arXiv subjects

Ganesh Sundaram

Publications and source records attributed to Ganesh Sundaram.

10 recordsLinked to original sources

arXiv2026

Data-Centric Benchmarking of Exploit Generation in LLMs: Understanding the Impact of Fine-Tuning

We study the task of CVE-conditioned exploit generation, where a model drafts proof-of-concept (PoC) exploits given software vulnerability context. We adopt a data-centric approach, constructing a high-quality dataset via multi-stage preprocessing and introducing a scalable evaluation framework with LLM-as-judge and fine-grained rubrics. Under this unified setup, we benchmark 17 large language models across 8 evaluation criteria, providing systematic insights into their zero-shot capabilities. We further show that a compact 8B open-weight model, when fine-tuned on curated data, achieves over 42.5% improvement in exploit quality and rivals some proprietary models when combined with simple test-time rejection strategies. Our results highlight the importance of data quality, structured supervision, and evaluation design for reliable exploit generation, suggesting that these factors can be as critical as model scale in adapting LLMs to cybersecurity tasks.

cs.CR↗

arXiv2026

kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation

Modern machine learning systems rely on complex data engineering workflows to extract, transform, and load (ELT) data into production pipelines. However, constructing these pipelines remains time-consuming and requires substantial expertise in data infrastructure and orchestration frameworks. Recent advances in large language model (LLM) agents offer a potential path toward automating these workflows, but existing approaches struggle with under-specified user intent, unreliable tool generation, and limited guarantees of executable outputs. We introduce kRAIG, an AI agent that translates natural language specifications into production-ready Kubeflow Pipelines (KFP). To resolve ambiguity in user intent, we propose ReQuesAct (Reason, Question, Act), an interaction framework that explicitly clarifies intent prior to pipeline synthesis. The system orchestrates end-to-end data movement from diverse sources and generates task-specific transformation components through a retrieval-augmented tool synthesis process. To ensure data quality and safety, kRAIG incorporates LLM-based validation stages that verify pipeline integrity prior to execution. Our framework achieves a 3x improvement in extraction and loading success and a 25 percent increase in transformation accuracy compared to state-of-the-art agentic baselines. These improvements demonstrate that structured agent workflows with explicit intent clarification and validation significantly enhance the reliability and executability of automated data engineering pipelines.

cs.SE↗

arXiv2026

Component-Aware Pruning Framework for Neural Network Controllers via Gradient-Based Importance Estimation

The transition from monolithic to multi-component neural architectures in advanced neural network controllers poses substantial challenges due to the high computational complexity of the latter. Conventional model compression techniques for complexity reduction, such as structured pruning based on norm-based metrics to estimate the relative importance of distinct parameter groups, often fail to capture functional significance. This paper introduces a component-aware pruning framework that utilizes gradient information to compute three distinct importance metrics during training: Gradient Accumulation, Fisher Information, and Bayesian Uncertainty. Experimental results with an autoencoder and a TD-MPC agent demonstrate that the proposed framework reveals critical structural dependencies and dynamic shifts in importance that static heuristics often miss, supporting more informed compression decisions.

cs.LG↗

arXiv2026

A Latent Space Framework for Modeling Transient Engine Emissions Using Joint Embedding Predictive Architectures

Accurately modeling and controlling vehicle exhaust emissions during transient events, such as rapid acceleration, is critical for meeting environmental regulations and optimizing powertrains. Conventional data-driven methods, such as Multilayer Perceptrons (MLPs) and Long Short-Term Memory (LSTM) networks, improve upon phenomenological models but often struggle with the complex nonlinear dynamics of emission formation. These monolithic architectures are sensitive to dataset variability and typically require deep, computationally expensive structures to perform well, limiting their practical utility. This paper introduces a novel approach that overcomes these limitations by modeling emission dynamics within a structured latent space. Leveraging a Joint Embedding Predictive Architecture (JEPA), the proposed framework learns from a rich dataset that combines real-world Portable Emission Measurement System (PEMS) data with high-frequency hardware-in-the-loop measurements. The model abstracts away irrelevant noise, encoding only the key factors governing emission behavior into a compact, robust representation. This results in superior data efficiency and predictive accuracy across diverse transient regimes, significantly outperforming high-performing LSTM baselines in generalization. To ensure suitability for real-world deployment, the JEPA framework is structured to support pruning and post-training quantization. This strategy drastically reduces the computational footprint, minimizing inference time and memory demand with negligible accuracy loss. The result is a highly efficient model ideal for on-board implementation of advanced strategies, such as model predictive control or model-based reinforcement learning, in conventional and hybrid powertrains. These findings offer a clear pathway toward more robust emission control systems for next-generation vehicles.

eess.SY↗

arXiv2025

Application-Specific Component-Aware Structured Pruning of Deep Neural Networks in Control via Soft Coefficient Optimization

