Abstract Low-Rank Adaptation (LoRA), which updates the dense neural network layers with
pluggable low-rank matrices, is one of the best performed parameter efficient fine-tuning …

Building general-purpose robots that operate seamlessly in any environment, with any
object, and utilizing various skills to complete diverse tasks has been a long-standing goal in …

Vision and Language (VL) models offer an effective method for aligning representation
spaces of images and text allowing for numerous applications such as cross-modal retrieval …

Large-scale pre-trained Vision & Language (VL) models have shown remarkable
performance in many applications, enabling replacing a fixed set of supported classes with …

This study addresses the Domain-Class Incremental Learning problem, a realistic but
challenging continual learning scenario where both the domain distribution and target …

Vision language models (VLM) have demonstrated remarkable performance across various
downstream tasks. However understanding fine-grained visual-linguistic concepts such as …

Multimodal foundation models serve numerous applications at the intersection of vision and
language. Still, despite being pretrained on extensive data, they become outdated over time …

Recent work has demonstrated a remarkable ability to customize text-to-image diffusion
models to multiple fine-grained concepts in a sequential (ie continual) manner while only …

Vehicle-to-everything (V2X) perception is an innovative technology that enhances vehicle
perception accuracy, thereby elevating the security and reliability of autonomous systems …

Compositionality facilitates the comprehension of novel objects using acquired concepts
and the maintenance of a knowledge pool. This is particularly crucial for continual learners …