arXiv subjects

Abhishek Jaiswal

Publications and source records attributed to Abhishek Jaiswal.

9 recordsLinked to original sources

arXiv2026

A Qualitative Model for Reasoning about Path and Support

Spatial reasoning abilities correlate strongly with performance in STEM fields. Games offer a compelling medium for training these critical skills in developing children who have a natural proclivity for play. However, to facilitate human-like tutoring and player guidance, these games require an AI agent capable of making commonsense inferences from spatial events. Qualitative reasoning (QR) models appear to be a suitable framework for these application domains. As these models reason in symbolic representations, they can seamlessly translate game states into interpretable feedback for human-like player guidance. This paper introduces a hybrid qualitative model designed for Camelot Jr., a block-puzzle game that requires constructing multi-level bridges to connect two avatars stationed on separate towers. The game poses a challenge for the player, who must make platforms stable, plan their path, and ensure they use all the provided blocks. To handle the precise physics required by the domain, we integrate a mathematical center-of-mass stability logic to guide our qualitative solver. Our work facilitates spatial skill training in Camelot Jr. and contributes to the development of human-centric, explainable game-playing agents.

cs.AI↗

arXiv2025

Posture-Driven Action Intent Inference for Playing style and Fatigue Assessment

Posture-based mental state inference has significant potential in diagnosing fatigue, preventing injury, and enhancing performance across various domains. Such tools must be research-validated with large datasets before being translated into practice. Unfortunately, such vision diagnosis faces serious challenges due to the sensitivity of human subject data. To address this, we identify sports settings as a viable alternative for accumulating data from human subjects experiencing diverse emotional states. We test our hypothesis in the game of cricket and present a posture-based solution to identify human intent from activity videos. Our method achieves over 75\% F1 score and over 80\% AUC-ROC in discriminating aggressive and defensive shot intent through motion analysis. These findings indicate that posture leaks out strong signals for intent inference, even with inherent noise in the data pipeline. Furthermore, we utilize existing data statistics as weak supervision to validate our findings, offering a potential solution for overcoming data labelling limitations. This research contributes to generalizable techniques for sports analytics and also opens possibilities for applying human behavior analysis across various fields.

cs.CV↗

arXiv2025

Red Teaming Large Language Models for Healthcare

We present the design process and findings of the pre-conference workshop at the Machine Learning for Healthcare Conference (2024) entitled Red Teaming Large Language Models for Healthcare, which took place on August 15, 2024. Conference participants, comprising a mix of computational and clinical expertise, attempted to discover vulnerabilities -- realistic clinical prompts for which a large language model (LLM) outputs a response that could cause clinical harm. Red-teaming with clinicians enables the identification of LLM vulnerabilities that may not be recognised by LLM developers lacking clinical expertise. We report the vulnerabilities found, categorise them, and present the results of a replication study assessing the vulnerabilities across all LLMs provided.

cs.CL↗

arXiv2025

Real-Time Feedback and Benchmark Dataset for Isometric Pose Evaluation

Isometric exercises appeal to individuals seeking convenience, privacy, and minimal dependence on equipments. However, such fitness training is often overdependent on unreliable digital media content instead of expert supervision, introducing serious risks, including incorrect posture, injury, and disengagement due to lack of corrective feedback. To address these challenges, we present a real-time feedback system for assessing isometric poses. Our contributions include the release of the largest multiclass isometric exercise video dataset to date, comprising over 3,600 clips across six poses with correct and incorrect variations. To support robust evaluation, we benchmark state-of-the-art models-including graph-based networks-on this dataset and introduce a novel three-part metric that captures classification accuracy, mistake localization, and model confidence. Our results enhance the feasibility of intelligent and personalized exercise training systems for home workouts. This expert-level diagnosis, delivered directly to the users, also expands the potential applications of these systems to rehabilitation, physiotherapy, and various other fitness disciplines that involve physical motion.

cs.CV↗

arXiv2024

Benchmarking Reliability of Deep Learning Models for Pathological Gait Classification

Early detection of neurodegenerative disorders is an important open problem, since early diagnosis and treatment may yield a better prognosis. Researchers have recently sought to leverage advances in machine learning algorithms to detect symptoms of altered gait, possibly corresponding to the emergence of neurodegenerative etiologies. However, while several claims of positive and accurate detection have been made in the recent literature, using a variety of sensors and algorithms, solutions are far from being realized in practice. This paper analyzes existing approaches to identify gaps inhibiting translation. Using a set of experiments across three Kinect-simulated and one real Parkinson's patient datasets, we highlight possible sources of errors and generalization failures in these approaches. Based on these observations, we propose our strong baseline called Asynchronous Multi-Stream Graph Convolutional Network (AMS-GCN) that can reliably differentiate multiple categories of pathological gaits across datasets.

