arXiv subjects

Mohit Sharma

Publications and source records attributed to Mohit Sharma.

At least 19 recordsLinked to original sources

arXiv2026

Temporal Tracking of Reeb-Space Sheets

Time-varying bivariate fields arise in many scientific applications, where the relationship between two scalar quantities evolves over time. While topological methods such as merge trees provide an effective framework for identifying and tracking features in univariate data, analogous approaches for bivariate fields remain comparatively underexplored. Reeb spaces extend topological analysis to multivariate data by representing fiber connectivity through a collection of interconnected sheets, making these sheets natural candidates for describing bivariate structures. However, establishing temporal correspondences between sheets is challenging due to the structural complexity of Reeb spaces, sensitivity to noise, and the difficulty of defining meaningful similarity measures across timesteps. We present a framework for tracking Reeb space sheets in time-varying bivariate fields. The method establishes correspondences between sheets in consecutive timesteps using complementary similarity measures defined in the spatial domain and the range space. We evaluate the method on a synthetic torus dataset and two time-varying molecular electronic structure datasets. The results show that Reeb space sheet tracking reveals persistent structures and highlights interesting intervals of temporal change. Overall, the results demonstrate that Reeb space sheets can serve as trackable topological structures and provide a foundation for the visual analysis of time-varying bivariate data.

cs.HC↗

arXiv2026

Summarizing Time-Varying Digital Image Correlation Strain Fields Using Sankey Diagrams

Digital Image Correlation (DIC) enables dense, time-resolved measurement of surface strain in deforming materials, providing insight into strain localization and failure mechanisms. However, the resulting strain fields are typically explored frame-by-frame through spatial visualizations, making global temporal patterns difficult to discern. We present a visual summarization approach that represents the evolution of high-strain regions as a single Sankey diagram constructed from superlevel sets of the von Mises equivalent strain field. By tracking connected components over time via spatial overlap, the diagram encodes the birth, persistence, merging, and disappearance of strain concentrations. Applied to four tensile test datasets with varying notch geometries, the approach compactly captures differences in deformation regimes and qualitative precursors to failure, complementing traditional spatial strain visualizations with a global temporal overview.

cs.HC↗

arXiv2025

A Generalized Weighted Overlap-Add (WOLA) Filter Bank for Improved Subband System Identification

This paper addresses the challenges in short-time Fourier transform (STFT) domain subband adaptive filtering, in particular, subband system identification. Previous studies in this area have primarily focused on setups with subband filtering at a downsampled rate, implemented using the weighted overlap-add (WOLA) filter bank, popular in audio and speech-processing for its reduced complexity. However, this traditional approach imposes constraints on the subband filters when transformed to their full-rate representation. This paper makes three key contributions. First, it introduces a generalized WOLA filter bank that repositions subband filters before the downsampling operation, eliminating the constraints on subband filters inherent in the conventional WOLA filter bank. Second, it investigates the mean square error (MSE) performance of the generalized WOLA filter bank for full-band system identification, establishing analytical ties between the order of subband filters, the full-band system impulse response length, the decimation factor, and the prototype filters. Third, to address the increased computational complexity of the generalized WOLA, the paper proposes a low-complexity implementation termed per-tone weighted overlap-add (PT-WOLA), which maintains computational complexity on par with conventional WOLA. Analytical and empirical evidence demonstrates that the proposed generalized WOLA filter bank significantly enhances the performance of subband system identification.

eess.AS↗

arXiv2025

Cost Efficient Fairness Audit Under Partial Feedback

We study the problem of auditing the fairness of a given classifier under partial feedback, where true labels are available only for positively classified individuals, (e.g., loan repayment outcomes are observed only for approved applicants). We introduce a novel cost model for acquiring additional labeled data, designed to more accurately reflect real-world costs such as credit assessment, loan processing, and potential defaults. Our goal is to find optimal fairness audit algorithms that are more cost-effective than random exploration and natural baselines. In our work, we consider two audit settings: a black-box model with no assumptions on the data distribution, and a mixture model, where features and true labels follow a mixture of exponential family distributions. In the black-box setting, we propose a near-optimal auditing algorithm under mild assumptions and show that a natural baseline can be strictly suboptimal. In the mixture model setting, we design a novel algorithm that achieves significantly lower audit cost than the black-box case. Our approach leverages prior work on learning from truncated samples and maximum-a-posteriori oracles, and extends known results on spherical Gaussian mixtures to handle exponential family mixtures, which may be of independent interest. Moreover, our algorithms apply to popular fairness metrics including demographic parity, equal opportunity, and equalized odds. Empirically, we demonstrate strong performance of our algorithms on real-world fair classification datasets like Adult Income and Law School, consistently outperforming natural baselines by around 50% in terms of audit cost.

