arXiv subjects

Srinivasan Iyengar

Publications and source records attributed to Srinivasan Iyengar.

15 recordsLinked to original sources

arXiv2026

CWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms

AI power demand is growing at an unprecedented rate while power grids are often ailing and struggle to keep up. Grid expansion comes with high capital expenditure and long-distance transmission losses, yet there is abundant renewable energy at the source, just not matched to demand. This paper proposes a complementary AI infrastructure deployment model, AI Greeninferencing, that brings modular AI compute to renewable energy sources, focusing on wind, allowing AI footprint expansion, generating local behind-the-meter demand for renewable sites, and helping ease the growing strain on power utilities. Our feasibility analysis shows that 890+ GW of wind capacity lies within 50 ms network round trip time of Azure data centers, and that site-wise right-sizing combined with spatial complementarity of wind energy keeps aggregate fleet utilization on par with traditional deployments. To serve inference requests under variable wind power, we build CWind, a lightweight, reactive, and workload-agnostic AI inference router that uses only real-time signals: inference latency, KV-cache utilization, and queue depth, to dynamically configure sites and distribute requests. Evaluated on a real 64-GPU A100 testbed emulating three wind-powered sites with Azure production traces, CWind reduces P99 end-to-end latency by up to 52% over the strongest contender (also our idea) and by up to 98% over baselines such as power-capping and GPU idling, with consistent gains across workload types, load levels, and GPU generations.

cs.DC↗

arXiv2026

Half the Interference, Most of the Answer: Approximate Quantum Simulation via Path-Sum Pruning

Classical simulation of quantum circuits is expensive for two distinct reasons. The obvious one is state-space size: an n-qubit system requires exponentially many amplitudes. The less obvious one is interference: useful output distributions emerge only after many computational histories have been coherently combined at common endpoints, and this aggregation step is itself a substantial source of cost. We introduce statistical interference sampling, a framework that makes this second bottleneck explicit by treating endpoint interference as a separately schedulable computation. Using the Chemical Abstract Machine (ChAM) as our model, weighted path contributions evolve as concurrent molecular species, and interference reactions combine contributions that share a common output state. A threshold rule terminates the process once an endpoint accumulates sufficient amplitude, discarding the remaining reactions. The method does not improve worst-case complexity and is not intended as a general-purpose simulator. Its purpose is to ask a more targeted question: how much of the interference calculation can be skipped while still recovering a useful output distribution? On benchmark circuits for Deutsch-Jozsa, Grover search, Simon's problem, and small Shor period-finding instances, we find that nearly 50% of endpoint interference reactions can be omitted while maintaining over 90% output accuracy for most algorithms tested. These results suggest that interference arithmetic is a structured resource that admits meaningful approximation, and that exposing it explicitly opens new opportunities for pruning strategies across path-sum, Pauli-path, and tensor-network simulation methods.

quant-ph↗

arXiv2025

SPIRIT: Short-term Prediction of solar IRradIance for zero-shot Transfer learning using Foundation Models

Traditional solar forecasting models are based on several years of site-specific historical irradiance data, often spanning five or more years, which are unavailable for newer photovoltaic farms. As renewable energy is highly intermittent, building accurate solar irradiance forecasting systems is essential for efficient grid management and enabling the ongoing proliferation of solar energy, which is crucial to achieve the United Nations' net zero goals. In this work, we propose SPIRIT, a novel approach leveraging foundation models for solar irradiance forecasting, making it applicable to newer solar installations. Our approach outperforms state-of-the-art models in zero-shot transfer learning by about 70%, enabling effective performance at new locations without relying on any historical data. Further improvements in performance are achieved through fine-tuning, as more location-specific data becomes available. These findings are supported by statistical significance, further validating our approach. SPIRIT represents a pivotal step towards rapid, scalable, and adaptable solar forecasting solutions, advancing the integration of renewable energy into global power systems.

