Scholar
Apratim Bhattacharyya
Google Scholar ID: SKb4VyUAAAAJ
Qualcomm AI Research
Citations & Impact
Citations
1,328
H-index
13
i10-index
14
Publications
20
Co-authors
25
list available
Publications
Resume (English only)
Academic Achievements
- Paper: Look, Remember and Reason: Visual Reasoning with Grounded Rationales, Technical Report, 2023.
- Paper: KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients, ECCV 2022 (oral).
- Paper: Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers, CVPR 2021.
- Paper: Normalizing Flows with Multi-scale Autoregressive Priors, CVPR 2020.
- Paper: Haar Wavelet based Block Autoregressive Flows for Trajectories, German Conference on Pattern Recognition 2020 (oral).
- Paper: Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning, USENIX Security Symposium 2020.
- Paper: Conditional Flow Variational Autoencoders for Structured Sequence Prediction, BDL@NeurIPS’19 and ML4AD@NeurIPS’19 (oral).
- Paper: Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods, ICLR 2019.
- Paper: Accurate and Diverse Sampling of Sequences based on a “Best of Many” Sample Objective, CVPR 2018 (oral).
- Paper: Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty, CVPR 2018.
- Paper: Long-Term Image Boundary Prediction, AAAI 2018.
- Paper: Efficiently Summarising Event Sequences with Rich Interleaving Patterns, SDM 2017.
Background
- Research interests: Large Language Models, Generative Models, and Bayesian Inference. Currently, a Machine Learning Researcher at Qualcomm AI Research.
Miscellany
- No detailed personal interests provided.
