arXiv subjects

Shivam Gupta

Publications and source records attributed to Shivam Gupta.

At least 19 recordsLinked to original sources

arXiv2026

Exploring the relationship between human-centric AI and firm idiosyncratic risks

Despite the extensive discussions of human-centric AI (HCAI) in Industry 5.0, its effects on firms' idiosyncratic risks (IR) remains underexplored. This is an imperative issue for firms navigate financial risks during the current technological revolution, as IR reflects investor reactions to corporate heterogeneous AI strategies and implementations by isolating firm-level stock volatility from systematic factors. Integrating situated AI theory with social-technical systems theory, we conceptualise HCAI as a situated AI strategy that reduces AI-related ethical risks and fosters AI-Human synergies in firms' business operations, ultimately reducing IR by aligning with stakeholders' diverse expectations. Moreover, socio-technical factors, namely digitalisation, operational efficiency, executive shareholding, and CEOs with IT background, may moderate the HCAI-IR relationship. Using a multi-source panel dataset of Chinese listed firms from 2015 to 2023, we find that HCAI is associated with lower firm IR. Furthermore, digitalisation and executive shareholding strengthen this risk-reducing effect, whereas operational efficiency and CEOs with IT background surprisingly attenuate it. Our findings offer theoretical contributions and practical insights for both ethical AI governance and firm financial risk management in the AI era.

cs.AI↗

arXiv2026

Entropic signatures of market response under concentrated policy communication

The first 100 days of Donald Trump second presidential term (January 20th - April 30th, 2025) featured policy actions with potential market repercussions, constituting a well-suited case study of a concentrated policy scenario. Here, we provide a first look at this period, rooted in the information theory, by analyzing major stock indices across the Americas, Europe as well as Asia and Oceania. Our approach jointly examines dispersion (standard deviation) and information complexity (entropy), but also employs a sliding window cumulative entropy to localize extreme events. We find a notable decoupling between the first two measures, indicating that entropy is not merely a proxy for amplitude but reflects the diversity of populated outcomes. As such, they allow us to capture both market volatility and narrative constraints, signaling large and coherent moves driven by policy changes. In turn, the cumulative entropy is found to notably increase during regional episodes with high information density, providing effective signatures of such events. We argue that the obtained results indicate short-term globally coupled, yet regionally modulated, market impacts with clear connection to introduced policies. In what follows, the presented entropic framework emerges as an efficient complement to standard methods for characterizing markets under turbulent conditions, with potential to enhance forecasting strategies such as the stochastic modeling.

q-fin.ST↗

arXiv2026

Welfarist Formulations for Diverse Similarity Search

Nearest Neighbor Search (NNS) is a fundamental problem in data structures with wide-ranging applications, such as web search, recommendation systems, and, more recently, retrieval-augmented generations (RAG). In such recent applications, in addition to the relevance (similarity) of the returned neighbors, diversity among the neighbors is a central requirement. In this paper, we develop principled welfare-based formulations in NNS for realizing diversity across attributes. Our formulations are based on welfare functions -- from mathematical economics -- that satisfy central diversity (fairness) and relevance (economic efficiency) axioms. With a particular focus on Nash social welfare, we note that our welfare-based formulations provide objective functions that adaptively balance relevance and diversity in a query-dependent manner. Notably, such a balance was not present in the prior constraint-based approach, which forced a fixed level of diversity and optimized for relevance. In addition, our formulation provides a parametric way to control the trade-off between relevance and diversity, providing practitioners with flexibility to tailor search results to task-specific requirements. We develop efficient nearest neighbor algorithms with provable guarantees for the welfare-based objectives. Notably, our algorithm can be applied on top of any standard ANN method (i.e., use standard ANN method as a subroutine) to efficiently find neighbors that approximately maximize our welfare-based objectives. Experimental results demonstrate that our approach is practical and substantially improves diversity while maintaining high relevance of the retrieved neighbors.

cs.DS↗

arXiv2025

Design, modelling and experimental validation of bipenniform shape memory alloy-based linear actuator integrable with hydraulic stroke amplification mechanism

