How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation models (Spotlight)
Tomaso Trinci, Simone Magistri, Roberto Verdecchia, Andy Bagdanov

Foundation Model or Finetune? Evaluation of few-shot semantic segmentation for river pollution
Marga Don, Yuki M Asano

Improved Baselines for Data-efficient Perceptual Augmentation of LLMs (Spotlight)
Théophane Vallaeys, Mustafa Shukor, Matthieu Cord, Jakob Verbeek

Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis
Davide Bucciarelli, Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Architecture-Agnostic Unsupervised Gradient Regularization For Parameter-Efficient Transfer Learning
Wenjie Zhu, Yabin Zhang, Pengfei Wang, Xin Jin, Wenjun Zeng, Lei Zhang

Watt for What: Rethinking Deep Learning's Energy-Performance Relationship
Shreyank N Gowda, Xinyue Hao, Gen Li, Shashank Narayana Gowda, Laura Sevilla-Lara, Xiaobo Jin

DiT-Pruner: Pruning Diffusion Transformer Models for Text-to-Image Synthesis Using Human Preference Scores
Youngwan Lee, Yong-Ju Lee, Sung Ju Hwang

MagMax: Leveraging Model Merging for Seamless Continual Learning
Daniel Marczak, Bartlomiej Twardowski, Tomasz Trzcinski, Sebastian Cygert

Resource-efficient LLM Inference Serving with Heterogeneous GPUs
Zhi Zhou, Liao Jianxiong, Zhi Zhou

Language-only Efficient Prompt Learning for Zero-shot Composed Image Retrieval
Seongwon Lee, Yong-Ju Lee

Conditional Gradient-based Textual Inversion
Xi Wang, Vicky Kalogeiton