Search Results for author:
Found 3 papers, 3 papers with code
Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
It is noteworthy that the inference latency of the self-draft model may no longer be negligible compared to the large model, necessitating strategies to increase the token acceptance rate while minimizing the drafting steps of the small model.
Rethinking Optimization and Architecture for Tiny Language Models
Several design formulas are empirically proved especially effective for tiny language models, including tokenizer compression, architecture tweaking, parameter inheritance and multiple-round training.
CORE: Consistent Representation Learning for Face Forgery Detection
Specifically, we first capture the different representations with different augmentations, then regularize the cosine distance of the representations to enhance the consistency.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
