News

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 …

Links: OpenReview GitHub Abstract Current methods for detecting spurious correlations rely on data splits or error patterns, leaving many harmful …

Introduction Fine tuning is usually framed as “adaptation”. In practice, it can also manufacture shortcuts. A model can recognize the “right” object …

Links: arXiv GitHub Abstract Self-supervised representations excel at many vision and speech tasks, but their potential for audio-visual deepfake …

Links: arXiv GitHub Abstract Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation …

Links: arXiv Abstract Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to …