Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks151 from public data
- VACE: All-in-One Video Creation and Editing530
VACE is introduced, which enables users to perform Video tasks within an All-in-one framework for Creation and Editing, allowing it to handle arbitrary video synthesis tasks flexibly and enables diverse applications through versatile task combinations.
- RAMS-Trans: Recurrent Attention Multi-scale Transformer for Fine-grained Image Recognition152
The recurrent attention multi-scale transformer (RAMS-Trans), which uses the transformer's self-attention to recursively learn discriminative region attention in a multi- scale manner, and achieves state-of-the-art results on three benchmark datasets.
- 81
- Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety76
This survey provides a systematic review of current safety research on large models, covering Vision Foundation Models, Large Language Models, Vision-Language Pre-training models, Vision-Language Models, Diffusion Models, and large-model-powered Agents, and presents a comprehensive taxonomy of safety threats to these models.
- The SAM domain of the RhoGAP DLC1 binds EF1A1 to regulate cell migration62
This finding reveals a novel contribution of the SAM-EF1A1 interaction as a potentially important GAP-independent modulation of cell migration by DLC1.
- Bilateral Dependency Optimization54
Experiments show that BiDO achieves the state-of-the-art defense performance for a variety of datasets, classifiers, and MI attacks while suffering a minor classification-accuracy drop compared to the well-trained classifier with no defense, which lights up a novel road to defend against MI attacks.
- BadLabel: A Robust Perspective on Evaluating and Enhancing Label-Noise Learning49
A robust LNL method is proposed that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable and effectively improve the generalization performance of the model under various types of label noise.
- Towards Robust ResNet: A Small Step but a Giant Leap44
It is proved that a small step factor h can benefit the training robustness for back-propagation and the generalization robustness of the residual network by an explicit Euler method.
- 42
- 35
- 31
- 28
- 26
- 23
- Towards Adversarially Robust Deep Image Denoising22
It is found that existing DIDs are vulnerable to the adversarial noise generated by OBSATK, and an adversarial training strategy that jointly trains DIDs with adversarial and non-adversarial noisy data can recover high-quality clean images from real-world noise even without training on real noisy data.
- 22
- 20
- 18
- 18
- 17
- 16
- 16
- 15
- 15
- 15
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.