2 papers
cs.CV2024
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
Rohan Choudhury, Guanglei Zhu, Sihan Liu +3
Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninf…
cs.CL2024
Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement
Wenda Xu, Guanglei Zhu, Xuandong Zhao +3
Recent studies show that large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We discovered that such a contrary i…