Long Mai
- Papers
- 8
Cite
Notes
Only stored in your browser.
Authored papers
8TokenDial: Continuous Attribute Control in Text-to-Video via Spatiotemporal Token Offsets
arXiv 2026
Improving Zero-Shot Object-Level Change Detection by Incorporating Visual Correspondence
arXiv 2025
TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models
ICCV 2025
Double Trouble: How to not explain a text classifier's decisions using counterfactuals synthesized by masked language models?
arXiv 2021
Compositional Sketch Search
arXiv 2021
An Internal Learning Approach to Video Inpainting
an-internal-learning-approach-to-video-1
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
arXiv 2019
Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects
strike-with-a-pose-neural-networks-are-easily-1
Affiliations
Frequent co-authors
10from 8 papers