Amit Roy-Chowdhury
17 papers · 2019–2026 · 9 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (39) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
ποΈ
Keyword Collector
(98)
π
Renaissance Researcher
(5)
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
Top co-authors
Research topics
Artificial Intelligence
(11)
Deep Learning
(9)
Core AI Β· Artificial Intelligence
(9)
Machine Learning
(7)
Learning Types Β· Deep Learning
(7)
Computer Vision
(6)
Reinforcement Learning
(4)
Learning Types Β· Machine Learning
(4)
Analysis
(3)
Application Areas
(3)
Learning Paradigms
(3)
Applications
(2)
Core AI Β· Computer Vision
(2)
Methods
(2)
Models
(2)
Keywords
adversarial attack
(4)
vision-language model
(3)
adversarial perturbation
(2)
reinforcement learning
(2)
human pose estimation
(2)
black-box attack
(2)
occlusion handling
(2)
domain adaptation
(1)
imitation learning
(1)
image classification
(1)
in-context learning
(1)
language modeling
(1)
multimodal learning
(1)
video understanding
(1)
attention mechanism
(1)
video classification
(1)
few-shot learning
(1)
safety alignment
(1)
hierarchical reinforcement learning
(1)
query efficiency
(1)
Papers
CARD: Correlation Aware Restoration with Diffusion
CVPR 2026
A Certified Unlearning Approach without Access to Source Data
ICML 2025
AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments
CVPR 2025
HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models
EMNLP 2025
Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models
ICML 2025
Provable Benefits of Task-Specific Prompts for In-context Learning
AISTATS 2025
STRIDE: Single-Video Based Temporally Continuous Occlusion-Robust 3D Pose Estimation
WACV 2025
Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling
CoRL 2025
VOccl3D: A Video Benchmark Dataset for 3D Human Pose and Shape Estimation under real Occlusions
ICCV 2025
Can Textual Unlearning Solve Cross-Modality Safety Alignment?
EMNLP 2024
Selective Attention: Enhancing Transformer through Principled Context Control
NeurIPS 2024
AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments
NeurIPS 2022
Blackbox Attacks via Surrogate Ensemble Search
NeurIPS 2022
GAMA: Generative Adversarial Multi-Object Scene Attacks
NeurIPS 2022
Adversarial Attacks on Black Box Video Classifiers: Leveraging the Power of Geometric Transformations
NeurIPS 2021
Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
ECCV 2020
Learning from Trajectories via Subgoal Discovery
NeurIPS 2019