arXiv subjects

Kunal Gupta

Publications and source records attributed to Kunal Gupta.

18 recordsLinked to original sources

arXiv2026

Spherical DAHA as an algebra of framed BPS states

Line operators of 4d $\mathcal{N}=2$ theories of class $\mathcal{S}$ of type $A_{N-1}$ in a half Omega background provide a physical model for $SL_N$ skein algebras. In this paper we extend this correspondence to $GL_N$ skein algebras and prove that the $GL_2$ skein algebra of the punctured torus is isomorphic to the $GL_2$ spherical double affine Hecke algebra ${{\mathbf{S}\ddot{\mathbf{H}}}}^{q,t}_2$. The construction is based on $\mathfrak{q}$-nonabelianization for the $SU(2)$ $\mathcal{N}=2^*$ gauge theory, which realizes the skein algebra as a quantum torus algebra associated with the Seiberg-Witten curve. Different regions of the Coulomb branch yield distinct presentations of ${{\mathbf{S}\ddot{\mathbf{H}}}}^{q,t}_2$. These range from the Macdonald $q$-difference module in Fenchel-Nielsen (weak coupling) charts to cluster-type realizations in Fock-Goncharov (strong coupling) charts. Transitions between these descriptions are governed by the vanilla BPS spectrum of the $\mathcal{N}=2^*$ theory via framed wall-crossing, which provides a unified physical framework for several representations of spherical DAHA.

hep-th↗

arXiv2026

The Missing Link of XR: Empathy-Driven Reality for XR and Beyond

Extended reality (XR) for socialising is becoming increasingly popular. However, unlike conventional social platforms, XR prioritises embodiment and immersion, factors that strongly impact one's physical and mental states. We envision a future for XR where all users, regardless of abilities and backgrounds, can understand one another, participate, and find safe socialisation spaces. An Empathy-Driven Reality (EDR) is a space where understanding each other's emotional, physical, and cognitive states takes centre stage. It has the potential to enhance empathy beyond how we normally perceive it. To explore this concept, we conducted a hybrid-style workshop over two months with 27 industry and academic researchers in XR, emotion, physiology, assistive technology, and social science. This paper reports on the findings and aims to establish a structure and reference for the 1) design guidelines, 2) research challenges, and 3) potential applications for the future of XR as an EDR. We frame EDR as a conceptual design framework rather than a validated system: a structured design space that links requirements to design mechanisms, together with a research agenda for empathy-centred XR.

cs.HC↗

arXiv2026

Reflecting Process Expertise in Procedural Material Generation

Procedural material creation underpins applications in digital content creation, visual effects, and 3D asset design. Achieving high-quality results requires more than reproducing node graphs -- it demands understanding the process by which experts construct materials. We formulate procedural material generation as retrieval-time process reasoning over expert demonstrations, elevating process to a first-class representation beyond graph-only synthesis. Concretely, we represent expert workflows as process traces: textual records of construction steps, parameters, and design intent. To instantiate this idea, we use a pretrained LLM-based ProcessSynthesizer to synthesize a process trace aligned with a user's intent and a pretrained LLM-based Compiler to ground the process trace into an executable Blender material graph. Because procedural expertise is most naturally conveyed through demonstrations, we leverage tutorial videos as a source of process knowledge and extract textual, LLM-compatible traces using automated video analysis tools. In an expert study with five Blender artists (avg. 7.5 years of experience), materials generated by reflecting expert demonstrations were found to produce workflows requiring fewer edits, and more closely match professional design strategies than methods operating solely on static artifacts. A user study with 150 participants further shows that our approach achieves superior generation and editing performance compared to prior procedural systems. All code, models, and data will be available at https://materialapprentice.github.io

