arXiv subjects

Shivam Patel

Publications and source records attributed to Shivam Patel.

15 recordsLinked to original sources

arXiv2026

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First, Persona 8B contains 8.3 billion persona records represented by 1,290 categorical dimensions. Records are either sampled from a dependency graph that preserves correlated attributes or derived from human-authored profiles. We release a quality-filtered coreset of approximately 1 million personas, comprising 599,847 human-grounded and 400,000 synthetic records. Second, the MatrAIx Playground provides four environments in which diverse users evaluate and interact with digital products: Survey, AI Chatbot, Web, and App. Third, MatrAIx provides 1,010 application tasks spanning more than 25 domains, including Commerce, Software, Finance, and Healthcare. We conducted 18,189 evaluation trials across eight representative tasks. Persona agents were powered by three LLMs: Claude Opus 4.8, GPT 5.5, and Claude Haiku 4.5. The resulting feedback captures how decisions and preferences vary across persona backgrounds, including hesitation after a price increase, willingness to continue after an AI assistant fails, and latency tolerance. We conducted two main validation studies: First, a 400-trial controlled study evaluated persona adherence across ten behavioral attributes and all four environments. The declared behavior was expressed or correctly suppressed in 366 trials (91.5%). Second, human and LLM judges evaluated the extraction quality of human-grounded personas. Overall, MatrAIx provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users.

cs.AI↗

arXiv2026

Beyond Accuracy and Cost: Latency-Aware LLM Query Routing for Dynamic Workloads

Modern language query routers improve inference efficiency by assigning each query to a model that balances response quality and monetary cost. However, current query routers are largely latency-agnostic and do not consider the generation latency experienced by queries at model instances. In practice, latency is often controlled by load-balancing policies such as round-robin or join-the-shortest-queue, which do not account for model accuracy or inference cost. Incorporating query latency into routing is challenging as it depends not only on the query's prompt length, but also on the current prefill and decode workload at the model instance and the scheduling and batching policy of the serving framework. We design a lightweight latency estimator that simulates autoregressive token batch processing in the serving framework and estimates the time-to-first-token (TTFT) of queries. We incorporate this latency estimator into a latency-aware router that jointly optimizes latency, accuracy, and cost when assigning queries to model instances. Our experimental results indicate that this joint optimization yields up to 40% improvement in accuracy--cost utility while maintaining the same latencies as standard load-balancing approaches.

cs.AI↗

arXiv2026

Universal monitored dynamics in multimode bosonic systems

We propose a route to study monitored many-body dynamics in multimode bosonic systems using circuit quantum electrodynamics. In this experimental setting, we construct several bosonic models comprising brickwork circuits built from beam-splitter gates, local parity measurements, and optional on-site Hubbard interactions, and diagnose their monitored dynamics via ancilla purification and a learnability-based probe. Under parity measurements, generic gate sets exhibit behavior that is largely consistent with a conventional measurement-induced phase transition, while a special class of beam-splitter circuits shows an apparent critical-like high-measurement regime in which purification times scale linearly with system size. We show that for realistic noise, gate, and measurement rates, these signatures are observable with near-term circuit QED hardware.

quant-ph↗

arXiv2026

Federate the Router: Learning Language Model Routers with Sparse and Decentralized Evaluations

Large language models (LLMs) are increasingly accessed as remotely hosted services by edge and enterprise clients that cannot run frontier models locally. Since models vary widely in capability and price, routing queries to models that balance quality and inference cost is essential. Existing router approaches assume access to centralized query-model evaluation data. However, these data are often fragmented across clients, such as end users and organizations, and are privacy-sensitive, which makes centralizing data infeasible. Additionally, per-client router training is ineffective since local evaluation data is limited and covers only a restricted query distribution and a biased subset of model evaluations. We introduce the first federated framework for LLM routing, enabling clients to learn a shared routing policy from local offline query-model evaluation data. Our framework supports both parametric multilayer perceptron router and nonparametric K-means router under heterogeneous client query distributions and non-uniform model coverage. Across two benchmarks, federated collaboration improves the accuracy-cost frontier over client-local routers, both via increased effective model coverage and better query generalization. Our theoretical results also validate that federated training reduces routing suboptimality.

