Kunal Gupta

Ruoyu Wen, Stephanie Elena Crowe, Kunal Gupta et al.

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.

Noam Aigerman, Kunal Gupta, Vladimir G. Kim et al.

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.

Poornima Meegammana, Niranjan Meegammana, Chathurika Jayalath et al.

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.

Poorvesh Dongre, Majid Behravan, Kunal Gupta et al.

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.

Eion Tyacke, Kunal Gupta, Jay Patel et al.

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.

Kunal Gupta, Brendan Colvert, Francisco Contijoch

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.

Kunal Gupta, Manmohan Chandraker

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.