REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environmentsby Kaustubh Sridhar, Souradeep…
DEIM: DETR with Improved Matching for Fast Convergenceby Shihua Huang, Zhichao Lu, Xiaodong Cun, Yongjun…
AyutthayaAlpha: A Thai-Latin Script Transliteration Transformerby Davor Lauc, Attapol Rutherford, Weerin WongwarawipatrFirst submitted to arxiv…
Panoptic Diffusion Models: co-generation of images and segmentation mapsby Yinghan Long, Kaushik RoyFirst submitted to…
FCL-ViT: Task-Aware Attention Tuning for Continual Learningby Anestis Kaimakamidis, Ioannis PitasFirst submitted to arxiv on:…
AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstructionby Lingteng Qiu, Shenhao…
Optimization of Transformer heart disease prediction model based on particle swarm optimization algorithmby Jingyuan Yi,…
Quantifying the Reliability of Predictions in Detection Transformers: Object-Level Calibration and Image-Level Uncertaintyby Young-Jin Park,…
Command-line Risk Classification using Transformer-based Neural Architecturesby Paolo Notaro, Soroush Haeri, Jorge Cardoso, Michael GerndtFirst…
Multimodal Medical Disease Classification with LLaMA IIby Christian Gapp, Elias Tappeiner, Martin Welk, Rainer SchubertFirst…