2025
Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models.
CoRR, April, 2025

Directional Gradient Projection for Robust Fine-Tuning of Foundation Models.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Robustness under distribution shifts in computer vision.
PhD thesis, 2024

Continual Adaptation of Vision Transformers for Federated Learning.
Trans. Mach. Learn. Res., 2024

Grounding Descriptions in Images informs Zero-Shot Visual Recognition.
CoRR, 2024

Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
HePCo: Data-Free Heterogeneous Prompt Consolidation for Continual Federated Learning.
CoRR, 2023

Fast Trainable Projection for Robust Fine-tuning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Trainable Projected Gradient Method for Robust Fine-Tuning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

A Closer Look at Rehearsal-Free Continual Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
An Intelligence Architecture for Grounded Language Communication with Field Robots.
Field Robotics, March, 2022

FedFOR: Stateless Heterogeneous Federated Learning with First-Order Regularization.
CoRR, 2022

A Closer Look at Rehearsal-Free Continual Learning.
CoRR, 2022

Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Striking the Right Balance: Recall Loss for Semantic Segmentation.
Proceedings of the 2022 International Conference on Robotics and Automation, 2022

Open-Set Semi-Supervised Object Detection.
Proceedings of the Computer Vision - ECCV 2022, 2022

2021
Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data.
CoRR, 2021

Enhancing Multi-Robot Perception via Learned Data Association.
CoRR, 2021

A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Overcoming Obstructions via Bandwidth-Limited Multi-Agent Spatial Handshaking.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2021

2020
Posterior Re-calibration for Imbalanced Datasets.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

UNO: Uncertainty-aware Noisy-Or Multimodal Fusion for Unanticipated Input Degradation.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

Who2com: Collaborative Perception via Learnable Handshake Communication.
Proceedings of the 2020 IEEE International Conference on Robotics and Automation, 2020

When2com: Multi-Agent Perception via Communication Graph Grouping.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019
Image Captioning with Compositional Neural Module Networks.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019