cs.LG↗

arXiv2025

On Optimal Steering to Achieve Exact Fairness

To fix the 'bias in, bias out' problem in fair machine learning, it is important to steer feature distributions of data or internal representations of Large Language Models (LLMs) to ideal ones that guarantee group-fair outcomes. Previous work on fair generative models and representation steering could greatly benefit from provable fairness guarantees on the model output. We define a distribution as ideal if the minimizer of any cost-sensitive risk on it is guaranteed to have exact group-fair outcomes (e.g., demographic parity, equal opportunity)-in other words, it has no fairness-utility trade-off. We formulate an optimization program for optimal steering by finding the nearest ideal distribution in KL-divergence, and provide efficient algorithms for it when the underlying distributions come from well-known parametric families (e.g., normal, log-normal). Empirically, our optimal steering techniques on both synthetic and real-world datasets improve fairness without diminishing utility (and sometimes even improve utility). We demonstrate affine steering of LLM representations to reduce bias in multi-class classification, e.g., occupation prediction from a short biography in Bios dataset (De-Arteaga et al.). Furthermore, we steer internal representations of LLMs towards desired outputs so that it works equally well across different groups.

cs.LG↗

arXiv2025

Topology-Aware Volume Fusion for Spectral Computed Tomography via Histograms and Extremum Graph

Photon-Counting Computed Tomography (PCCT) is a novel imaging modality that simultaneously acquires volumetric data at multiple X-ray energy levels, generating separate volumes that capture energy-dependent attenuation properties. Attenuation refers to the reduction in X-ray intensity as it passes through different tissues or materials. This spectral information enhances tissue and material differentiation, enabling more accurate diagnosis and analysis. However, the resulting multivolume datasets are often complex and redundant, making visualization and interpretation challenging. To address these challenges, we propose a method for fusing spectral PCCT data into a single representative volume that enables direct volume rendering and segmentation by leveraging both shared and complementary information across different channels. Our approach starts by computing 2D histograms between pairs of volumes to identify those that exhibit prominent structural features. These histograms reveal relationships and variations that may be difficult to discern from individual volumes alone. Next, we construct an extremum graph from the 2D histogram of two minimally correlated yet complementary volumes-selected to capture both shared and distinct features-thereby maximizing the information content. The graph captures the topological distribution of histogram extrema. By extracting prominent structure within this graph and projecting each grid point in histogram space onto it, we reduce the dimensionality to one, producing a unified volume. This representative volume retains key structural and material characteristics from the original spectral data while significantly reducing the analysis scope from multiple volumes to one. The result is a topology-aware, information-rich fusion of multi-energy CT datasets that facilitates more effective visualization and segmentation.

cs.HC↗

arXiv2025

Growth of Structural Lengthscale in Kob Andersen Binary Mixtures: Role of medium range order

A central and extensively debated question in glass physics concerns whether a single, growing lengthscale fundamentally controls glassy dynamics, particularly in systems lacking obvious structural motifs like the Kob Andersen binary Lennard Jones (KALJ) model. In this work, we investigate structural and dynamical lengthscales in supercooled liquids using KALJ model in two compositions: 80:20 and 60:40. We compute the dynamical lengthscale from displacement displacement correlation functions and observe a consistent growth as temperature decreases. To explore the static counterpart, we use a structural order parameter (SOP) based on the mean field caging potential. While this SOP is known to predict short time dynamics effectively, its bare correlation function reveals minimal spatial growth. Motivated by recent findings that long time dynamics reflect collective rearrangements, we perform spatial coarse graining of the SOP and identify an optimal lengthscale Lmax that maximises structure dynamics correlation. We show that the structural correlation length derived from SOP coarse grained over Lmax exhibits clear growth with cooling and closely tracks the dynamical lengthscale, especially for A particles in the 80:20 mixture and for both A and B particles in the 60:40 system. Our results reconcile the previously observed absence of static length growth in the KALJ model by highlighting the necessity of intermediate range structural descriptors. Furthermore, we find that the particles with larger structural length growth also correspond to species with latent crystallisation tendencies, suggesting a possible link between structural order, dynamics, and incipient crystallisation.

cond-mat.soft↗

arXiv2025

Structure-Dynamics Correlation and Its Link to Fragility and Dynamic Heterogeneity

