Vansh Sharma

Dr. Vansh Sharma

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 January 2025 in Combustion and Flame
Verified
Journal Article
Closed access
SASebastian Abisleiman
Sebastian Abisleiman
VSVansh Sharma
Vansh Sharma
RBRal Bielawski
Ral Bielawski
VRVenkat Raman
Venkat Raman

18 April 2024 in Energy and AI
Verified
Journal Article
Open access
VSVansh Sharma
Vansh Sharma
VRVenkat Raman
Venkat Raman

11 February 2025 in Combustion and Flame
Verified
Journal Article
Closed access
VSVansh Sharma
Vansh Sharma
MUMichael Ullman
Michael Ullman
VRVenkat Raman
Venkat Raman

6 August 2025 in Proceedings of the Combustion Institute
Verified
Journal Article
Closed access
SZShuzhi Zhang
Shuzhi Zhang
VSVansh Sharma
Vansh Sharma
VRVenkat Raman
Venkat Raman
TSTristan T. Shahin
Tristan T. Shahin
AHAlexander J. Hodge
Alexander J. Hodge
CSCarson D. Slabaugh
Carson D. Slabaugh

23 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
VSVansh Sharma
Vansh Sharma
VRVenkat Raman
Venkat Raman
This work examines whether activating latent subspaces in language models (LLMs) can steer scientific code generation toward a specific programming language. Five causal LLMs were first evaluated on scientific coding prompts to quantify their baseline bias among four programming languages. A static neuron-attribution method, perturbing the highest activated MLP weight for a C++ or CPP token, proved brittle and exhibited limited generalization across prompt styles and model scales. To address these limitations, a gradient-refined adaptive activation steering framework (G-ACT) was developed: per-prompt activation differences are clustered into a small set of steering directions, and lightweight per-layer probes are trained and refined online to select the appropriate steering vector. In LLaMA-3.2 3B, this approach reliably biases generation towards the CPP language by increasing the average probe classification accuracy by 15% and the early layers (0-6) improving the probe classification accuracy by 61.5% compared to the standard ACT framework. For LLaMA-3.3 70B, where attention-head signals become more diffuse, targeted injections at key layers still improve language selection. Although per-layer probing introduces a modest inference overhead, it remains practical by steering only a subset of layers and enables reproducible model behavior. These results demonstrate a scalable, interpretable and efficient mechanism for concept-level control for practical agentic systems.

11 September 2024 in arXiv
Verified
Preprint
Open access
PDF file
VSVansh Sharma
Vansh Sharma
MUMichael Ullman
Michael Ullman
VRVenkat Raman
Venkat Raman
This study presents a novel algorithm based on machine learning (ML) for the precise segmentation and measurement of detonation cells from soot foil images, addressing the limitations of manual and primitive edge detection methods prevalent in the field. Using advances in cellular biology segmentation models, the proposed algorithm is designed to accurately extract cellular patterns without a training procedure or dataset, which is a significant challenge in detonation research. The algorithm's performance was validated using a series of test cases that mimic experimental and numerical detonation studies. The results demonstrated consistent accuracy, with errors remaining within 10%, even in complex cases. The algorithm effectively captured key cell metrics such as cell area and span, revealing trends across different soot foil samples with uniform to highly irregular cellular structures. Although the model proved robust, challenges remain in segmenting and analyzing highly complex or irregular cellular patterns. This work highlights the broad applicability and potential of the algorithm to advance the understanding of detonation wave dynamics.