Research
Papers and ongoing work by Rajkiran Panuganti on Generative AI, with a current focus on mechanistic interpretability of transformer models. Earlier work covers parallel computing, compiler optimization, and image super-resolution.
Rajkiran Panuganti on Google Scholar for publications and citations.
FABRIC: AI Financial Advisors Hallucinate More Than They Forget on Indian Markets
SSRN · 2026A benchmark of 204 verified Indian financial questions across six languages. Evaluates seven models on 16,000+ responses. Finds hallucination is the dominant failure mode, Indian-origin models do not perform better on Indian financial questions, and Hinglish outperforms pure Hindi. WebRAG dramatically reduces both hallucination and outdated errors.
Read paper →CircuitProbe: Predicting Reasoning Circuits in Transformers via Stability Zone Detection
arXiv · 2026A method for predicting where reasoning circuits live inside transformer models by detecting stability zones in activation statistics. Replaces brute-force layer search with a process roughly 1000x faster.
Read paper →Krutrim LLM: Multilingual Foundational Model for over a Billion People
arXiv · 2025 · Additional contributorThe Krutrim LLM technical report credits Rajkiran Panuganti as an additional contributor. It describes the team's multilingual foundation model and its development.
Read paper →MATLAB: A Language for Parallel Computing
International Journal of Parallel Programming · 2008Presents extensions to MATLAB for parallel computing including mexMPI for message passing and GAMMA for distributed shared memory, enabling high-performance computing while retaining MATLAB's productivity.
Read paper →A Learning-Based Method for Image Super-Resolution from Zoomed Observations
IEEE Transactions on Systems, Man and Cybernetics, Part B · 2005A machine learning approach to image super-resolution using observations at different camera zoom levels.
Read paper →Integrated Loop Optimizations for Data Locality Enhancement of Tensor Contraction Expressions
SC 2005 (Supercomputing) · 2005Compiler optimizations for improving data locality in tensor contraction computations used in quantum chemistry.
Read paper →Cache Miss Characterization and Data Locality Optimization for Imperfectly Nested Loops on Shared Memory Multiprocessors
IPDPS 2005 · 2005Analysis and optimization of cache performance for irregular loop structures on shared-memory parallel systems.
Read paper →Super-Resolution Imaging: Use of Zoom as a Cue
Image and Vision Computing · 2004Obtaining high-resolution images of a scene from observations at different camera zoom levels. B.Tech thesis work at IIT Bombay, advised by Dr. Subhasis Chaudhuri.
Read paper →A High Productivity Framework for Parallel Data Intensive Computing in MATLAB
PhD Thesis, The Ohio State University · 2008Presents mexMPI, GAMMA, and LA: three frameworks enabling parallel computing directly in MATLAB for high-performance workloads while retaining MATLAB's productivity. Advisor: P. Sadayappan.
Read paper →