cs.CV↗

arXiv2026

From Uncertainty to Possibility: Early Computing Experiences for Rural Girls

Girls remain underrepresented in computing, and rural contexts often compound barriers of access, language, and gender norms. Prior work in computing education highlights that confidence and belonging can shape participation, yet most evidence comes from well-resourced, English-dominant settings. Less is known about how locally grounded pathways can build programming self-efficacy and broaden career interest for adolescent girls. We addressed this gap by delivering a curriculum that began with digital foundations and unplugged problem-solving, then progressed to block-based programming activities, supported by parent awareness and teacher training in gender-responsive practices. Pre and post-surveys showed a reliable increase in programming self-efficacy, and career aspirations shifted toward technology. Complementary qualitative data indicate that mastery experiences, peer collaboration, and the creation of personal projects were key drivers of confidence, suggesting design priorities for scalable, locally relevant programmes in low-resource communities that can shift perceptions of who belongs in computing.

cs.HC↗

arXiv2026

NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code

The proliferation of neural radiance field (NeRF) research requires significant efforts to reimplement papers before building upon them. We introduce NERFIFY, a multi-agent framework that reliably converts NeRF research papers into trainable Nerfstudio plugins, in contrast to generic paper-to-code methods and frontier models like GPT-5 that usually fail to produce runnable code. NERFIFY achieves domain-specific executability through six key innovations: (1) Context-free grammar (CFG): LLM synthesis is constrained by Nerfstudio formalized as a CFG, ensuring generated code satisfies architectural invariants. (2) Graph-of-Thought code synthesis: Specialized multi-file-agents generate repositories in topological dependency order, validating contracts and errors at each node. (3) Compositional citation recovery: Agents automatically retrieve and integrate components (samplers, encoders, proposal networks) from citation graphs of references. (4) Visual feedback: Artifacts are diagnosed through PSNR-minima ROI analysis, cross-view geometric validation, and VLM-guided patching to iteratively improve quality. (5) Knowledge enhancement: Beyond reproduction, methods can be improved with novel optimizations. (6) Benchmarking: An evaluation framework is designed for NeRF paper-to-code synthesis across 30 diverse papers. On papers without public implementations, NERFIFY achieves visual quality matching expert human code (+/-0.5 dB PSNR, +/-0.2 SSIM) while reducing implementation time from weeks to minutes. NERFIFY demonstrates that a domain-aware design enables code translation for complex vision papers, potentiating accelerated and democratized reproducible research. Code, data and implementations will be publicly released.

cs.CV↗

arXiv2025

Investigating AI in Peer Support via Multi-Module System-Driven Embodied Conversational Agents

Young people's mental well-being is a global concern, with peer support playing a key role in daily emotional regulation. Conversational agents are increasingly viewed as promising tools for delivering accessible, personalised peer support, particularly where professional counselling is limited. However, existing systems often suffer from rigid input formats, scripted responses, and limited emotional sensitivity. The emergence of large language models introduces new possibilities for generating flexible, context-aware, and empathetic responses. To explore how individuals with psychological training perceive such systems in peer support contexts, we developed an LLM-based multi-module system to drive embodied conversational agents informed by Cognitive Behavioral Therapy (CBT). In a user study (N=10), we qualitatively examined participants' perceptions, focusing on trust, response quality, workflow integration, and design opportunities for future mental well-being support systems.

cs.HC↗

arXiv2025

IsoNet: Causal Analysis of Multimodal Transformers for Neuromuscular Gesture Classification

Hand gestures are a primary output of the human motor system, yet the decoding of their neuromuscular signatures remains a bottleneck for basic neuroscience and assistive technologies such as prosthetics. Traditional human-machine interface pipelines rely on a single biosignal modality, but multimodal fusion can exploit complementary information from sensors. We systematically compare linear and attention-based fusion strategies across three architectures: a Multimodal MLP, a Multimodal Transformer, and a Hierarchical Transformer, evaluating performance on scenarios with unimodal and multimodal inputs. Experiments use two publicly available datasets: NinaPro DB2 (sEMG and accelerometer) and HD-sEMG 65-Gesture (high-density sEMG and force). Across both datasets, the Hierarchical Transformer with attention-based fusion consistently achieved the highest accuracy, surpassing the multimodal and best single-modality linear-fusion MLP baseline by over 10% on NinaPro DB2 and 3.7% on HD-sEMG. To investigate how modalities interact, we introduce an Isolation Network that selectively silences unimodal or cross-modal attention pathways, quantifying each group of token interactions' contribution to downstream decisions. Ablations reveal that cross-modal interactions contribute approximately 30% of the decision signal across transformer layers, highlighting the importance of attention-driven fusion in harnessing complementary modality information. Together, these findings reveal when and how multimodal fusion would enhance biosignal classification and also provides mechanistic insights of human muscle activities. The study would be beneficial in the design of sensor arrays for neurorobotic systems.