cs.LG↗

arXiv2024

Learning to Play Video Games with Intuitive Physics Priors

Video game playing is an extremely structured domain where algorithmic decision-making can be tested without adverse real-world consequences. While prevailing methods rely on image inputs to avoid the problem of hand-crafting state space representations, this approach systematically diverges from the way humans actually learn to play games. In this paper, we design object-based input representations that generalize well across a number of video games. Using these representations, we evaluate an agent's ability to learn games similar to an infant - with limited world experience, employing simple inductive biases derived from intuitive representations of physics from the real world. Using such biases, we construct an object category representation to be used by a Q-learning algorithm and assess how well it learns to play multiple games based on observed object affordances. Our results suggest that a human-like object interaction setup capably learns to play several video games, and demonstrates superior generalizability, particularly for unfamiliar objects. Further exploring such methods will allow machines to learn in a human-centric way, thus incorporating more human-like learning benefits.

cs.LG↗

arXiv2023

Using Learnable Physics for Real-Time Exercise Form Recommendations

Good posture and form are essential for safe and productive exercising. Even in gym settings, trainers may not be readily available for feedback. Rehabilitation therapies and fitness workouts can thus benefit from recommender systems that provide real-time evaluation. In this paper, we present an algorithmic pipeline that can diagnose problems in exercise techniques and offer corrective recommendations, with high sensitivity and specificity in real-time. We use MediaPipe for pose recognition, count repetitions using peak-prominence detection, and use a learnable physics simulator to track motion evolution for each exercise. A test video is diagnosed based on deviations from the prototypical learned motion using statistical learning. The system is evaluated on six full and upper body exercises. These real-time recommendations, counseled via low-cost equipment like smartphones, will allow exercisers to rectify potential mistakes making self-practice feasible while reducing the risk of workout injuries.

cs.AI↗

arXiv2021

Stabilization of lifted hydrogen jet diffusion flame in a vitiated co-flow: effects of jet and coflow velocities, coflow temperature and mixing

The present paper reports on the numerical investigation of lifted turbulent jet flames with H2/N2 fuel issuing into a vitiated coflow of lean combustion products of H2/air using conditional moment closure method (CMC). A 2D axisymmetric formulation has been used for the predictions of fluid flow, while CMC equations are solved with detailed chemistry to represent the turbulence-chemistry interaction. Simulations are carried out for different coflow temperatures, jet and coflow velocities in order to investigate the impact on the flame lift-off height as well as on the flame stabilization. Furthermore, the role of conditional velocity models on the flame has also been investigated. In addition, the effect of mixing is investigated over a range of coflow temperatures and the stabilization mechanism is determined from the analysis of the transport budgets. It is found that the lift-off height is highly sensitive to the coflow temperature, while the predicted lift-off height using the mixing model constant, i.e., CΦ=4, is found to be the closest to the experimental results. For all the coflow temperatures, the balance is found between the chemical, axial convection and molecular diffusion terms while the contribution from axial and radial diffusion is negligible, thus indicating auto-ignition as the flame stabilization mechanism.

physics.flu-dyn↗

arXiv2016

Correlation between Fragility and the Arrhenius Crossover Phenomenon in Metallic, Molecular, and Network Liquids

We report the observation of a distinct correlation between the kinetic fragility index $m$ and the reduced Arrhenius crossover temperature $θ_A = T_A/T_g$ in various glass-forming liquids, identifying three distinguishable groups. In particular, for 11 glass-forming metallic liquids, we universally observe a crossover in the mean diffusion coefficient from high-temperature Arrhenius to low-temperature super-Arrhenius behavior at approximately $θ_A \approx 2$ which is in the stable liquid phases. In contrast, for fragile molecular liquids, this crossover occurs at much lower $θ_A \approx 1.4$ and usually in their supercooled states. The $θ_A$ values for strong network liquids spans a wide range higher than 2. Intriguingly, the high-temperature activation barrier $E_\infty$ is universally found to be $\sim 11\ k_B T_g$ and uncorrelated with the fragility or the reduced crossover temperature $θ_A$ for metallic and molecular liquids. These observations provide a way to estimate the low-temperature glassy characteristics ($T_g$ and $m$) from the high-temperature liquid quantities ($E_\infty$ and $θ_A$).

cond-mat.soft↗