Understanding the connection between structure, dynamics, and fragility, the rate at which the relaxation time grows with decreasing temperature, is central to unravelling the glass transition. Fragility is often associated with dynamic heterogeneity, implying that if structure influences dynamics, more fragile systems should exhibit stronger structure dynamics correlations. In this study, we test the generality of this assumption using: Lennard Jones (LJ) and Weeks Chandler Andersen (WCA) systems, where fragility is tuned via density, and a modified LJ (q,p) system, where fragility is varied by changing the potential softness. We define a structural order parameter based on a mean field caging potential and analyse energy barriers at both macroscopic and microscopic levels. While the macroscopic free energy barrier slope correlates with fragility, the microscopic free energy barrier does not show a consistent trend. Instead, it exhibits a strong correlation with a structure dynamics correlation measure obtained from isoconfigurational ensemble simulations. Interestingly, the two systems showing the highest structure dynamics correlation, LJ at rho = 1.1 and the (8,5) model, are respectively the least and most fragile within their classes. These systems exhibit broad mobility distributions, large non Gaussian parameters, yet low four point susceptibilities, suggesting a decoupling between spatial correlation length and mobility contrast. Both systems lie in the enthalpy dominated regime and are close to the spinodal, pointing to mechanical instability as a source of heterogeneity. Our results reveal that structure dynamics correlation is more closely linked to the contrast in individual particle mobility than to the spatial extent of dynamic correlations that typically scale with fragility.

cond-mat.soft↗

arXiv2025

Cascaded Diffusion Models for Neural Motion Planning

Robots in the real world need to perceive and move to goals in complex environments without collisions. Avoiding collisions is especially difficult when relying on sensor perception and when goals are among clutter. Diffusion policies and other generative models have shown strong performance in solving local planning problems, but often struggle at avoiding all of the subtle constraint violations that characterize truly challenging global motion planning problems. In this work, we propose an approach for learning global motion planning using diffusion policies, allowing the robot to generate full trajectories through complex scenes and reasoning about multiple obstacles along the path. Our approach uses cascaded hierarchical models which unify global prediction and local refinement together with online plan repair to ensure the trajectories are collision free. Our method outperforms (by ~5%) a wide variety of baselines on challenging tasks in multiple domains including navigation and manipulation.

cs.RO↗

arXiv2025

Gemini Robotics: Bringing AI into the Physical World

Recent advancements in large multimodal models have led to the emergence of remarkable generalist capabilities in digital domains, yet their translation to physical agents such as robots remains a significant challenge. This report introduces a new family of AI models purposefully designed for robotics and built upon the foundation of Gemini 2.0. We present Gemini Robotics, an advanced Vision-Language-Action (VLA) generalist model capable of directly controlling robots. Gemini Robotics executes smooth and reactive movements to tackle a wide range of complex manipulation tasks while also being robust to variations in object types and positions, handling unseen environments as well as following diverse, open vocabulary instructions. We show that with additional fine-tuning, Gemini Robotics can be specialized to new capabilities including solving long-horizon, highly dexterous tasks, learning new short-horizon tasks from as few as 100 demonstrations and adapting to completely novel robot embodiments. This is made possible because Gemini Robotics builds on top of the Gemini Robotics-ER model, the second model we introduce in this work. Gemini Robotics-ER (Embodied Reasoning) extends Gemini's multimodal reasoning capabilities into the physical world, with enhanced spatial and temporal understanding. This enables capabilities relevant to robotics including object detection, pointing, trajectory and grasp prediction, as well as multi-view correspondence and 3D bounding box predictions. We show how this novel combination can support a variety of robotics applications. We also discuss and address important safety considerations related to this new class of robotics foundation models. The Gemini Robotics family marks a substantial step towards developing general-purpose robots that realizes AI's potential in the physical world.

cs.RO↗

arXiv2025

Continuous Scatterplot and Image Moments for Time-Varying Bivariate Field Analysis of Electronic Structure Evolution