cs.LG↗

arXiv2024

Linking disks, spinning vortices and exponential networks of augmentation curves

We propose a mirror derivation of the quiver description of open topological strings known as the knots-quivers correspondence, based on enumerative invariants of augmentation curves encoded by exponential networks. Quivers are obtained by studying M2 branes wrapping holomorphic disks with Lagrangian boundary conditions on an M5 brane, through their identification with a distinguished sector of BPS kinky vortices in the 3d-3d dual QFT. Our proposal suggests that holomorphic disks with Lagrangian boundary conditions are mirror to calibrated 1-chains on the associated augmentation curve, whose intersections encode the linking of boundaries.

hep-th↗

arXiv2024

Infinite-Length Limit of Spectral Curves and Inverse Scattering

Integrability equips models of theoretical physics with efficient methods for the exact construction of useful states and their evolution. Relevant tools for classical integrable field models in one spatial dimensional are spectral curves in the case of periodic fields and inverse scattering for asymptotic boundary conditions. Even though the two methods are quite different in many ways, they ought to be related by taking the periodicity length of closed boundary conditions to infinity. Using the Korteweg-de Vries equation and the continuous Heisenberg magnet as prototypical classical integrable field models, we discuss and illustrate how data for spectral curves transforms into asymptotic scattering data. In order to gain intuition and also for concreteness, we review how the elliptic states of these models degenerate into solitons at infinite length.

math-ph↗

arXiv2024

Large Language Models for Automatic Detection of Sensitive Topics

Sensitive information detection is crucial in content moderation to maintain safe online communities. Assisting in this traditionally manual process could relieve human moderators from overwhelming and tedious tasks, allowing them to focus solely on flagged content that may pose potential risks. Rapidly advancing large language models (LLMs) are known for their capability to understand and process natural language and so present a potential solution to support this process. This study explores the capabilities of five LLMs for detecting sensitive messages in the mental well-being domain within two online datasets and assesses their performance in terms of accuracy, precision, recall, F1 scores, and consistency. Our findings indicate that LLMs have the potential to be integrated into the moderation workflow as a convenient and precise detection tool. The best-performing model, GPT-4o, achieved an average accuracy of 99.5\% and an F1-score of 0.99. We discuss the advantages and potential challenges of using LLMs in the moderation workflow and suggest that future research should address the ethical considerations of utilising this technology.

cs.CL↗

arXiv2024

Vortices on Cylinders and Warped Exponential Networks

We study 3d $\mathcal{N}=2$ $U(1)$ Chern-Simons-matter QFT on a cylinder $C\times\mathbb{R}$. The topology of $C$ gives rise to BPS sectors of low-energy solitons known as kinky vortices, which interpolate between (possibly) different vacua at the ends of the cylinder and at the same time carry magnetic flux. We compute the spectrum of BPS vortices on the cylinder in an isolated Higgs vacuum, through the framework of \emph{warped} exponential networks, which we introduce. We then conjecture a relation between these and standard vortices on $\mathbb{R}^2$, which are related to genus-zero open Gromov-Witten invariants of toric branes. More specifically, we show that in the limit of large Fayet-Iliopoulos coupling, the spectrum of kinky vortices on $C$ undergoes an infinite sequence of wall-crossing transitions, and eventually stabilizes. We then propose an exact relation between a generating series of stabilized CFIV indices and the Gromov-Witten disk potential, and discuss its consequences for the structure of moduli spaces of vortices.