Deep neural networks (DNNs) offer significant flexibility and robust performance. This makes them ideal for building not only system models but also advanced neural network controllers (NNCs). However, their high complexity and computational needs often limit their use. Various model compression strategies have been developed over the past few decades to address these issues. These strategies are effective for general DNNs but do not directly apply to NNCs. NNCs need both size reduction and the retention of key application-specific performance features. In structured pruning, which removes groups of related elements, standard importance metrics often fail to protect these critical characteristics. In this paper, we introduce a novel framework for calculating importance metrics in pruning groups. This framework not only shrinks the model size but also considers various application-specific constraints. To find the best pruning coefficient for each group, we evaluate two approaches. The first approach involves simple exploration through grid search. The second utilizes gradient descent optimization, aiming to balance compression and task performance. We test our method in two use cases: one on an MNIST autoencoder and the other on a Temporal Difference Model Predictive Control (TDMPC) agent. Results show that the method effectively maintains application-relevant performance while achieving a significant reduction in model size.

cs.LG↗

arXiv2025

Learning State-Space Models of Dynamic Systems from Arbitrary Data using Joint Embedding Predictive Architectures

With the advent of Joint Embedding Predictive Architectures (JEPAs), which appear to be more capable than reconstruction-based methods, this paper introduces a novel technique for creating world models using continuous-time dynamic systems from arbitrary observation data. The proposed method integrates sequence embeddings with neural ordinary differential equations (neural ODEs). It employs loss functions that enforce contractive embeddings and Lipschitz constants in state transitions to construct a well-organized latent state space. The approach's effectiveness is demonstrated through the generation of structured latent state-space models for a simple pendulum system using only image data. This opens up a new technique for developing more general control algorithms and estimation techniques with broad applications in robotics.

cs.LG↗

arXiv2025

COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Models

The rapid growth of resource-constrained mobile platforms, including mobile robots, wearable systems, and Internet-of-Things devices, has increased the demand for computationally efficient neural network controllers (NNCs) that can operate within strict hardware limitations. While deep neural networks (DNNs) demonstrate superior performance in control applications, their substantial computational complexity and memory requirements present significant barriers to practical deployment on edge devices. This paper introduces a comprehensive model compression methodology that leverages component-aware structured pruning to determine the optimal pruning magnitude for each pruning group, ensuring a balance between compression and stability for NNC deployment. Our approach is rigorously evaluated on Temporal Difference Model Predictive Control (TD-MPC), a state-of-the-art model-based reinforcement learning algorithm, with a systematic integration of mathematical stability guarantee properties, specifically Lyapunov criteria. The key contribution of this work lies in providing a principled framework for determining the theoretical limits of model compression while preserving controller stability. Experimental validation demonstrates that our methodology successfully reduces model complexity while maintaining requisite control performance and stability characteristics. Furthermore, our approach establishes a quantitative boundary for safe compression ratios, enabling practitioners to systematically determine the maximum permissible model reduction before violating critical stability properties, thereby facilitating the confident deployment of compressed NNCs in resource-limited environments.

cs.RO↗

arXiv2025

Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis

Deep neural networks (DNNs) deliver outstanding performance, but their complexity often prohibits deployment in resource-constrained settings. Comprehensive structured pruning frameworks based on parameter dependency analysis reduce model size with specific regard to computational performance. When applying them to Multi-Component Neural Architectures (MCNAs), they risk network integrity by removing large parameter groups. We introduce a component-aware pruning strategy, extending dependency graphs to isolate individual components and inter-component flows. This creates smaller, targeted pruning groups that conserve functional integrity. Demonstrated effectively on a control task, our approach achieves greater sparsity and reduced performance degradation, opening a path for optimizing complex, multi-component DNNs efficiently.

cs.LG↗

arXiv2003

Intrinsic self-rotation of BEC Bloch wave packets

The semiclassical theory of Bloch wave packet dynamics predicts a self-rotation angular momentum in asymmetric periodic potentials, which has never been observed. We show how this is manifested in Bose-Einstein condensed atoms in optical lattices. Displacing the wave packet to a corner of the Brillouin zone we obtain a current distribution with a non-quantized angular momentum, independent of the size of the distribution. A weak interatomic interaction does not modify the results, affecting only the rate of spreading in the lattice. A strong repulsive interaction results in a collapse of the wavefunction into matter-wave lattice solitons.

cond-mat↗

arXiv1999

Wave-packet dynamics in slowly perturbed crystals: Gradient corrections and Berry-phase effects

We present a unified theory for wave-packet dynamics of electrons in crystals subject to perturbations varying slowly in space and time. We derive the wave-packet energy up to the first order gradient correction and obtain all kinds of Berry-phase terms for the semiclassical dynamics and the quantization rule. For electromagnetic perturbations, we recover the orbital magnetization energy and the anomalous velocity purely within a single-band picture without invoking inter-band couplings. For deformations in crystals, besides a deformation potential, we obtain a Berry-phase term in the Lagrangian due to lattice tracking, which gives rise to new terms in the expressions for the wave-packet velocity and the semiclassical force. For multiple-valued displacement fields surrounding dislocations, this term manifests as a Berry phase, which we show to be proportional to the Burgers vector around each dislocation.

cond-mat↗