KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head.
CoRR, 2024
Does Continual Learning = Catastrophic Forgetting?
CoRR, 2021
Transformer-Based Neural Text Generation with Syntactic Guidance.
CoRR, 2020
Recognizing Objects From Any View With Object and Viewer-Centered Representations.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020