

arXiv2024

Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers

Retrieval-Augmented Generation (RAG) is a prevalent approach to infuse a private knowledge base of documents with Large Language Models (LLM) to build Generative Q\&A (Question-Answering) systems. However, RAG accuracy becomes increasingly challenging as the corpus of documents scales up, with Retrievers playing an outsized role in the overall RAG accuracy by extracting the most relevant document from the corpus to provide context to the LLM. In this paper, we propose the 'Blended RAG' method of leveraging semantic search techniques, such as Dense Vector indexes and Sparse Encoder indexes, blended with hybrid query strategies. Our study achieves better retrieval results and sets new benchmarks for IR (Information Retrieval) datasets like NQ and TREC-COVID datasets. We further extend such a 'Blended Retriever' to the RAG system to demonstrate far superior results on Generative Q\&A datasets like SQUAD, even surpassing fine-tuning performance.

cs.IR↗

arXiv2020

Automated Metadata Harmonization Using Entity Resolution & Contextual Embedding

ML Data Curation process typically consist of heterogeneous & federated source systems with varied schema structures; requiring curation process to standardize metadata from different schemas to an inter-operable schema. This manual process of Metadata Harmonization & cataloging slows efficiency of ML-Ops lifecycle. We demonstrate automation of this step with the help of entity resolution methods & also by using Cogntive Database's Db2Vec embedding approach to capture hidden inter-column & intra-column relationships which detect similarity of metadata and then predict metadata columns from source schemas to any standardized schemas. Apart from matching schemas, we demonstrate that it can also infer the correct ontological structure of the target data model.

cs.DB↗

arXiv2020

Dynamically Tie the Right Offer to the Right Customer in Telecommunications Industry

For a successful business, engaging in an effective campaign is a key task for marketers. Most previous studies used various mathematical models to segment customers without considering the correlation between customer segmentation and a campaign. This work presents a conceptual model by studying the significant campaign-dependent variables of customer targeting in customer segmentation context. In this way, the processes of customer segmentation and targeting thus can be linked and solved together. The outcomes of customer segmentation of this study could be more meaningful and relevant for marketers. This investigation applies a customer life time value (LTV) model to assess the fitness between targeted customer groups and marketing strategies. To integrate customer segmentation and customer targeting, this work uses the genetic algorithm (GA) to determine the optimized marketing strategy. Later, we suggest using C&RT (Classification and Regression Tree) in SPSS PASW Modeler as the replacement to Genetic Algorithm technique to accomplish these results. We also suggest using LOSSYCOUNTING and Counting Bloom Filter to dynamically design the right and up-to-date offer to the right customer.

cs.IR↗