Shriyank Somvanshi

Mr. Shriyank Somvanshi

Ingram School of Engineering, Texas State University, San Marcos, California, USA
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
10 September 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
Shriyank SomvanshiShriyank Somvanshi
Shriyank Somvanshi
SJSyed Aaqib Javed
Syed Aaqib Javed
MIMonzurul Islam
Monzurul Islam
DPDiwas Pandit
Diwas Pandit
SDSubasish Das
Subasish Das
This review study explores the theoretical foundations, evolution, applications, and future potential of Kolmogorov–Arnold Networks (KAN), a neural network model inspired by the Kolmogorov–Arnold representation theorem. KANs set themselves apart from traditional neural networks by employing learnable, spline-parameterized functions rather than fixed activation functions, allowing for flexible and interpretable representations of high-dimensional functions. The review explores Kan’s architectural strengths, including adaptive edge-based activation functions that enhance parameter efficiency and scalability across varied applications such as time series forecasting, computational biomedicine, and graph learning. Key advancements including Temporal-KAN (T-KAN), FastKAN, and Partial Differential Equation (PDE) KAN illustrate KAN’s growing applicability in dynamic environments, significantly improving interpretability, computational efficiency, and adaptability for complex function approximation tasks. Moreover, the article discusses KANs integration with other architectures, such as convolutional, recurrent, and transformer-based models, showcasing its versatility in complementing established neural networks for tasks that require hybrid approaches. Despite its strengths, KAN faces computational challenges in high-dimensional and noisy data settings, sparking continued research into optimization strategies, regularization techniques, and hybrid models. This article highlights KANs expanding role in modern neural architectures and outlines future directions to enhance its computational efficiency, interpretability, and scalability in data-intensive applications.

24 December 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
Shriyank SomvanshiShriyank Somvanshi
Shriyank Somvanshi
MIMonzurul Islam
Monzurul Islam
GCGaurab Chhetri
Gaurab Chhetri
RCRohit Chakraborty
Rohit Chakraborty
MMMahmuda Sultana Mimi
Mahmuda Sultana Mimi
SDSubasish Das
Subasish Das
The rapid growth of edge devices has driven the demand for deploying artificial intelligence (AI) at the edge, giving rise to Tiny Machine Learning (TinyML) and its evolving counterpart, Tiny Deep Learning (TinyDL). While TinyML initially focused on enabling simple inference tasks on microcontrollers, the emergence of TinyDL marks a paradigm shift toward deploying deep learning models on severely resource-constrained hardware. This survey presents a comprehensive overview of the transition from TinyML to TinyDL, encompassing architectural innovations, hardware platforms, model optimization techniques, and software toolchains. We analyze state-of-the-art methods in quantization, pruning, and neural architecture search (NAS), and examine hardware trends from MCUs to dedicated neural accelerators. Furthermore, we categorize software deployment frameworks, compilers, and AutoML tools enabling practical on-device learning. Applications across domains such as computer vision, audio recognition, healthcare, and industrial monitoring are reviewed to illustrate the real-world impact of TinyDL. Finally, we identify emerging directions including neuromorphic computing, federated TinyDL, edge-native foundation models, and domain-specific co-design approaches. This survey aims to serve as a foundational resource for researchers and practitioners, offering a holistic view of the ecosystem and laying the groundwork for future advancements in edge AI.

4 February 2026 in ACM Computing Surveys
Verified
Journal Article
Open access
Shriyank SomvanshiShriyank Somvanshi
Shriyank Somvanshi
MIMonzurul Islam
Monzurul Islam
ARAmir Rafe
Amir Rafe
ATAnannya Ghosh Tusti
Anannya Ghosh Tusti
ACArka Chakraborty
Arka Chakraborty
SDSubasish Das
Subasish Das
Mechanistic interpretability seeks to reverse-engineer the internal logic of neural networks by uncovering human-understandable circuits, algorithms, and causal structures that drive model behavior. Unlike post hoc explanations that describe what models do, this paradigm focuses on why and how they compute, tracing information flow through neurons, attention heads, and activation pathways. This survey provides a high-level synthesis of the field-highlighting its motivation, conceptual foundations, and methodological taxonomy rather than enumerating individual techniques. We organize mechanistic interpretability across three abstraction layers— neurons , circuits , and algorithms —and three evaluation perspectives: behavioral , counterfactual , and causal . We further discuss representative approaches and toolchains that enable structural analysis of modern AI systems, outlining how mechanistic interpretability bridges theoretical insights with practical transparency. Despite rapid progress, challenges persist in scaling these analyses to frontier models, resolving polysemantic representations, and establishing standardized causal benchmarks. By connecting historical evolution, current methodologies, and emerging research directions, this survey aims to provide an integrative framework for understanding how mechanistic interpretability can support transparency, reliability, and governance in large-scale AI.