cs.LG↗

arXiv2026

LOCUS: Low-Dimensional Model Embeddings for Efficient Model Exploration, Comparison, and Selection

The rapidly growing ecosystem of Large Language Models (LLMs) makes it increasingly challenging to manage and utilize the vast and dynamic pool of models effectively. We propose LOCUS, a method that produces low-dimensional vector embeddings that compactly represent a language model's capabilities across queries. LOCUS is an attention-based approach that generates embeddings by a deterministic forward pass over query encodings and evaluation scores via an encoder model, enabling seamless incorporation of new models to the pool and refinement of existing model embeddings without having to perform any retraining. We additionally train a correctness predictor that uses model embeddings and query encodings to achieve state-of-the-art routing accuracy on unseen queries. Experiments show that LOCUS needs up to 4.8x fewer query evaluation samples than baselines to produce informative and robust embeddings. Moreover, the learned embedding space is geometrically meaningful: proximity reflects model similarity, enabling a range of downstream applications including model comparison and clustering, model portfolio selection, and resilient proxies of unavailable models.

cs.LG↗

arXiv2025

ProxRouter: Proximity-Weighted LLM Query Routing for Improved Robustness to Outliers

Large language model (LLM) query routers are critical to modern AI platforms as they seek to improve efficiency by assigning inference queries to accurate, yet low-cost models. Parametric routers typically use trained neural networks for LLM selection but suffer from retraining and maintenance overheads. Nonparametric routers are training-free, instead estimating LLM accuracy and cost via similarity between encodings of the input query and training set queries. However, like their parametric counterparts, nonparametric routers struggle to generalize to outlier queries, an issue exacerbated by limited diversity in training sets which are costly to expand and difficult to keep current with ever-evolving use cases. We propose ProxRouter, which applies an exponentially tilted aggregation mechanism to balance bias and variance in nonparametric routers, improving their robustness to outliers. Experiments show ProxRouter enhances outlier routing while preserving inlier performance with minimal overhead.

cs.LG↗

arXiv2024

An Asymptotic CVaR Measure of Risk for Markov Chains

Risk sensitive decision making finds important applications in current day use cases. Existing risk measures consider a single or finite collection of random variables, which do not account for the asymptotic behaviour of underlying systems. Conditional Value at Risk (CVaR) is the most commonly used risk measure, and has been extensively utilized for modelling rare events in finite horizon scenarios. Naive extension of existing risk criteria to asymptotic regimes faces fundamental challenges, where basic assumptions of existing risk measures fail. We present a complete simulation based approach for sequentially computing Asymptotic CVaR (ACVaR), a risk measure we define on limiting empirical averages of markovian rewards. Large deviations theory, density estimation, and two-time scale stochastic approximation are utilized to define a 'tilted' probability kernel on the underlying state space to facilitate ACVaR simulation. Our algorithm enjoys theoretical guarantees, and we numerically evaluate its performance over a variety of test cases.

q-fin.RM↗

arXiv2024

ACEGEN: Reinforcement learning of generative chemical agents for drug discovery

In recent years, reinforcement learning (RL) has emerged as a valuable tool in drug design, offering the potential to propose and optimize molecules with desired properties. However, striking a balance between capabilities, flexibility, reliability, and efficiency remains challenging due to the complexity of advanced RL algorithms and the significant reliance on specialized code. In this work, we introduce ACEGEN, a comprehensive and streamlined toolkit tailored for generative drug design, built using TorchRL, a modern RL library that offers thoroughly tested reusable components. We validate ACEGEN by benchmarking against other published generative modeling algorithms and show comparable or improved performance. We also show examples of ACEGEN applied in multiple drug discovery case studies. ACEGEN is accessible at \url{https://github.com/acellera/acegen-open} and available for use under the MIT license.

