Sandeep Madireddy

Senior Personnel (ANL), Lab 25-3560, (Lead PI: Rick Stevens, Argonne National Laboratory), FY26-FY28

Co-PI (ANL), Foundational Models for Energy Applications, LDRD Prime Focus Area, (Lead-PI: Pinaki Pal, Argonne National Laboratory), FY26-FY28

Co-PI (ANL), LAB 25-3510.000002, (Lead PI: Robert Ross, Argonne National Laboratory), FY26-FY31

Co-PI (ANL), Critical Materials and Supply Chains, LDRD Prime Focus Area, (Lead-PI: Barron YoungSmith, Argonne National Laboratory), FY26-FY28

Microelectronics Science Research Center Projects for Energy Efficiency and Extreme Environments (LAB 24-3320), (Lead PI: Valerie Taylor, Argonne National Laboratory), FY25-FY27 https://www.energy.gov/sites/default/files/2024-12/122324-msrc-awards-list.pdf

KORAL: Knowledge Graph Guided LLM Reasoning for SSD Operational Analysis

Multi-task Modeling for Engineering Applications with Sparse Data

This paper presents a Multi-Task Gaussian Processes (MTGP) framework designed for engineering systems with multi-source, multi-fidelity data, addressing issues of data scarcity and varying task correlations. By leveraging inter-task relationships, the framework improves prediction accuracy and reduces computational costs, as demonstrated through benchmarks including the Forrester function, 3D void modeling, and friction-stir welding scenarios.

Aeris: Argonne earth systems model for reliable and skillful predictions

This research introduces AERIS, a large-scale pixel-level Swin diffusion transformer, and SWiPe, a technique for efficient parallelism in window-based transformers, to improve weather forecasting with diffusion models. AERIS achieves state-of-the-art performance and scalability on the ERA5 dataset, outperforming existing methods and maintaining stability for seasonal-scale predictions up to 90 days.

Ailuminate: Introducing v1. 0 of the ai risk and reliability benchmark from mlcommons

The paper presents AILuminate v1.0, the first comprehensive industry-standard benchmark designed to evaluate AI systems' resistance to prompts eliciting dangerous, illegal, or undesirable behaviors across 12 hazard categories. This benchmark features a novel evaluation framework, extensive prompt datasets, a five-tier grading scale, and an entropy-based response assessment, supported by infrastructure for ongoing development and cross-disciplinary input.

★AstroMLab 1: Who wins astronomy jeopardy!?

AstroMLab 1

AuroraGPT Data Collection Interface

The software package enables efficient data collection to evaluate the performance of large language models (LLMs) on scientific topics. It is designed to support comprehensive assessment, ensuring accurate measurement of LLM capabilities in understanding and processing scientific information.

Automated MCQA Benchmarking at Scale: Evaluating Reasoning Traces as Retrieval Sources for Domain Adaptation of Small Language Models

The authors present a scalable, modular framework that automates the creation of multiple-choice question-answering benchmarks from large scientific corpora, demonstrated by generating over 16,000 questions from 22,000 radiation and cancer biology papers. Evaluating small language models on these questions reveals that retrieval-augmented generation using reasoning traces significantly improves performance, enabling several smaller models to outperform GPT-4 on a specialized 2023 exam.

Can LLMs Model the Environmental Impact on SSD?

Environmental stressors significantly affect SSD performance and reliability, but studying these effects is difficult due to limited data, complex interrelated factors, and the specialized equipment required. Existing storage management techniques neglect environmental impacts, and accurately modeling these effects remains challenging because of varied NAND flash responses and the cascading influence of historical exposure.

Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation

This paper introduces Chance-constrained Flow Matching (CCFM), a training-free method that incorporates stochastic optimization during sampling to enforce hard constraints while preserving high-fidelity generation. CCFM guarantees feasibility comparable to repeated projection but operates on noisy intermediates, reducing distributional distortion and complexity.

