If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptionsby Reza Esfandiarpoor,…
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveyby Zeyu Han, Chao Gao, Jinyang Liu, Jeff…
FlexCap: Describe Anything in Images in Controllable Detailby Debidatta Dwibedi, Vidhi Jain, Jonathan Tompson, Andrew…
Linguacodus: A Synergistic Framework for Transformative Code Generation in Machine Learning Pipelinesby Ekaterina Trofimova, Emil…
Improving Dialogue Agents by Decomposing One Global Explicit Annotation with Local Implicit Multimodal Feedbackby Dong…
LookALike: Human Mimicry based collaborative decision makingby Rabimba Karanjai, Weidong ShiFirst submitted to arxiv on:…
Learning to Watermark LLM-generated Text via Reinforcement Learningby Xiaojun Xu, Yuanshun Yao, Yang LiuFirst submitted…
Improving Medical Multi-modal Contrastive Learning with Expert Annotationsby Yogesh Kumar, Pekka MarttinenFirst submitted to arxiv…
Logits of API-Protected LLMs Leak Proprietary Informationby Matthew Finlayson, Xiang Ren, Swabha SwayamdiptaFirst submitted to…
Navigating the Peril of Generated Alternative Facts: A ChatGPT-4 Fabricated Omega Variant Case as a…