Repeat After Me: Transformers are Better than State Space Models at Copying
Paper
•
2402.01032
•
Published
•
24
Interesting Papers
-
-
Craw4LLM: Efficient Web Crawling for LLM Pretraining
Paper • 2502.13347 • Published • 30 -
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation
Paper • 2502.20583 • Published • 13 -
The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable High-Accuracy Authorship Attribution
Paper • 2510.10493 • Published • 2 -
Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs
Paper • 2510.09201 • Published • 49