The increasing industrial demand for alternative actuators over conventional electromagnetism-based systems having limited efficiency, bulky size, complex design due to in-built gear-train mechanisms, and high production and amortization costs necessitates the innovation in new actuator development. Integrating bio-inspired design principles into linear actuators could bring forth the next generation of adaptive and energy efficient smart material-based actuation systems. The present study amalgamates the advantages of bipenniform architecture, which generates high force in the given physiological region and a high power-to-weight ratio of shape memory alloy (SMA), into a novel bio-inspired SMA-based linear actuator. A mathematical model of a multi-layered bipenniform configuration-based SMA actuator was developed and validated experimentally. The current research also caters to the incorporation of failure mitigation strategies using design failure mode and effects analysis along with the experimental assessment of the performance of the developed actuator. The system has been benchmarked against an industry-developed stepper motor-driven actuator. It has shown promising results generating an actuation force of 257 N with 15 V input voltage, meeting the acceptable range for actuation operation. It further exhibits about 67% reduction in the weight of the drive mechanism, with 80% lesser component, 32% cost reduction, and 19% energy savings and similar envelope dimensions for assembly compatibility with dampers and louvers for easy onsite deployment. The study introduces SMA coil-based actuator as an advanced design that can be deployed for high force-high stroke applications. The bio-inspired SMA-based linear actuator has applications ranging from building automation controls to lightweight actuation systems for space robotics and medical prosthesis.

cs.RO↗

arXiv2025

Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics

Given a noisy linear measurement $y = Ax + \xi$ of a distribution $p(x)$, and a good approximation to the prior $p(x)$, when can we sample from the posterior $p(x \mid y)$? Posterior sampling provides an accurate and fair framework for tasks such as inpainting, deblurring, and MRI reconstruction, and several heuristics attempt to approximate it. Unfortunately, approximate posterior sampling is computationally intractable in general. To sidestep this hardness, we focus on (local or global) log-concave distributions $p(x)$. In this regime, Langevin dynamics yields posterior samples when the exact scores of $p(x)$ are available, but it is brittle to score--estimation error, requiring an MGF bound (sub-exponential error). By contrast, in the unconditional setting, diffusion models succeed with only an $L^2$ bound on the score error. We prove that combining diffusion models with an annealed variant of Langevin dynamics achieves conditional sampling in polynomial time using merely an $L^4$ bound on the score error.

cs.LG↗

arXiv2025

AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up

Recent advances in generative AI have accelerated the discovery of novel chemicals and materials. However, scaling these discoveries to industrial production remains a major bottleneck due to the synthesis gap -- the need to develop entirely new manufacturing processes. This challenge requires detailed engineering blueprints: PFDs for equipment layouts and material/energy flows, and PIDs for process plant operations. Current AI systems cannot yet reliably generate these critical engineering schematics, creating a fundamental obstacle to manufacturing scale-up of novel discoveries. We present a closed-loop, physics-aware framework for automated generation of industrially viable PFDs and PIDs. The framework integrates three key components: (1) domain-specialized small language models (SLMs) trained for auto-generation of PFDs and PIDs, (2) a hierarchical knowledge graph containing process flow and instrumentation descriptions for 1,020+ chemicals for Graph Retrieval-Augmented Generation (GRAG), and (3) an open-source chemical process simulator for modeling, simulation, optimization, and analysis of novel chemical processes. The SLMs are trained through a multi-stage pipeline on synthetic datasets, with process simulator-in-the-loop validation ensuring feasibility. To enhance computational efficiency, the framework implements structural pruning (width and depth) guided by importance heuristics to reduce language model size while preserving accuracy, followed by advanced inference optimizations including FlashAttention, Lookahead Decoding, PagedAttention with KV-cache quantization, and Test-Time Inference Scaling. Experimental results demonstrate that our framework generates simulator-validated process descriptions with high fidelity.

cs.LG↗

arXiv2025

Dynamics of Thin Lubricant Films upon Liquid Contact on Slippery Surfaces

In recent years, slippery surfaces have attracted significant interest due to their excellent liquid-repellent properties and their potential in diverse commercial applications. Such surfaces are prepared by coating functionalized solid substrates with a thin lubricant film that prevents direct contact between a liquid and the substrate. The morphology of thin films upon liquid contact plays a central role in governing various phenomena, including the coalescence and mobility of liquid droplets, heat transfer efficiency, and the extent of lubricant depletion. However, a detailed understanding of film dynamics upon droplet contact remains limited, both from theoretical and experimental perspectives. Here, by employing principles of fluid dynamics, optics, and surface wetting, we present a comprehensive study that examines both the spatial and temporal variations of lubricant films upon contact with sessile liquid droplets and liquid bridges. Our findings reveal that the film dynamics can be categorized into three distinct stages, each significantly influenced by key system parameters: initial film thickness, three-phase contact line width, and Laplace pressure of liquids. Furthermore, we demonstrate that by optimizing these parameters, it is possible to reverse the lubricant flow in the final stage, thereby causing the liquid to partially lift off from the slippery surface.