Photoinduced electronic transitions are complex quantum-mechanical processes where electrons move between energy levels due to light absorption. This induces dynamics in electronic structure and nuclear geometry, driving important physical and chemical processes in fields like photobiology, materials design, and medicine. The evolving electronic structure can be characterized by two electron density fields: hole and particle natural transition orbitals (NTOs). Studying these density fields helps understand electronic charge movement between donor and acceptor regions within a molecule. Previous works rely on side-by-side visual comparisons of isosurfaces, statistical approaches, or bivariate field analysis with few instances. We propose a new method to analyze time-varying bivariate fields with many instances, which is relevant for understanding electronic structure changes during light-induced dynamics. Since NTO fields depend on nuclear geometry, the nuclear motion results in numerous time steps to analyze. This paper presents a structured approach to feature-directed visual exploration of time-varying bivariate fields using continuous scatterplots (CSPs) and image moment-based descriptors, tailored for studying evolving electronic structures post-photoexcitation. The CSP of the bivariate field at each time step is represented by a four-length image moment vector. The collection of all vector descriptors forms a point cloud in R^4, visualized using principal component analysis. Selecting appropriate principal components results in a representation of the point cloud as a curve on the plane, aiding tasks such as identifying key time steps, recognizing patterns within the bivariate field, and tracking the temporal evolution. We demonstrate this with two case studies on excited-state molecular dynamics, showing how bivariate field analysis provides application-specific insights.

cs.HC↗

arXiv2025

Predictive Red Teaming: Breaking Policies Without Breaking Robots

Visuomotor policies trained via imitation learning are capable of performing challenging manipulation tasks, but are often extremely brittle to lighting, visual distractors, and object locations. These vulnerabilities can depend unpredictably on the specifics of training, and are challenging to expose without time-consuming and expensive hardware evaluations. We propose the problem of predictive red teaming: discovering vulnerabilities of a policy with respect to environmental factors, and predicting the corresponding performance degradation without hardware evaluations in off-nominal scenarios. In order to achieve this, we develop RoboART: an automated red teaming (ART) pipeline that (1) modifies nominal observations using generative image editing to vary different environmental factors, and (2) predicts performance under each variation using a policy-specific anomaly detector executed on edited observations. Experiments across 500+ hardware trials in twelve off-nominal conditions for visuomotor diffusion policies demonstrate that RoboART predicts performance degradation with high accuracy (less than 0.19 average difference between predicted and real success rates). We also demonstrate how predictive red teaming enables targeted data collection: fine-tuning with data collected under conditions predicted to be adverse boosts baseline performance by 2-7x.

cs.RO↗

arXiv2025

Learning the RoPEs: Better 2D and 3D Position Encodings with STRING

We introduce STRING: Separable Translationally Invariant Position Encodings. STRING extends Rotary Position Encodings, a recently proposed and widely used algorithm in large language models, via a unifying theoretical framework. Importantly, STRING still provides exact translation invariance, including token coordinates of arbitrary dimensionality, whilst maintaining a low computational footprint. These properties are especially important in robotics, where efficient 3D token representation is key. We integrate STRING into Vision Transformers with RGB(-D) inputs (color plus optional depth), showing substantial gains, e.g. in open-vocabulary object detection and for robotics controllers. We complement our experiments with a rigorous mathematical analysis, proving the universality of our methods.

cs.LG↗

arXiv2024

Gen-AI for User Safety: A Survey

Machine Learning and data mining techniques (i.e. supervised and unsupervised techniques) are used across domains to detect user safety violations. Examples include classifiers used to detect whether an email is spam or a web-page is requesting bank login information. However, existing ML/DM classifiers are limited in their ability to understand natural languages w.r.t the context and nuances. The aforementioned challenges are overcome with the arrival of Gen-AI techniques, along with their inherent ability w.r.t translation between languages, fine-tuning between various tasks and domains. In this manuscript, we provide a comprehensive overview of the various work done while using Gen-AI techniques w.r.t user safety. In particular, we first provide the various domains (e.g. phishing, malware, content moderation, counterfeit, physical safety) across which Gen-AI techniques have been applied. Next, we provide how Gen-AI techniques can be used in conjunction with various data modalities i.e. text, images, videos, audio, executable binaries to detect violations of user-safety. Further, also provide an overview of how Gen-AI techniques can be used in an adversarial setting. We believe that this work represents the first summarization of Gen-AI techniques for user-safety.

cs.AI↗

arXiv2024

Semantically Controllable Augmentations for Generalizable Robot Learning

Generalization to unseen real-world scenarios for robot manipulation requires exposure to diverse datasets during training. However, collecting large real-world datasets is intractable due to high operational costs. For robot learning to generalize despite these challenges, it is essential to leverage sources of data or priors beyond the robot's direct experience. In this work, we posit that image-text generative models, which are pre-trained on large corpora of web-scraped data, can serve as such a data source. These generative models encompass a broad range of real-world scenarios beyond a robot's direct experience and can synthesize novel synthetic experiences that expose robotic agents to additional world priors aiding real-world generalization at no extra cost. In particular, our approach leverages pre-trained generative models as an effective tool for data augmentation. We propose a generative augmentation framework for semantically controllable augmentations and rapidly multiplying robot datasets while inducing rich variations that enable real-world generalization. Based on diverse augmentations of robot data, we show how scalable robot manipulation policies can be trained and deployed both in simulation and in unseen real-world environments such as kitchens and table-tops. By demonstrating the effectiveness of image-text generative models in diverse real-world robotic applications, our generative augmentation framework provides a scalable and efficient path for boosting generalization in robot learning at no extra human cost.

