arXiv subjects

Shikhar Gupta

Publications and source records attributed to Shikhar Gupta.

4 recordsLinked to original sources

arXiv2026

Execution-Grounded Credit Assignment for GRPO in Code Generation

Critic-free reinforcement learning with verifiable rewards (RLVR) improves code generation by optimizing unit-test pass rates, but GRPO-style updates suffer from coarse credit assignment: a single outcome signal is spread uniformly across long programs even when failure stems from a localized semantic error. We propose Execution-Grounded Credit Assignment (EGCA), which localizes GRPO updates using execution traces. For programs that satisfy algorithmic constraints but fail tests, EGCA executes the candidate and a canonical reference solution (curated once offline; used for analysis, not supervision) under identical instrumentation, identifies the earliest semantic divergence, and assigns advantage only to the corresponding token span while masking downstream tokens. EGCA is a drop-in modification requiring no critic, auxiliary loss, or learned verifier, yielding 82.1% pass@1 on HumanEval (+3.1 over GRPO) and 68.9% on MBPP (+1.5) with 18% wall-clock overhead.

cs.LG↗

arXiv2024

Imprinting electrically switchable scalar spin chirality by anisotropic strain in a Kagome antiferromagnet

Topological chiral antiferromagnets, such as Mn$_{3}$Sn, are emerging as promising materials for next-generation spintronic devices due to their intrinsic transport properties linked to exotic magnetic configurations. Here, we demonstrate that anisotropic strain in Mn$_{3}$Sn thin films offers a novel approach to manipulate the magnetic ground state, unlocking new functionalities in this material. Anisotropic strain reduces the point group symmetry of the manganese (Mn) Kagome triangles from $C_{3v}$ to $C_{1}$, significantly altering the energy landscape of the magnetic states in Mn$_{3}$Sn. This symmetry reduction enables even a tiny in-plane Dzyaloshinskii-Moriya (DM) interaction to induce canting of the Mn spins out of the Kagome plane. The modified magnetic ground state introduces a finite scalar spin chirality and results in a significant Berry phase in momentum space. Consequently, a large anomalous Hall effect emerges in the Kagome plane at room temperature - an effect that is absent in the bulk material. Moreover, this two-fold degenerate magnetic state enables the creation of multiple-stable, non-volatile anomalous Hall resistance (AHR) memory states. These states are field-stable and can be controlled by thermal assisted current-induced magnetization switching requiring modest current densities and small bias fields, thereby offering a compelling new functionality in Mn$_{3}$Sn for spintronic applications.

cond-mat.mtrl-sci↗

arXiv2022

Developing a Machine-Learning Algorithm to Diagnose Age-Related Macular Degeneration

Today, more than 12 million people over the age of 40 suffer from ocular diseases. Most commonly, older patients are susceptible to age related macular degeneration, an eye disease that causes blurring of the central vision due to the deterioration of the retina. The former can only be detected through complex and expensive imaging software, markedly a visual field test; this leaves a significant population with untreated eye disease and holds them at risk for complete vision loss. The use of machine learning algorithms has been proposed for treating eye disease. However, the development of these models is limited by a lack of understanding regarding appropriate model and training parameters to maximize model performance. In our study, we address these points by generating 6 models, each with a learning rate of 1 * 10^n where n is 0, -1, -2, ... -6, and calculated a f1 score for each of the models. Our analysis shows that sample imbalance is a key challenge in training of machine learning models and can result in deceptive improvements in training cost which does not translate to true improvements in model predictive performance. Considering the wide ranging impact of the disease and its adverse effects, we developed a machine learning algorithm to treat the same. We trained our model on varying eye disease datasets consisting of over 5000 patients, and the pictures of their infected eyes. In the future, we hope this model is used extensively, especially in areas that are under-resourced, to better diagnose eye disease and improve well being for humanity.

eess.IV↗

arXiv2020

FPGA Implementation of Simplified Spiking Neural Network

Spiking Neural Networks (SNN) are third-generation Artificial Neural Networks (ANN) which are close to the biological neural system. In recent years SNN has become popular in the area of robotics and embedded applications, therefore, it has become imperative to explore its real-time and energy-efficient implementations. SNNs are more powerful than their predecessors because they encode temporal information and use biologically plausible plasticity rules. In this paper, a simpler and computationally efficient SNN model using FPGA architecture is described. The proposed model is validated on a Xilinx Virtex 6 FPGA and analyzes a fully connected network which consists of 800 neurons and 12,544 synapses in real-time.

cs.NE↗