cond-mat.soft↗

arXiv2025

Scaling Test-Time Inference with Policy-Optimized, Dynamic Retrieval-Augmented Generation via KV Caching and Decoding

We present a comprehensive framework for enhancing Retrieval-Augmented Generation (RAG) systems through dynamic retrieval strategies and reinforcement fine-tuning. This approach significantly improves large language models on knowledge-intensive tasks, including opendomain question answering and complex reasoning. Our framework integrates two complementary techniques: Policy-Optimized RetrievalAugmented Generation (PORAG), which optimizes the use of retrieved information, and Adaptive Token-Layer Attention Scoring (ATLAS), which dynamically determines retrieval timing and content based on contextual needs. Together, these techniques enhance both the utilization and relevance of retrieved content, improving factual accuracy and response quality. Designed as a lightweight solution compatible with any Transformer-based LLM without requiring additional training, our framework excels in knowledge-intensive tasks, boosting output accuracy in RAG settings. We further propose CRITIC, a novel method to selectively compress key-value caches by token importance, mitigating memory bottlenecks in long-context applications. The framework also incorporates test-time scaling techniques to dynamically balance reasoning depth and computational resources, alongside optimized decoding strategies for faster inference. Experiments on benchmark datasets show that our framework reduces hallucinations, strengthens domain-specific reasoning, and achieves significant efficiency and scalability gains over traditional RAG systems. This integrated approach advances the development of robust, efficient, and scalable RAG systems across diverse applications.

cs.LG↗

arXiv2025

Agentic Multimodal AI for Hyperpersonalized B2B and B2C Advertising in Competitive Markets: An AI-Driven Competitive Advertising Framework

The growing use of foundation models (FMs) in real-world applications demands adaptive, reliable, and efficient strategies for dynamic markets. In the chemical industry, AI-discovered materials drive innovation, but commercial success hinges on market adoption, requiring FM-driven advertising frameworks that operate in-the-wild. We present a multilingual, multimodal AI framework for autonomous, hyper-personalized advertising in B2B and B2C markets. By integrating retrieval-augmented generation (RAG), multimodal reasoning, and adaptive persona-based targeting, our system generates culturally relevant, market-aware ads tailored to shifting consumer behaviors and competition. Validation combines real-world product experiments with a Simulated Humanistic Colony of Agents to model consumer personas, optimize strategies at scale, and ensure privacy compliance. Synthetic experiments mirror real-world scenarios, enabling cost-effective testing of ad strategies without risky A/B tests. Combining structured retrieval-augmented reasoning with in-context learning (ICL), the framework boosts engagement, prevents market cannibalization, and maximizes ROAS. This work bridges AI-driven innovation and market adoption, advancing multimodal FM deployment for high-stakes decision-making in commercial marketing.

cs.LG↗

arXiv2025

Efficient Knowledge Distillation via Curriculum Extraction

Knowledge distillation is a technique used to train a small student network using the output generated by a large teacher network, and has many empirical advantages~\citep{Hinton2015DistillingTK}. While the standard one-shot approach to distillation only uses the output of the final teacher network, recent work~\citep{panigrahi2024progressive} has shown that using intermediate checkpoints from the teacher's training process as an implicit ``curriculum'' for progressive distillation can significantly speed up training. However, such schemes require storing these checkpoints, and often require careful selection of the intermediate checkpoints to train on, which can be impractical for large-scale training. In this paper, we show that a curriculum can be \emph{extracted} from just the fully trained teacher network, and that this extracted curriculum can give similar efficiency benefits to those of progressive distillation. Our extraction scheme is natural; we use a random projection of the hidden representations of the teacher network to progressively train the student network, before training using the output of the full network. We show that our scheme significantly outperforms one-shot distillation and achieves a performance similar to that of progressive distillation for learning sparse parities with two-layer networks, and provide theoretical guarantees for this setting. Additionally, we show that our method outperforms one-shot distillation even when using transformer-based architectures, both for sparse-parity learning, and language modeling tasks.