cs.RO↗

arXiv2024

Exploring the soft pinning effect in the dynamics and the structure dynamics correlation in multicomponent supercooled liquids

We study multicomponent liquids by increasing the mass of $15\%$ of the particles in a binary Kob-Andersen model. We find that the heavy particles have dual effects on the lighter particles. At higher temperatures, there is a significant decoupling of the dynamics between heavier and lighter particles, with the former resembling a pinned particle to the latter. The dynamics of the lighter particles slow down due to the excluded volume around the nearly immobile heavier particles. Conversely, at lower temperatures, there is a coupling between the dynamics of the heavier and lighter particles. The heavier particles' mass slows down the dynamics of both types of particles. This makes the soft pinning effect of the heavy particles questionable in this regime. We demonstrate that as the mass of the heavy particles increases, the coupling of the dynamics between the lighter and heavier particles weakens. Consequently, the heavier the mass of the heavy particles, the more effectively they act as soft pinning centres in both high and low-temperature regimes. A key finding is that akin to the pinned system, the self and collective dynamics of the lighter particles decouple from each other as the mass of the heavy particles has a more pronounced impact on the latter. We analyze the structure dynamics correlation by considering the system under the binary and modified quaternary framework, the latter describing the pinned system. Our findings indicate that whenever the heavy mass particles function as soft pinning centres, the modified quaternary framework predicts a higher correlation.

cond-mat.soft↗

arXiv2024

Jacobi Set Simplification for Tracking Topological Features in Time-Varying Scalar Fields

The Jacobi set of a bivariate scalar field is the set of points where the gradients of the two constituent scalar fields align with each other. It captures the regions of topological changes in the bivariate field. The Jacobi set is a bivariate analog of critical points, and may correspond to features of interest. In the specific case of time-varying fields and when one of the scalar fields is time, the Jacobi set corresponds to temporal tracks of critical points, and serves as a feature-tracking graph. The Jacobi set of a bivariate field or a time-varying scalar field is complex, resulting in cluttered visualizations that are difficult to analyze. This paper addresses the problem of Jacobi set simplification. Specifically, we use the time-varying scalar field scenario to introduce a method that computes a reduced Jacobi set. The method is based on a stability measure called robustness that was originally developed for vector fields and helps capture the structural stability of critical points. We also present a mathematical analysis for the method, and describe an implementation for 2D time-varying scalar fields. Applications to both synthetic and real-world datasets demonstrate the effectiveness of the method for tracking features.

math.NA↗

arXiv2024

How Far Can Fairness Constraints Help Recover From Biased Data?

A general belief in fair classification is that fairness constraints incur a trade-off with accuracy, which biased data may worsen. Contrary to this belief, Blum & Stangl (2019) show that fair classification with equal opportunity constraints even on extremely biased data can recover optimally accurate and fair classifiers on the original data distribution. Their result is interesting because it demonstrates that fairness constraints can implicitly rectify data bias and simultaneously overcome a perceived fairness-accuracy trade-off. Their data bias model simulates under-representation and label bias in underprivileged population, and they show the above result on a stylized data distribution with i.i.d. label noise, under simple conditions on the data distribution and bias parameters. We propose a general approach to extend the result of Blum & Stangl (2019) to different fairness constraints, data bias models, data distributions, and hypothesis classes. We strengthen their result, and extend it to the case when their stylized distribution has labels with Massart noise instead of i.i.d. noise. We prove a similar recovery result for arbitrary data distributions using fair reject option classifiers. We further generalize it to arbitrary data distributions and arbitrary hypothesis classes, i.e., we prove that for any data distribution, if the optimally accurate classifier in a given hypothesis class is fair and robust, then it can be recovered through fair classification with equal opportunity constraints on the biased distribution whenever the bias parameters satisfy certain simple conditions. Finally, we show applications of our technique to time-varying data bias in classification and fair machine learning pipelines.

cs.LG↗