cs.LG↗

arXiv2025

LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision

Curating high-quality, domain-specific datasets is a major bottleneck for deploying robust vision systems, requiring complex trade-offs between data quality, diversity, and cost when researching vast, unlabeled data lakes. We introduce Labeling Copilot, the first data curation deep research agent for computer vision. A central orchestrator agent, powered by a large multimodal language model, uses multi-step reasoning to execute specialized tools across three core capabilities: (1) Calibrated Discovery sources relevant, in-distribution data from large repositories; (2) Controllable Synthesis generates novel data for rare scenarios with robust filtering; and (3) Consensus Annotation produces accurate labels by orchestrating multiple foundation models via a novel consensus mechanism incorporating non-maximum suppression and voting. Our large-scale validation proves the effectiveness of Labeling Copilot's components. The Consensus Annotation module excels at object discovery: on the dense COCO dataset, it averages 14.2 candidate proposals per image-nearly double the 7.4 ground-truth objects-achieving a final annotation mAP of 37.1%. On the web-scale Open Images dataset, it navigated extreme class imbalance to discover 903 new bounding box categories, expanding its capability to over 1500 total. Concurrently, our Calibrated Discovery tool, tested at a 10-million sample scale, features an active learning strategy that is up to 40x more computationally efficient than alternatives with equivalent sample efficiency. These experiments validate that an agentic workflow with optimized, scalable tools provides a robust foundation for curating industrial-scale datasets.

cs.CV↗

arXiv2025

Grammars of Formal Uncertainty: When to Trust LLMs in Automated Reasoning Tasks

Large language models (LLMs) show remarkable promise for democratizing automated reasoning by generating formal specifications. However, a fundamental tension exists: LLMs are probabilistic, while formal verification demands deterministic guarantees. This paper addresses this epistemological gap by comprehensively investigating failure modes and uncertainty quantification (UQ) in LLM-generated formal artifacts. Our systematic evaluation of five frontier LLMs reveals Satisfiability Modulo Theories (SMT) based autoformalization's domain-specific impact on accuracy (from +34.8% on logical tasks to -44.5% on factual ones), with known UQ techniques like the entropy of token probabilities failing to identify these errors. We introduce a probabilistic context-free grammar (PCFG) framework to model LLM outputs, yielding a refined uncertainty taxonomy. We find uncertainty signals are task-dependent (e.g., grammar entropy for logic, AUROC>0.93). Finally, a lightweight fusion of these signals enables selective verification, drastically reducing errors (14-100%) with minimal abstention, transforming LLM-driven formalization into a reliable engineering discipline.

cs.CL↗

arXiv2025

AI Greenferencing: Routing AI Inferencing to Green Modular Data Centers with Heron

AI power demand is growing unprecedentedly thanks to the high power density of AI compute and the emerging inferencing workload. On the supply side, abundant wind power is waiting for grid access in interconnection queues. In this light, this paper argues bringing AI workload to modular compute clusters co-located in wind farms. Our deployment right-sizing strategy makes it economically viable to deploy more than 6 million high-end GPUs today that could consume cheap, green power at its source. We built Heron, a cross-site software router, that could efficiently leverage the complementarity of power generation across wind farms by routing AI inferencing workload around power drops. Using 1-week ofcoding and conversation production traces from Azure and (real) variable wind power traces, we show how Heron improves aggregate goodput of AI compute by up to 80% compared to the state-of-the-art.

cs.DC↗

arXiv2025

EnCortex: A General, Extensible and Scalable Framework for Decision Management in New-age Energy Systems

With increased global warming, there has been a significant emphasis to replace fossil fuel-dependent energy sources with clean, renewable sources. These new-age energy systems are becoming more complex with an increasing proportion of renewable energy sources (like solar and wind), energy storage systems (like batteries), and demand side control in the mix. Most new-age sources being highly dependent on weather and climate conditions bring about high variability and uncertainty. Energy operators rely on such uncertain data to make different planning and operations decisions periodically, and sometimes in real-time, to maintain the grid stability and optimize their objectives (cost savings, carbon footprint, etc.). Hitherto, operators mostly rely on domain knowledge, heuristics, or solve point problems to take decisions. These approaches fall short because of their specific assumptions and limitations. Further, there is a lack of a unified framework for both research and production environments at scale. In this paper, we propose EnCortex to address these challenges. EnCortex provides a general, easy-to-use, extensible, and scalable energy decision framework that enables operators to plan, build and execute their real-world scenarios efficiently. We show that using EnCortex, we can define and compose complex new-age scenarios, owing to industry-standard abstractions of energy entities and the modularity of the framework. EnCortex provides a foundational structure to support several state-of-the-art optimizers with minimal effort. EnCortex supports both quick developments for research prototypes and scaling the solutions to production environments. We demonstrate the utility of EnCortex with three complex new-age real-world scenarios and show that significant cost and carbon footprint savings can be achieved.

eess.SY↗

arXiv2024

An Agentic Approach to Automatic Creation of P&ID Diagrams from Natural Language Descriptions

