Search Results for author:
Found 3 papers, 0 papers with code
Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models
Large-scale vision-language models (VLMs) have shown a strong zero-shot generalization capability on unseen-domain data.
Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Erasers
The former refrains the model from producing images associated with the target concept for any paraphrased or learned prompts, while the latter preserves its ability in generating images with non-target concepts.
DCT: Dynamic Compressive Transformer for Modeling Unbounded Sequence
In this paper, we propose Dynamic Compressive Transformer (DCT), a transformer-based framework for modeling the unbounded sequence.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