Data-Efficient Dimensionality Reduction and Surrogate Modeling of High-Dimensional Stress Fields

This study presents a convolutional autoencoder framework enhanced by an information bottleneck loss to model tensor datatypes in simulations under limited data conditions, improving robustness by filtering nuisance information while retaining relevant features. The approach is combined with hyperparameter optimization and is numerically compared with dimensionality reduction-based surrogate modeling methods to demonstrate improved predictive performance for engineering applications.

Eaira: Establishing a methodology for evaluating ai models as scientific research assistants

This paper presents EAIRA, a comprehensive methodology developed at Argonne National Laboratory for evaluating Large Language Models as scientific research assistants through multiple choice questions, open responses, lab-style experiments, and field-style experiments. These evaluations provide a holistic assessment of LLMs' factual recall, reasoning, problem-solving, and real-world research interactions across diverse scientific domains.

Efficient Flow Matching using Latent Variables

Flow matching models typically overlook the clustering structure in target data, leading to inefficient learning, especially for high-dimensional datasets on low-dimensional manifolds. Latent-CFM addresses this by conditioning on pretrained deep latent features, achieving better generation quality with less training and computation across synthetic, image, and physical spatial field datasets.

Ensembles of Neural Surrogates for Parametric Sensitivity in Ocean Modeling

This research improves ocean simulation accuracy by using deep learning surrogates combined with large-scale hyperparameter search and ensemble learning to enhance forward predictions and sensitivity estimations. The ensemble approach also quantifies epistemic uncertainty, increasing the reliability of neural surrogates for parameter tuning and decision making.

Evaluating the Safety and Skill Reasoning of Large Reasoning Models Under Compute Constraints

This work investigates reducing the computational cost of reasoning language models by using reasoning length constraints and model quantization, focusing on their effect on safety performance. It proposes fine-tuning with length controlled policy optimization and quantization to balance computational efficiency with model safety within user-defined compute limits.

Evaluation of Test-Time Compute Constraints on Safety and Skill Large Reasoning Models

This research examines two compute constraint strategies—reasoning length constraint and model quantization—to manage the trade-off between computational efficiency and safety in reasoning language models. It proposes fine-tuning models with a length-controlled policy optimization method and applying quantization to maximize chain-of-thought generation within user-defined compute limits.

Heimdall: Optimizing storage i/o admission with extensive machine learning pipeline

This paper presents Heimdall, a machine learning-based I/O admission policy for flash storage that achieves 93% decision accuracy through domain-specific innovations and fine-tuning. Heimdall offers sub-microsecond inference latency, minimal memory overhead, and reduces average I/O latency by 15-35% compared to state-of-the-art methods, supporting various deployment scenarios.

Large Language Models Inference Engines based on Spiking Neural Networks

This research addresses the computational challenges of transformer models by exploring spiking neural networks (SNNs) for efficient design. The proposed NeurTransformer methodology combines supervised fine-tuning with existing conversion techniques to optimize transformer-based SNNs for inference, reducing latency caused by high spike time-steps.

LExI: Layer-Adaptive Active Experts for Efficient MoE Model Inference

This work shows that traditional pruning methods for Mixture-of-Experts (MoE) models mainly reduce memory usage without significantly boosting inference speed on GPUs. The authors propose LExI, a data-free technique that adaptively selects the number of active experts per layer based on model weights, leading to improved inference efficiency and performance on language and vision benchmarks.

Multi-diagnostic Time Series Generative model for Prediction of the Edge Localized Modes in Tokamak plasmas

This research addresses edge-localized modes (ELMs), instabilities in high performance tokamak plasmas driven by edge current density and pressure gradients predicted by magnetohydrodynamic peeling-ballooning theory. It introduces a conceptual model for the evolving magnetic separatrix topology in tokamaks with a dominant lower hyperbolic point and discusses the nonlinear dynamics of ELMs governed by this topology.