arXiv subjects

Abhishikth Mallampalli

Publications and source records attributed to Abhishikth Mallampalli.

4 recordsLinked to original sources

arXiv2026

MITRA: An AI Assistant for Knowledge Retrieval in Physics Collaborations

Large-scale scientific collaborations, such as the Compact Muon Solenoid (CMS) at CERN, produce a vast and ever-growing corpus of internal documentation. Navigating this complex information landscape presents a significant challenge for both new and experienced researchers, hindering knowledge sharing and slowing down the pace of scientific discovery. To address this, we present a prototype of MITRA, a Retrieval-Augmented Generation (RAG) based system, designed to answer specific, context-aware questions about physics analyses. MITRA employs a novel, automated pipeline using Selenium for document retrieval from internal databases and Optical Character Recognition (OCR) with layout parsing for high-fidelity text extraction. Crucially, MITRA's entire framework, from the embedding model to the Large Language Model (LLM), is hosted on-premise, ensuring that sensitive collaboration data remains private. We introduce a two-tiered vector database architecture that first identifies the relevant analysis from abstracts before focusing on the full documentation, resolving potential ambiguities between different analyses. We demonstrate the prototype's superior retrieval performance against a standard keyword-based baseline on realistic queries and discuss future work towards developing a comprehensive research agent for large experimental collaborations.

cs.IR↗

arXiv2026

Searching solo for the invisible at Compact Muon Solenoid (CMS)

Despite the success of the Standard Model (SM), several fundamental questions remain unanswered, such as the nature of dark matter (DM), motivating searches for new physics. This paper summarizes three recent searches for new physics in proton-proton collisions at a center-of-mass energy of $\sqrt{s}=13$ TeV, using data recorded with the Compact Muon Solenoid (CMS) detector at the CERN Large Hadron Collider (LHC). The searches focus on "mono-X" final states, characterized by a large imbalance in transverse momentum recoiling against a single visible SM particle ($X$), and serve as powerful probes of new physics scenarios. Results are presented for searches in the pencil-jet (low-multiplicity jet), mono-photon, and mono-top final states, using CMS Run 2 data corresponding to an integrated luminosity of 138 fb$^{-1}$. No significant excess of events beyond SM predictions is observed, and the results are used to set stringent exclusion limits on various new physics scenarios, including simplified DM models and models of large extra spacetime dimensions.

hep-ex↗

arXiv2025

Evaluation of Novel Fast Machine Learning Algorithms for Knowledge-Distillation-Based Anomaly Detection at CMS

The CICADA (Calorimeter Image Convolutional Anomaly Detection Algorithm) project aims to detect anomalous physics signatures without bias from theoretical models in proton-proton collisions at the Compact Muon Solenoid (CMS) experiment at the Large Hadron Collider. CICADA identifies anomalies in low-level calorimeter trigger data using a convolutional autoencoder, whose behavior is transferred to compact student models via knowledge distillation. Careful model design and quantization ensure sub-200 ns inference times on FPGAs. We investigate novel student model architectures that employ differentiable relaxations to enable extremely fast inference at the cost of slower training -- a welcome tradeoff in the knowledge distillation context. Evaluated on CMS open data and under emulated FPGA conditions, these models achieve comparable anomaly detection performance to classically quantized baselines with significantly reduced resource usage. The savings in resource usage enable the possibility to look at a richer input granularity.

hep-ex↗

arXiv2025

Building Machine Learning Challenges for Anomaly Detection in Science

Scientific discoveries are often made by finding a pattern or object that was not predicted by the known rules of science. Oftentimes, these anomalous events or objects that do not conform to the norms are an indication that the rules of science governing the data are incomplete, and something new needs to be present to explain these unexpected outliers. The challenge of finding anomalies can be confounding since it requires codifying a complete knowledge of the known scientific behaviors and then projecting these known behaviors on the data to look for deviations. When utilizing machine learning, this presents a particular challenge since we require that the model not only understands scientific data perfectly but also recognizes when the data is inconsistent and out of the scope of its trained behavior. In this paper, we present three datasets aimed at developing machine learning-based anomaly detection for disparate scientific domains covering astrophysics, genomics, and polar science. We present the different datasets along with a scheme to make machine learning challenges around the three datasets findable, accessible, interoperable, and reusable (FAIR). Furthermore, we present an approach that generalizes to future machine learning challenges, enabling the possibility of large, more compute-intensive challenges that can ultimately lead to scientific discovery.

cs.LG↗