Topic: decoding

A new speculative decoding method for language models has been proposed, aiming to accelerate inference by allowing more flexible verification rules beyond traditional token-matching criteria. This approach could potentially enhance efficiency without the need for extensive training, making it a significant advancement in LLM processing speed and resource utilization.

arxiv.org↗

Large Vision-Language Models (LVLMs), while effective in various tasks, can exhibit biased behavior due to social biases in their training data. Researchers propose a method called Counterfactual Ensemble Decoding to mitigate these biases, highlighting the importance of addressing fairness in AI systems.

arxiv.org↗