LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?by Yuchi Wang, Shuhuai…
From a Lossless (~1.5:1) Compression Algorithm for Llama2 7B Weights to Variable Precision, Variable Range,…
Exploring the Role of Token in Transformer-based Time Series Forecastingby Jianqi Zhang, Jingyao Wang, Chuxiong…
Mitigating Hallucination in Abstractive Summarization with Domain-Conditional Mutual Informationby Kyubyung Chae, Jaepill Choi, Yohan Jo,…
Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You…
CATP: Cross-Attention Token Pruning for Accuracy Preserved Multimodal Model Inferenceby Ruqi Liao, Chuqing Zhao, Jin…
LLM2Vec: Large Language Models Are Secretly Powerful Text Encodersby Parishad BehnamGhader, Vaibhav Adlakha, Marius Mosbach,…
Band-Attention Modulated RetNet for Face Forgery Detectionby Zhida Zhang, Jie Cao, Wenkui Yang, Qihang Fan,…
Event Extraction in Basque: Typologically motivated Cross-Lingual Transfer-Learning Analysisby Mikel Zubillaga, Oscar Sainz, Ainara Estarrona,…
GvT: A Graph-based Vision Transformer with Talking-Heads Utilizing Sparsity, Trained from Scratch on Small Datasetsby…