News

Links: arXiv Abstract We study how visual information is routed in vision-language models (VLMs). Using causal patching on controlled synthetic and …

Links: arXiv Abstract The proliferation of text-to-speech (TTS) systems capable of generating realistic synthetic speech poses growing challenges for …

Links: arXiv Abstract Can a dataset be recognized from the spurious correlations it induces during training? We argue that datasets leave …

Links: arXiv Abstract Equivariant neural networks encode geometric symmetries by construction, yet they are often difficult to optimize and can …

Links: arXiv GitHub Abstract Classifying protein topology is essential for deciphering biological function, but progress is held back by the lack of …

Links: arXiv Abstract Learning from a sequence of interactions, as soon as observations are perceived and acted upon, without explicitly storing them, …

Links: arXiv Abstract Continual learning (CL) studies how models acquire tasks sequentially while retaining previously learned knowledge. Despite …

Links: arXiv Abstract Streaming Continual Learning (CL) typically converts a continuous stream into a sequence of discrete tasks through temporal …

Links: arXiv Abstract Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by …