cs.LG↗

arXiv2024

f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization

Training and deploying machine learning models that meet fairness criteria for protected groups are fundamental in modern artificial intelligence. While numerous constraints and regularization terms have been proposed in the literature to promote fairness in machine learning tasks, most of these methods are not amenable to stochastic optimization due to the complex and nonlinear structure of constraints and regularizers. Here, the term "stochastic" refers to the ability of the algorithm to work with small mini-batches of data. Motivated by the limitation of existing literature, this paper presents a unified stochastic optimization framework for fair empirical risk minimization based on f-divergence measures (f-FERM). The proposed stochastic algorithm enjoys theoretical convergence guarantees. In addition, our experiments demonstrate the superiority of fairness-accuracy tradeoffs offered by f-FERM for almost all batch sizes (ranging from full-batch to batch size of one). Moreover, we show that our framework can be extended to the case where there is a distribution shift from training to the test data. Our extension is based on a distributionally robust optimization reformulation of f-FERM objective under $L_p$ norms as uncertainty sets. Again, in this distributionally robust setting, f-FERM not only enjoys theoretical convergence guarantees but also outperforms other baselines in the literature in the tasks involving distribution shifts. An efficient stochastic implementation of $f$-FERM is publicly available.

cs.LG↗

arXiv2024

Towards a low carbon proof-of-work blockchain

Proof of Work (PoW) blockchains burn a lot of energy. Proof-of-work algorithms are expensive by design and often only serve to compute blockchains. In some sense, carbon-based and non-carbon based regional electric power is fungible. So the total carbon and non-carbon electric power mix plays a role. Thus, generally PoW algorithms have large CO$_2$ footprints solely for computing blockchains. A proof of technology is described towards replacing hashcash or other PoW methods with a lottery and proof-of-VM (PoVM) emulation. PoVM emulation is a form of PoW where an autonomous blockchain miner gets a lottery ticket in exchange for providing a VM (virtual Machine) for a specified period. These VMs get their jobs from a job queue. Managing and ensuring, by concensus, that autonomous PoVMs are properly configured and running as expected gives several gaps for a complete practical system. These gaps are discussed. Our system is similar to a number of other blockchain systems. We briefly survey these systems. This paper along with our proof of technology was done as a senior design project.

cs.CR↗

arXiv2024

Intelligent Agricultural Management Considering N$_2$O Emission and Climate Variability with Uncertainties

This study examines how artificial intelligence (AI), especially Reinforcement Learning (RL), can be used in farming to boost crop yields, fine-tune nitrogen use and watering, and reduce nitrate runoff and greenhouse gases, focusing on Nitrous Oxide (N$_2$O) emissions from soil. Facing climate change and limited agricultural knowledge, we use Partially Observable Markov Decision Processes (POMDPs) with a crop simulator to model AI agents' interactions with farming environments. We apply deep Q-learning with Recurrent Neural Network (RNN)-based Q networks for training agents on optimal actions. Also, we develop Machine Learning (ML) models to predict N$_2$O emissions, integrating these predictions into the simulator. Our research tackles uncertainties in N$_2$O emission estimates with a probabilistic ML approach and climate variability through a stochastic weather model, offering a range of emission outcomes to improve forecast reliability and decision-making. By incorporating climate change effects, we enhance agents' climate adaptability, aiming for resilient agricultural practices. Results show these agents can align crop productivity with environmental concerns by penalizing N$_2$O emissions, adapting effectively to climate shifts like warmer temperatures and less rain. This strategy improves farm management under climate change, highlighting AI's role in sustainable agriculture.