15 October 2024 in arXiv
Verified
Preprint
Open access
PDF file
Shriyank SomvanshiShriyank Somvanshi
Shriyank Somvanshi
SDSubasish Das
Subasish Das
SJSyed Aaqib Javed
Syed Aaqib Javed
GAGian Antariksa
Gian Antariksa
AHAhmed Hossain
Ahmed Hossain
Tabular data, widely used in industries like healthcare, finance, and transportation, presents unique challenges for deep learning due to its heterogeneous nature and lack of spatial structure. This survey reviews the evolution of deep learning models for tabular data, from early fully connected networks (FCNs) to advanced architectures like TabNet, SAINT, TabTranSELU, and MambaNet. These models incorporate attention mechanisms, feature embeddings, and hybrid architectures to address tabular data complexities. TabNet uses sequential attention for instance-wise feature selection, improving interpretability, while SAINT combines self-attention and intersample attention to capture complex interactions across features and data points, both advancing scalability and reducing computational overhead. Hybrid architectures such as TabTransformer and FT-Transformer integrate attention mechanisms with multi-layer perceptrons (MLPs) to handle categorical and numerical data, with FT-Transformer adapting transformers for tabular datasets. Research continues to balance performance and efficiency for large datasets. Graph-based models like GNN4TDL and GANDALF combine neural networks with decision trees or graph structures, enhancing feature representation and mitigating overfitting in small datasets through advanced regularization techniques. Diffusion-based models like the Tabular Denoising Diffusion Probabilistic Model (TabDDPM) generate synthetic data to address data scarcity, improving model robustness. Similarly, models like TabPFN and Ptab leverage pre-trained language models, incorporating transfer learning and self-supervised techniques into tabular tasks. This survey highlights key advancements and outlines future research directions on scalability, generalization, and interpretability in diverse tabular data applications.

8 April 2026 in ACM Computing Surveys
Verified
Journal Article
Open access
Shriyank SomvanshiShriyank Somvanshi
Shriyank Somvanshi
SDSubasish Das
Subasish Das
SJSyed Javed
Syed Javed
GAGian Antariksa
Gian Antariksa
AHAhmed Hossain
Ahmed Hossain
Tabular data remains one of the most challenging modalities for deep learning due to its heterogeneity, lack of spatial or sequential inductive bias, and small-sample regimes. Key complexities include mixed feature types, high-cardinality categoricals, missing or sparse entries, and weak or irregular feature interactions-conditions that make representation learning and generalization difficult for neural networks. While early neural approaches struggled to match tree-based methods, recent advances demonstrate measurable progress across representation learning, regularization, and architectural design. This survey synthesizes findings from more than a decade of research, highlighting tabular data across two major families of approaches: classical models centered on decision trees and ensembles, and deep learning architectures. We identify three major trends: (1) the shift toward attention-based and hybrid architectures capable of modeling non-local interactions; (2) growing use of pretraining, self-supervision, and foundation-model-style priors to mitigate overfitting; and (3) emerging diffusion, graph-based, and multimodal frameworks that improve robustness and generalization. Despite these advances, tree-based methods remain strong baselines in low-dimensional and small-data contexts. By distilling empirical patterns across benchmarks and applications, this survey clarifies when deep learning delivers real gains for tabular data. We close with a prioritized research agenda on scalability, interpretability, and unified modeling.

3 December 2024 in Transportation Research Part D: Transport and Environment
Verified
Journal Article
Closed access
JLJinli Liu
Jinli Liu
GAGian Antariksa
Gian Antariksa
Shriyank SomvanshiShriyank Somvanshi
Shriyank Somvanshi
SDSubasish Das
Subasish Das