cs.LG↗

arXiv2025

Signatures of extreme events in the cumulative entropic spectrum

In this study, the cumulative effect of the empirical probability distribution of a random variable is identified as a factor that amplifies the occurrence of extreme events in datasets. To quantify this observation, a corresponding information measure is introduced, drawing upon Shannon entropy for joint probabilities. The proposed approach is validated using selected market data as case studies, encompassing various instances of extreme events. In particular, the results indicate that the introduced cumulative measure exhibits distinctive signatures of such events, even when the data is relatively noisy. These findings highlight the potential of the discussed concept for developing a new class of related indicators or classifiers.

physics.data-an↗

arXiv2025

Entropy-Assisted Quality Pattern Identification in Finance

Short-term patterns in financial time series form the cornerstone of many algorithmic trading strategies, yet extracting these patterns reliably from noisy market data remains a formidable challenge. In this paper, we propose an entropy-assisted framework for identifying high-quality, non-overlapping patterns that exhibit consistent behavior over time. We ground our approach in the premise that historical patterns, when accurately clustered and pruned, can yield substantial predictive power for short-term price movements. To achieve this, we incorporate an entropy-based measure as a proxy for information gain. Patterns that lead to high one-sided movements in historical data, yet retain low local entropy, are more informative in signaling future market direction. Compared to conventional clustering techniques such as K-means and Gaussian Mixture Models (GMM), which often yield biased or unbalanced groupings, our approach emphasizes balance over a forced visual boundary, ensuring that quality patterns are not lost due to over-segmentation. By emphasizing both predictive purity (low local entropy) and historical profitability, our method achieves a balanced representation of Buy and Sell patterns, making it better suited for short-term algorithmic trading strategies.

q-fin.TR↗

arXiv2025

FLIGHT: Facility Location Integrating Generalized, Holistic Theory of Welfare

The Facility Location Problem (FLP) is a well-studied optimization problem with applications in many real-world scenarios. Past literature has explored the solutions from different perspectives to tackle FLPs. These include investigating FLPs under objective functions such as utilitarian, egalitarian, Nash welfare, etc. Also, there is no treatment for asymmetric welfare functions around the facility. We propose a unified framework, FLIGHT, to accommodate a broad class of welfare notions. The framework undergoes rigorous theoretical analysis, and we prove some structural properties of the solution to FLP. Additionally, we provide approximation bounds, which provide insight into an interesting fact: as the number of agents arbitrarily increases, the choice of welfare notion is irrelevant. Furthermore, the paper also includes results around concentration bounds under certain distributional assumptions over the preferred locations of agents.

cs.GT↗

arXiv2024

Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design

Process Flow Diagrams (PFDs) and Process and Instrumentation Diagrams (PIDs) are critical tools for industrial process design, control, and safety. However, the generation of precise and regulation-compliant diagrams remains a significant challenge, particularly in scaling breakthroughs from material discovery to industrial production in an era of automation and digitalization. This paper introduces an autonomous agentic framework to address these challenges through a twostage approach involving knowledge acquisition and generation. The framework integrates specialized sub-agents for retrieving and synthesizing multimodal data from publicly available online sources and constructs ontological knowledge graphs using a Graph Retrieval-Augmented Generation (Graph RAG) paradigm. These capabilities enable the automation of diagram generation and open-domain question answering (ODQA) tasks with high contextual accuracy. Extensive empirical experiments demonstrate the frameworks ability to deliver regulation-compliant diagrams with minimal expert intervention, highlighting its practical utility for industrial applications.

cs.LG↗

arXiv2024

Multi-Source Knowledge-Based Hybrid Neural Framework for Time Series Representation Learning

Accurately predicting the behavior of complex dynamical systems, characterized by high-dimensional multivariate time series(MTS) in interconnected sensor networks, is crucial for informed decision-making in various applications to minimize risk. While graph forecasting networks(GFNs) are ideal for forecasting MTS data that exhibit spatio-temporal dependencies, prior works rely solely on the domain-specific knowledge of time-series variables inter-relationships to model the nonlinear dynamics, neglecting inherent relational structural dependencies among the variables within the MTS data. In contrast, contemporary works infer relational structures from MTS data but neglect domain-specific knowledge. The proposed hybrid architecture addresses these limitations by combining both domain-specific knowledge and implicit knowledge of the relational structure underlying the MTS data using Knowledge-Based Compositional Generalization. The hybrid architecture shows promising results on multiple benchmark datasets, outperforming state-of-the-art forecasting methods. Additionally, the architecture models the time varying uncertainty of multi-horizon forecasts.