cs.LG↗

arXiv2021

Smart Band: An Integrated Device for Emergency Management

In the event of a kidnapping or a medical emergency, a person is often incapacitated to be able to call for help. And it's usually too late before the first responders arrive on-scene. Currently, a vast array of 'safety' devices available in the market are often far too rudimentary such as double tapping the power button that isn't very practical, or an app on a smart watch that is a huge investment in the first place. The Smart Band aims to eliminate the need for a physical trigger by the person who finds himself in dangerous situations like kidnapping, front-facing some wild animal, heart attack, etc., and rather senses the heartbeat. The Smart Band is designed as a personalized wearable device, wherein the user heart beat rate is collected and trained using machine learning algorithm, which triggers the alert system automatically when the event is identified. Hence the accuracy of assessing emergency situation will be high and false rate will be reduced. As soon as the event is detected, the band relays GPS coordinates to first responders and emergency contacts, which will be sent via the Network Carrier (SIM card module) directly from the band, not relying on a mobile phone, which is usually out of reach during such emergency situations. In essence, the Smart Band consists of a GPS tracker, a heartbeat sensor, a Network module, and a Bluetooth module, all existing technologies which have been mass produced to an extent that the end product can be made affordable, and in huge quantities as well. On further development the smart band can be customized to a finely wearable jewel which can serve the purpose autonomously.

cs.CY↗

arXiv2021

Topic Modeling Based Extractive Text Summarization

Text summarization is an approach for identifying important information present within text documents. This computational technique aims to generate shorter versions of the source text, by including only the relevant and salient information present within the source text. In this paper, we propose a novel method to summarize a text document by clustering its contents based on latent topics produced using topic modeling techniques and by generating extractive summaries for each of the identified text clusters. All extractive sub-summaries are later combined to generate a summary for any given source document. We utilize the lesser used and challenging WikiHow dataset in our approach to text summarization. This dataset is unlike the commonly used news datasets which are available for text summarization. The well-known news datasets present their most important information in the first few lines of their source texts, which make their summarization a lesser challenging task when compared to summarizing the WikiHow dataset. Contrary to these news datasets, the documents in the WikiHow dataset are written using a generalized approach and have lesser abstractedness and higher compression ratio, thus proposing a greater challenge to generate summaries. A lot of the current state-of-the-art text summarization techniques tend to eliminate important information present in source documents in the favor of brevity. Our proposed technique aims to capture all the varied information present in source documents. Although the dataset proved challenging, after performing extensive tests within our experimental setup, we have discovered that our model produces encouraging ROUGE results and summaries when compared to the other published extractive and abstractive text summarization models.

cs.CL↗

arXiv2020

Gandhipedia: A one-stop AI-enabled portal for browsing Gandhian literature, life-events and his social network

We introduce an AI-enabled portal that presents an excellent visualization of Mahatma Gandhi's life events by constructing temporal and spatial social networks from the Gandhian literature. Applying an ensemble of methods drawn from NLTK, Polyglot and Spacy we extract the key persons and places that find mentions in Gandhi's written works. We visualize these entities and connections between them based on co-mentions within the same time frame as networks in an interactive web portal. The nodes in the network, when clicked, fire search queries about the entity and all the information about the entity presented in the corresponding book from which the network is constructed, are retrieved and presented back on the portal. Overall, this system can be used as a digital and user-friendly resource to study Gandhian literature.

cs.IR↗

arXiv2014

Toward Software Measurement and Quality Analysis of MARF and GIPSY Case Studies, a Team 8 SOEN6611-S14 Project Report

Measurement is an important criterion to improve the performance of a product. This paper presents a comparative study involving measurements between two frameworks MARF and GIPSY. Initially it establishes a thorough understanding of these frameworks and their applications. MARF comprises of a number of algorithms for voice and speech processing etc. GIPSY on the contrary provides a multi lingual platform for developing compiler components. These frameworks are meant to provide an open source environment for the programmers or users and implement them in applications. Several metrics are used for object-oriented design quality assessment. We use these metrics to evaluate the code quality of both MARF and GIPSY. We describe how tools can be used to analyze these metric values and categorize the quality of the code as excellent or worse. Based on these values we interpret the results in terms of quality attributes achieved. Quantitative and qualitative analysis of metric values is made in this regard to elaborate the impact of design parameters on the quality of the code.

cs.SE↗