Disentangling Where and When
Factored spatio-temporal explanations for video action recognition: separating where the evidence sits in each frame from when it matters across the clip, so each can be read on its own.
New · NeurIPS 2026 & IJCLR 2026 papers
I build visual intelligence that explains itself.
Researching interpretable machine learning for complex scenes, where computer vision, logical reasoning, and human understanding meet.
INTERPRETABILITY
HUMAN × AI
VISUAL REASONING
RELATIONAL LEARNING
01
Selected work
Research made tangible.
A selection of projects spanning video and logical explanations, neuro-symbolic learning, content-based retrieval, aerial imagery, and learning theory.
Probabilistic Logic Programs, Guided by Language Models
Learning probabilistic logic programs with language models that propose clauses and functional gradients that guide which ones are kept and how they are weighted.
Explainable Artificial Intelligence
Research toward systems that communicate why they made a decision—not only what they predicted.
Program ↗
Resilience of Deep Network Interpretations
Investigating how model interpretations behave under perturbations in satellite and aerial imagery.
Thesis ↗
Jersey Number Reader
A dual-head joint-learning architecture for reading two-digit jersey numbers from imagery.
Code ↗
Bi-temporal Change Detection
Siamese-style neural architectures for finding meaningful change across paired satellite images.
Code ↗
Generalization Bounds for Metric Learning
Exploring Rademacher complexity and matrix norms to characterize generalization in metric and similarity learning.
Probabilistically Checkable Proofs
An accessible exploration of PCPs, their surprising power, and the weak PCP theorem.
02
Publications
Ideas, peer reviewed.
Papers across interpretable vision, logical and neuro-symbolic explanations, image retrieval, and remote sensing, from NeurIPS and AAAI to IEEE journals.
- Publications
- 21
- Latest venues
- NeurIPS · IJCLR
- Years active
- 2018–2026
Disentangling Where and When: Factored Spatio-Temporal Explanations for Video Action Recognition
Link soon
Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models
Link soon
GLARE: A Natural Language Interface for Querying Global Explanations
Local-to-Global Logical Explanations for Deep Vision Models
Beyond Local Explanations: A Framework for Global Concept-Based Interpretation in Image Classification
Interactive Mars Image Content-Based Search with Interpretable Machine Learning
Global Explanations for Image Classifiers
Content-based Search of Large Image Archives at PDS Imaging Node
X-MIR: EXplainable Medical Image Retrieval
XAITK: The Explainable AI Toolkit
Explainable, Interactive Content-Based Image Retrieval
Resilience and Plasticity of Deep Network Interpretations for Aerial Imagery
Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanations
Visualizing the Resilience of Deep Convolutional Network Interpretations
Explainability for Content-Based Image Retrieval
Training Deep Networks for Patch-Based Search in Satellite Imagery
Visualizing Resiliency of Deep Convolutional Network Interpretations for Aerial Imagery
Resilience and Self-Healing of Deep Convolutional Object Detectors
Siamese Network with Multi-Level Features for Patch-Based Change Detection in Satellite Imagery
Aerial-CAM: Salient Structures and Textures in Network Class Activation Maps of Aerial Imagery
Deep Learning for Object Detection and Classification in Satellite Imagery
03
Journey
Built across disciplines.
From electronics and imaging science to applied computer vision, explainability, and planetary data.
Education
B.E. in Electronics & Communication Engineering
Global Academy of Technology · Bangalore, India
Education + Research
M.S. in Computer Engineering
Rochester Institute of Technology · Center for Imaging Science
Industry research
R&D Engineer, Computer Vision
Kitware · New York
Planetary AI
Graduate Research Fellow
NASA JPL, Caltech · Machine Learning & Instrument Autonomy Group
Doctoral research
Ph.D., Electrical Engineering & Computer Science
Oregon State University · advised by Prof. Prasad TadepalliAbout
Rigorous research.
Creative curiosity.
My work uses computer vision and machine learning to find patterns, inspect model behavior, and turn opaque predictions into understandable interactions. I enjoy entering unfamiliar research spaces and building on existing ideas with practical, creative improvements.
Beyond research, I care about access to education and minority empowerment. Photography and music shape how I observe, frame, and communicate technical ideas.
Interpretable MLHuman–AI InteractionInteractive MLComputer VisionImage RetrievalRemote Sensing
“Be bold enough to follow the obvious, but have the tenacity to go after the behemoth.”
Personal maxim
04
Field notes
Milestones & moments.
A selected stream of talks, awards, papers, and community work. Hover or swipe to browse.
Paper accepted at NeurIPS 2026
Disentangling Where and When: factored spatio-temporal explanations for video action recognition.
IJCLR 2026 in Valencia
Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models.
GLARE preprint released
A natural-language interface for querying global explanations of image classifiers.
Program Committee: NeurIPS 2026 & ICLR 2027
Reviewing for NeurIPS 2026, ICLR 2027, and AAAI 2024–2026.
Logical explanations at IJCLR 2025
Local-to-Global Logical Explanations for Deep Vision Models, presented in Guildford, UK.
Best poster, 1st place at AI Week
Won first place for best poster at Oregon State University’s AI Week two years running.
Oral presentation at IAAI 2024
Presented interactive Mars image search research in Vancouver.
IAAI paper accepted
Interactive Mars Image Content-Based Search with Interpretable Machine Learning.
AAAI 2024 Workflow Chair
Handled workflow responsibilities for the AAAI 2024 conference in Vancouver, Canada.
“Most Impactful” poster
Rule-Based Explanations for Deep Networks recognized at the PPI Center meeting.
NASA JPL Graduate Research Fellow
Interpretable ML for the Planetary Data System with the Machine Learning & Instrument Autonomy group.
Collaborator perspective
Trusted to go beyond the obvious.
“He combines a deep knowledge of machine learning techniques and research with an unparalleled willingness to branch out and try new things.”
“Bhavan knows the foundations clearly enough to understand subtle mistakes and is capable enough to appreciate subtle but breakthrough ideas.”
“It’s rare to come across individuals who excel in different domains, and Bhavan is indeed a rare find.”
Contact
Let’s make opaque systems a little more understandable.
For research collaborations, speaking, reviewing, or thoughtful conversations about visual intelligence.