The Piping and Instrumentation Diagrams (P&IDs) are foundational to the design, construction, and operation of workflows in the engineering and process industries. However, their manual creation is often labor-intensive, error-prone, and lacks robust mechanisms for error detection and correction. While recent advancements in Generative AI, particularly Large Language Models (LLMs) and Vision-Language Models (VLMs), have demonstrated significant potential across various domains, their application in automating generation of engineering workflows remains underexplored. In this work, we introduce a novel copilot for automating the generation of P&IDs from natural language descriptions. Leveraging a multi-step agentic workflow, our copilot provides a structured and iterative approach to diagram creation directly from Natural Language prompts. We demonstrate the feasibility of the generation process by evaluating the soundness and completeness of the workflow, and show improved results compared to vanilla zero-shot and few-shot generation approaches.

cs.LG↗

arXiv2024

Proof of Thought : Neurosymbolic Program Synthesis allows Robust and Interpretable Reasoning

Large Language Models (LLMs) have revolutionized natural language processing, yet they struggle with inconsistent reasoning, particularly in novel domains and complex logical sequences. This research introduces Proof of Thought, a framework that enhances the reliability and transparency of LLM outputs. Our approach bridges LLM-generated ideas with formal logic verification, employing a custom interpreter to convert LLM outputs into First Order Logic constructs for theorem prover scrutiny. Central to our method is an intermediary JSON-based Domain-Specific Language, which by design balances precise logical structures with intuitive human concepts. This hybrid representation enables both rigorous validation and accessible human comprehension of LLM reasoning processes. Key contributions include a robust type system with sort management for enhanced logical integrity, explicit representation of rules for clear distinction between factual and inferential knowledge, and a flexible architecture that allows for easy extension to various domain-specific applications. We demonstrate Proof of Thought's effectiveness through benchmarking on StrategyQA and a novel multimodal reasoning task, showing improved performance in open-ended scenarios. By providing verifiable and interpretable results, our technique addresses critical needs for AI system accountability and sets a foundation for human-in-the-loop oversight in high-stakes domains.

cs.AI↗

arXiv2022

Streaming Video Analytics On The Edge With Asynchronous Cloud Support

Emerging Internet of Things (IoT) and mobile computing applications are expected to support latency-sensitive deep neural network (DNN) workloads. To realize this vision, the Internet is evolving towards an edge-computing architecture, where computing infrastructure is located closer to the end device to help achieve low latency. However, edge computing may have limited resources compared to cloud environments and thus, cannot run large DNN models that often have high accuracy. In this work, we develop REACT, a framework that leverages cloud resources to execute large DNN models with higher accuracy to improve the accuracy of models running on edge devices. To do so, we propose a novel edge-cloud fusion algorithm that fuses edge and cloud predictions, achieving low latency and high accuracy. We extensively evaluate our approach and show that our approach can significantly improve the accuracy compared to baseline approaches. We focus specifically on object detection in videos (applicable in many video analytics scenarios) and show that the fused edge-cloud predictions can outperform the accuracy of edge-only and cloud-only scenarios by as much as 50%. We also show that REACT can achieve good performance across tradeoff points by choosing a wide range of system parameters to satisfy use-case specific constraints, such as limited network bandwidth or GPU cycles.

cs.CV↗

arXiv2020

WattScale: A Data-driven Approach for Energy Efficiency Analytics of Buildings at Scale

Buildings consume over 40% of the total energy in modern societies, and improving their energy efficiency can significantly reduce our energy footprint. In this paper, we present \texttt{WattScale}, a data-driven approach to identify the least energy-efficient buildings from a large population of buildings in a city or a region. Unlike previous methods such as least-squares that use point estimates, \texttt{WattScale} uses Bayesian inference to capture the stochasticity in the daily energy usage by estimating the distribution of parameters that affect a building. Further, it compares them with similar homes in a given population. \texttt{WattScale} also incorporates a fault detection algorithm to identify the underlying causes of energy inefficiency. We validate our approach using ground truth data from different geographical locations, which showcases its applicability in various settings. \texttt{WattScale} has two execution modes -- (i) individual, and (ii) region-based, which we highlight using two case studies. For the individual execution mode, we present results from a city containing >10,000 buildings and show that more than half of the buildings are inefficient in one way or another indicating a significant potential from energy improvement measures. Additionally, we provide probable cause of inefficiency and find that 41\%, 23.73\%, and 0.51\% homes have poor building envelope, heating, and cooling system faults, respectively. For the region-based execution mode, we show that \texttt{WattScale} can be extended to millions of homes in the US due to the recent availability of representative energy datasets.

