VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extractionby Khai Phan Tran, Wen Hua, Xue…
CognitionCapturer: Decoding Visual Stimuli From Human EEG Signal With Multimodal Informationby Kaifan Zhang, Lihuo He,…
Is Contrastive Distillation Enough for Learning Comprehensive 3D Representations?by Yifan Zhang, Junhui HouFirst submitted to…
Uniform Discretized Integrated Gradients: An effective attribution based method for explaining large language modelsby Swarnava…
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Modelby Qianhan Feng, Wenshuo Li, Tong Lin,…
On the Fairness, Diversity and Reliability of Text-to-Image Generative Modelsby Jordan Vice, Naveed Akhtar, Richard…
Do LLMs “know” internally when they follow instructions?by Juyeon Heo, Christina Heinze-Deml, Oussama Elachqar, Shirley…
A new approach for fine-tuning sentence transformers for intent classification and out-of-scope detection tasksby Tianyi…
Exploring Efficient Foundational Multi-modal Models for Video Summarizationby Karan Samel, Apoorva Beedu, Nitish Sontakke, Irfan…
Vector-ICL: In-context Learning with Continuous Vector Representationsby Yufan Zhuang, Chandan Singh, Liyuan Liu, Jingbo Shang,…