hep-th↗

arXiv2024

Integrating Physiological Data with Large Language Models for Empathic Human-AI Interaction

This paper explores enhancing empathy in Large Language Models (LLMs) by integrating them with physiological data. We propose a physiological computing approach that includes developing deep learning models that use physiological data for recognizing psychological states and integrating the predicted states with LLMs for empathic interaction. We showcase the application of this approach in an Empathic LLM (EmLLM) chatbot for stress monitoring and control. We also discuss the results of a pilot study that evaluates this EmLLM chatbot based on its ability to accurately predict user stress, provide human-like responses, and assess the therapeutic alliance with the user.

eess.SP↗

arXiv2023

From Unstable Contacts to Stable Control: A Deep Learning Paradigm for HD-sEMG in Neurorobotics

In the past decade, there has been significant advancement in designing wearable neural interfaces for controlling neurorobotic systems, particularly bionic limbs. These interfaces function by decoding signals captured non-invasively from the skin's surface. Portable high-density surface electromyography (HD-sEMG) modules combined with deep learning decoding have attracted interest by achieving excellent gesture prediction and myoelectric control of prosthetic systems and neurorobots. However, factors like pixel-shape electrode size and unstable skin contact make HD-sEMG susceptible to pixel electrode drops. The sparse electrode-skin disconnections rooted in issues such as low adhesion, sweating, hair blockage, and skin stretch challenge the reliability and scalability of these modules as the perception unit for neurorobotic systems. This paper proposes a novel deep-learning model providing resiliency for HD-sEMG modules, which can be used in the wearable interfaces of neurorobots. The proposed 3D Dilated Efficient CapsNet model trains on an augmented input space to computationally `force' the network to learn channel dropout variations and thus learn robustness to channel dropout. The proposed framework maintained high performance under a sensor dropout reliability study conducted. Results show conventional models' performance significantly degrades with dropout and is recovered using the proposed architecture and the training paradigm.

cs.RO↗

arXiv2023

Wish You Were Here: Mental and Physiological Effects of Remote Music Collaboration in Mixed Reality

With face-to-face music collaboration being severely limited during the recent pandemic, mixed reality technologies and their potential to provide musicians a feeling of "being there" with their musical partner can offer tremendous opportunities. In order to assess this potential, we conducted a laboratory study in which musicians made music together in real-time while simultaneously seeing their jamming partner's mixed reality point cloud via a head-mounted display and compared mental effects such as flow, affect, and co-presence to an audio-only baseline. In addition, we tracked the musicians' physiological signals and evaluated their features during times of self-reported flow. For users jamming in mixed reality, we observed a significant increase in co-presence. Regardless of the condition (mixed reality or audio-only), we observed an increase in positive affect after jamming remotely. Furthermore, we identified heart rate and HF/LF as promising features for classifying the flow state musicians experienced while making music together.

cs.HC↗

arXiv2022

Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes

This paper introduces a framework designed to accurately predict piecewise linear mappings of arbitrary meshes via a neural network, enabling training and evaluating over heterogeneous collections of meshes that do not share a triangulation, as well as producing highly detail-preserving maps whose accuracy exceeds current state of the art. The framework is based on reducing the neural aspect to a prediction of a matrix for a single given point, conditioned on a global shape descriptor. The field of matrices is then projected onto the tangent bundle of the given mesh, and used as candidate jacobians for the predicted map. The map is computed by a standard Poisson solve, implemented as a differentiable layer with cached pre-factorization for efficient training. This construction is agnostic to the triangulation of the input, thereby enabling applications on datasets with varying triangulations. At the same time, by operating in the intrinsic gradient domain of each individual mesh, it allows the framework to predict highly-accurate mappings. We validate these properties by conducting experiments over a broad range of scenarios, from semantic ones such as morphing, registration, and deformation transfer, to optimization-based ones, such as emulating elastic deformations and contact correction, as well as being the first work, to our knowledge, to tackle the task of learning to compute UV parameterizations of arbitrary meshes. The results exhibit the high accuracy of the method as well as its versatility, as it is readily applied to the above scenarios without any changes to the framework.