cs.LG↗

arXiv2024

Multi-Knowledge Fusion Network for Time Series Representation Learning

Forecasting the behaviour of complex dynamical systems such as interconnected sensor networks characterized by high-dimensional multivariate time series(MTS) is of paramount importance for making informed decisions and planning for the future in a broad spectrum of applications. Graph forecasting networks(GFNs) are well-suited for forecasting MTS data that exhibit spatio-temporal dependencies. However, most prior works of GFN-based methods on MTS forecasting rely on domain-expertise to model the nonlinear dynamics of the system, but neglect the potential to leverage the inherent relational-structural dependencies among time series variables underlying MTS data. On the other hand, contemporary works attempt to infer the relational structure of the complex dependencies between the variables and simultaneously learn the nonlinear dynamics of the interconnected system but neglect the possibility of incorporating domain-specific prior knowledge to improve forecast accuracy. To this end, we propose a hybrid architecture that combines explicit prior knowledge with implicit knowledge of the relational structure within the MTS data. It jointly learns intra-series temporal dependencies and inter-series spatial dependencies by encoding time-conditioned structural spatio-temporal inductive biases to provide more accurate and reliable forecasts. It also models the time-varying uncertainty of the multi-horizon forecasts to support decision-making by providing estimates of prediction uncertainty. The proposed architecture has shown promising results on multiple benchmark datasets and outperforms state-of-the-art forecasting methods by a significant margin. We report and discuss the ablation studies to validate our forecasting architecture.

cs.LG↗

arXiv2024

Joint Hypergraph Rewiring and Memory-Augmented Forecasting Techniques in Digital Twin Technology

Digital Twin technology creates virtual replicas of physical objects, processes, or systems by replicating their properties, data, and behaviors. This advanced technology offers a range of intelligent functionalities, such as modeling, simulation, and data-driven decision-making, that facilitate design optimization, performance estimation, and monitoring operations. Forecasting plays a pivotal role in Digital Twin technology, as it enables the prediction of future outcomes, supports informed decision-making, minimizes risks, driving improvements in efficiency, productivity, and cost reduction. Recently, Digital Twin technology has leveraged Graph forecasting techniques in large-scale complex sensor networks to enable accurate forecasting and simulation of diverse scenarios, fostering proactive and data-driven decision making. However, existing Graph forecasting techniques lack scalability for many real-world applications. They have limited ability to adapt to non-stationary environments, retain past knowledge, lack a mechanism to capture the higher order spatio-temporal dynamics, and estimate uncertainty in model predictions. To surmount the challenges, we introduce a hybrid architecture that enhances the hypergraph representation learning backbone by incorporating fast adaptation to new patterns and memory-based retrieval of past knowledge. This balance aims to improve the slowly-learned backbone and achieve better performance in adapting to recent changes. In addition, it models the time-varying uncertainty of multi-horizon forecasts, providing estimates of prediction uncertainty. Our forecasting architecture has been validated through ablation studies and has demonstrated promising results across multiple benchmark datasets, surpassing state-ofthe-art forecasting methods by a significant margin.

cs.LG↗

arXiv2024

Genetic Algorithm to Optimize Design of Micro-Surgical Scissors

Microrobotics is an attractive area of research as small-scale robots have the potential to improve the precision and dexterity offered by minimally invasive surgeries. One example of such a tool is a pair of micro-surgical scissors that was developed for cutting of tumors or cancerous tissues present deep inside the body such as in the brain. This task is often deemed difficult or impossible with conventional robotic tools due to their size and dexterity. The scissors are designed with two magnets placed a specific distance apart to maximize deflection and generate cutting forces. However, remote actuation and size requirements of the micro-surgical scissors limits the force that can be generated to puncture the tissue. To address the limitation of small output forces, we use an evolutionary algorithm to further optimize the performance of the scissors. In this study, the design of the previously developed untethered micro-surgical scissors has been modified and their performance is enhanced by determining the optimal position of the magnets as well as the direction of each magnetic moment. The developed algorithm is successfully applied to a 4-magnet configuration which results in increased net torque. This improvement in net torque is directly translated into higher cutting forces. The new configuration generates a cutting force of 58 mN from 80 generations of the evolutionary algorithm which is a 1.65 times improvement from the original design. Furthermore, the developed algorithm has the advantage that it can be deployed with minor modifications to other microrobotic tools and systems, opening up new possibilities for various medical procedures and applications.

cs.RO↗