Large Language Model
Semantic-Guided Multi-Attention Localization for Zero-Shot Learning
Yizhe Zhu, Jianwen Xie, Zhiqiang Tang, Xi Peng, Ahmed Elgammal
Neural Information Processing Systems http://nips.cc/
Bridge the Modality and Capability Gaps in Vision-Language Model Selection
To better reuse the VLM resource and fully leverage its potential on different zero-shot image classification tasks, a promising strategy is selecting appropriate Pre-Trained VLMs from the VLM Zoo, relying solely on the text data of the target dataset without access to the dataset's images.
Accelerating Blockwise Parallel Language Models with Draft Refinement T aehyeon Kim
First, we analyze token distributions generated across multiple prediction heads.
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
This dataset includes over 3.5 million documents with rich metadata, making it one of the most extensive collections of debate evidence.