Describe Anything: Detailed Localized Image and Video Captioning.
,
,
,
,
,
,
,
,
,
,
CoRR, April, 2025
Learning Adaptive Parallel Reasoning with Language Models.
CoRR, April, 2025
TULIP: Towards Unified Language-Image Pretraining.
CoRR, March, 2025
Atlas: Multi-Scale Attention Improves Long Context Image Modeling.
CoRR, March, 2025
LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models.
Trans. Mach. Learn. Res., 2024
Rethinking Patch Dependence for Masked Autoencoders.
CoRR, 2024
LLM-grounded Video Diffusion Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Self-Correcting LLM-Controlled Diffusion Models.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Unsupervised Universal Image Segmentation.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Q-Diffusion: Quantizing Diffusion Models.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Improving Unsupervised Video Object Segmentation with Motion-Appearance Synergy.
CoRR, 2022
Debiased Learning from Naturally Imbalanced Pseudo-Labels for Zero-Shot and Semi-Supervised Learning.
CoRR, 2022
Unsupervised Selective Labeling for More Effective Semi-supervised Learning.
Proceedings of the Computer Vision - ECCV 2022, 2022
Debiased Learning from Naturally Imbalanced Pseudo-Labels.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Data-Centric Semi-Supervised Learning.
CoRR, 2021
Long-tailed Recognition by Routing Diverse Distribution-Aware Experts.
Proceedings of the 9th International Conference on Learning Representations, 2021
Unsupervised Visual Attention and Invariance for Reinforcement Learning.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021