Sentiment-oriented Transformer-based Variational Autoencoder Network for Live Video Commentingby Fengyi Fu, Shancheng Fang, Weidong Chen,…
AccidentBlip: Agent of Accident Warning based on MA-formerby Yihua Shao, Yeling Xu, Xinwei Long, Siyu…
MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generationby Kuan-Chieh Wang, Daniil Ostashev, Yuwei Fang,…
SNP: Structured Neuron-level Pruning to Preserve Attention Scoresby Kyunghwan Shim, Jaewoong Yun, Shinkook ChoiFirst submitted…
HumMUSS: Human Motion Understanding using State Space Modelsby Arnab Kumar Mondal, Stefano Alletto, Denis TomeFirst…
Unveiling the Misuse Potential of Base Large Language Models via In-Context Learningby Xiao Wang, Tianze…
Vision Augmentation Prediction Autoencoder with Attention Design (VAPAAD)by Yiqiao YinFirst submitted to arxiv on: 15…
Synergising Human-like Responses and Machine Intelligence for Planning in Disaster Responseby Savvas Papaioannou, Panayiotis Kolios,…
Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspectiveby Yuguang ShiFirst submitted to arxiv on:…
StreakNet-Arch: An Anti-scattering Network-based Architecture for Underwater Carrier LiDAR-Radar Imagingby Xuelong Li, Hongjun An, Guangying…