cs.CY↗

arXiv2020

Emission-aware Energy Storage Scheduling for a Greener Grid

Reducing our reliance on carbon-intensive energy sources is vital for reducing the carbon footprint of the electric grid. Although the grid is seeing increasing deployments of clean, renewable sources of energy, a significant portion of the grid demand is still met using traditional carbon-intensive energy sources. In this paper, we study the problem of using energy storage deployed in the grid to reduce the grid's carbon emissions. While energy storage has previously been used for grid optimizations such as peak shaving and smoothing intermittent sources, our insight is to use distributed storage to enable utilities to reduce their reliance on their less efficient and most carbon-intensive power plants and thereby reduce their overall emission footprint. We formulate the problem of emission-aware scheduling of distributed energy storage as an optimization problem, and use a robust optimization approach that is well-suited for handling the uncertainty in load predictions, especially in the presence of intermittent renewables such as solar and wind. We evaluate our approach using a state of the art neural network load forecasting technique and real load traces from a distribution grid with 1,341 homes. Our results show a reduction of >0.5 million kg in annual carbon emissions -- equivalent to a drop of 23.3% in our electric grid emissions.

eess.SY↗

arXiv2019

Modulo: Drive-by Sensing at City-scale on the Cheap

Drive-by sensing is gaining popularity as an inexpensive way to perform fine-grained, city-scale, spatiotemporal monitoring of physical phenomena. Prior work explores several challenges in the design of low-cost sensors, the reliability of these sensors, and their application for specific use-cases like pothole detection and pollution monitoring. However, the process of deployment of a drive-by sensing network at a city-scale is still unexplored. Despite the rise of ride-sharing services, there is still no way to optimally select vehicles from a fleet that can accomplish the sensing task by providing enough coverage of the city. In this paper, we propose Modulo -- a system to bootstrap drive-by sensing deployment by taking into consideration a variety of aspects such as spatiotemporal coverage, budget constraints. Further, Modulo is well-suited to satisfy unique deployment constraints such as colocations with other sensors (needed for gas and PM sensor calibration), etc. We compare Modulo with two baseline algorithms on real-world taxi and bus datasets. We find that Modulo marginally outperforms the two baselines for datasets with just random-routes vehicles such as taxis. However, it significantly outperforms the baselines when a fleet comprises of both taxis and fixed-route vehicles such as public transport buses. Finally, we present a real-deployment that uses Modulo to select vehicles for an air pollution sensing application.

cs.NI↗

arXiv2017

Time-of-Flight Three Dimensional Neutron Diffraction in Transmission Mode for Mapping Crystal Grain Structures

The physical properties of polycrystalline materials depend on their microstructure, which is the nano-to-centimeter-scale arrangement of phases and defects in their interior. Such microstructure depends on the shape, crystallographic phase and orientation, and interfacing of the grains constituting the material. This article presents a new non-destructive 3D technique to study bulk samples with sizes in the cm range with a resolution of hundred micrometers: time-of-flight three-dimensional neutron diffraction (ToF 3DND). Compared to existing analogous X-ray diffraction techniques, ToF 3DND enables studies of samples that can be both larger in size and made of heavier elements. Moreover, ToF 3DND facilitates the use of complicated sample environments. The basic ToF 3DND setup, utilizing an imaging detector with high spatial and temporal resolution, can easily be implemented at a time-of-flight neutron beamline. The technique was developed and tested with data collected at the Materials and Life Science Experimental Facility of the Japan Proton Accelerator Complex (J-PARC) for an iron sample. We successfully reconstructed the shape of 108 grains and developed an indexing procedure. The reconstruction algorithms have been validated by reconstructing two stacked Co-Ni-Ga single crystals and by comparison with a grain map obtained by post-mortem electron backscatter diffraction (EBSD).

physics.ins-det↗

arXiv2009

A Minimum Variance Method for Problems in Radio Antenna Placement

Aperture synthesis radio telescopes generate images of celestial bodies from data obtained from several radio antennas. Placement of these antennas has always been a source of interesting problems. Often, several potentially contradictory objectives like good image quality and low infra-structural cost have to be satisfied simultaneously. In this paper, we propose a general Minimum Variance Method that focuses on obtaining good images in the presence of limiting situations. We show its versatility and goodness in three different situations: (a) Placing the antennas on the ground to get a target Gaussian UV distribution (b) Staggering the construction of a telescope in the event of staggered budgets and (c) Whenever available, using the mobility of antennas to obtain a high degree of fault tolerance.

astro-ph.IM↗