cs.GR↗

arXiv2022

Neural Computed Tomography

Motion during acquisition of a set of projections can lead to significant motion artifacts in computed tomography reconstructions despite fast acquisition of individual views. In cases such as cardiac imaging, motion may be unavoidable and evaluating motion may be of clinical interest. Reconstructing images with reduced motion artifacts has typically been achieved by developing systems with faster gantry rotation or using algorithms which measure and/or estimate the displacements. However, these approaches have had limited success due to both physical constraints as well as the challenge of estimating/measuring non-rigid, temporally varying, and patient-specific motions. We propose a novel reconstruction framework, NeuralCT, to generate time-resolved images free from motion artifacts. Our approaches utilizes a neural implicit approach and does not require estimation or modeling of the underlying motion. Instead, boundaries are represented using a signed distance metric and neural implicit framework. We utilize `analysis-by-synthesis' to identify a solution consistent with the acquired sinogram as well as spatial and temporal consistency constraints. We illustrate the utility of NeuralCT in three progressively more complex scenarios: translation of a small circle, heartbeat-like change in an ellipse's diameter, and complex topological deformation. Without hyperparameter tuning or change to the architecture, NeuralCT provides high quality image reconstruction for all three motions, as compared to filtered backprojection, using mean-square-error and Dice metrics.

eess.IV↗

arXiv2020

Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows

Meshes are important representations of physical 3D entities in the virtual world. Applications like rendering, simulations and 3D printing require meshes to be manifold so that they can interact with the world like the real objects they represent. Prior methods generate meshes with great geometric accuracy but poor manifoldness. In this work, we propose Neural Mesh Flow (NMF) to generate two-manifold meshes for genus-0 shapes. Specifically, NMF is a shape auto-encoder consisting of several Neural Ordinary Differential Equation (NODE)[1] blocks that learn accurate mesh geometry by progressively deforming a spherical mesh. Training NMF is simpler compared to state-of-the-art methods since it does not require any explicit mesh-based regularization. Our experiments demonstrate that NMF facilitates several applications such as single-view mesh reconstruction, global shape parameterization, texture mapping, shape deformation and correspondence. Importantly, we demonstrate that manifold meshes generated using NMF are better-suited for physically-based rendering and simulation. Code and data are released.

cs.CV↗

arXiv2017

Empirical Analysis on Comparing the Performance of Alpha Miner Algorithm in SQL Query Language and NoSQL Column-Oriented Databases Using Apache Phoenix

Process-Aware Information Systems (PAIS) is an IT system that support business processes and generate large amounts of event logs from the execution of business processes. An event log is represented as a tuple of CaseID, Timestamp, Activity and Actor. Process Mining is a new and emerging field that aims at analyzing the event logs to discover, enhance and improve business processes and check conformance between run time and design time business processes. The large volume of event logs generated are stored in the databases. Relational databases perform well for a certain class of applications. However, there are a certain class of applications for which relational databases are not able to scale. To handle such class of applications, NoSQL database systems emerged. Discovering a process model (workflow model) from event logs is one of the most challenging and important Process Mining task. The $\alpha$-miner algorithm is one of the first and most widely used Process Discovery technique. Our objective is to investigate which of the databases (Relational or NoSQL) performs better for a Process Discovery application under Process Mining. We implement the $\alpha$-miner algorithm on relational (row-oriented) and NoSQL (column-oriented) databases in database query languages so that our algorithm is tightly coupled to the database. We present a performance benchmarking and comparison of the $\alpha$-miner algorithm on row-oriented database and NoSQL column-oriented database so that we can compare which database can efficiently store massive event logs and analyze it in seconds to discover a process model.

cs.DB↗