19 citations · 27 across the 11 of their papers we have counts for
12 papers
DepthWorld: 3D World Model for Robot Manipulation
Jai Bardhan, Josef Sivic, Vladimir Petrik
World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and planning. All of these uses depe…
Curve Skeletonization in Continuous domain for Meshes and Point Clouds
Jai Bardhan, Ramya Hebbalaguppe, Aravind Udupa
Advancements in 3D curve skeletonization are accelerating progress across a wide range of applications. However, developing robust skeletonization algorithms that capture intricate…
Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning
Jai Bardhan, Patrik Drozdik, Josef Sivic +1
Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks tha…
REALM: A Real-to-Sim Validated Benchmark for Generalization in Robotic Manipulation
Martin Sedlacek, Pavlo Yefanov, Georgy Ponimatkin +7
Vision-Language-Action (VLA) models empower robots to understand and execute tasks described by natural language instructions. However, a key challenge lies in their ability to gen…
Refine and Align: Confidence Calibration through Multi-Agent Interaction in VQA
Ayush Pandey, Jai Bardhan, Ishita Jain +3
In the context of Visual Question Answering (VQA) and Agentic AI, calibration refers to how closely an AI system's confidence in its answers reflects their actual correctness. This…
Tagging fully hadronic exotic decays of the vectorlike quark using a graph neural network
Jai Bardhan, Tanumoy Mandal, Subhadip Mitra +2
Following up on our earlier study in [J. Bardhan et al., Machine learning-enhanced search for a vectorlike singlet B quark decaying to a singlet scalar or pseudoscalar, Phys. Rev.…
HEP-JEPA: A foundation model for collider physics using joint embedding predictive architecture
Jai Bardhan, Radhikesh Agrawal, Abhiram Tilak +2
We present a transformer architecture-based foundation model for tasks at high-energy particle colliders such as the Large Hadron Collider. We train the model to classify jets usin…
Constructing sensible baselines for Integrated Gradients
Jai Bardhan, Cyrin Neeraj, Mihir Rawat +1
Machine learning methods have seen a meteoric rise in their applications in the scientific community. However, little effort has been put into understanding these "black box" model…
Loss function to optimise signal significance in particle physics
Jai Bardhan, Cyrin Neeraj, Subhadip Mitra +1
We construct a surrogate loss to directly optimise the significance metric used in particle physics. We evaluate our loss function for a simple event classification task using a li…
ReMOVE: A Reference-free Metric for Object Erasure
Aditya Chandrasekar, Goirik Chakrabarty, Jai Bardhan +2
We introduce , a novel reference-free metric for assessing object erasure efficacy in diffusion-based image editing models post-generation. Unlike existing measure…
Unsupervised and lightly supervised learning in particle physics
Jai Bardhan, Tanumoy Mandal, Subhadip Mitra +2
We review the main applications of machine learning models that are not fully supervised in particle physics, i.e., clustering, anomaly detection, detector simulation, and unfoldin…
Machine learning-enhanced search for a vectorlike singlet quark decaying to a singlet scalar or pseudoscalar
Jai Bardhan, Tanumoy Mandal, Subhadip Mitra +1
The presence of a new decay mode relaxes the current mass exclusion limits on vectorlike quarks considerably. We consider the case of a weak-singlet vectorlike quark that can d…