Despite being responsible for state-of-the-art results in several computer vision and natural
language processing tasks, neural networks have faced harsh criticism due to some of their …

Widely used alignment techniques, such as reinforcement learning from human feedback
(RLHF), rely on the ability of humans to supervise model behavior-for example, to evaluate …

Vision Transformers convert images to sequences by slicing them into patches. The size of
these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher …

Large Language Models (LLMs) have revolutionized natural language processing tasks with
remarkable success. However, their formidable size and computational demands present …

Most cross-device federated learning (FL) studies focus on the model-homogeneous setting
where the global server model and local client models are identical. However, such …

Recent work in natural language processing (NLP) has yielded appealing results from
scaling model parameters and training data; however, using only scale to improve …

Recent neural methods for vehicle routing problems always train and test the deep models
on the same instance distribution (ie, uniform). To tackle the consequent cross-distribution …

In recent years, larger and deeper models are springing up and continuously pushing state-
of-the-art (SOTA) results across various fields like natural language processing (NLP) and …

Federated learning is an important privacy-preserving multi-party learning paradigm,
involving collaborative learning with others and local updating on private data. Model …

Abstract Human-Object Interaction (HOI) detection aims to localize human-object pairs and
recognize their interactions. Recently, Contrastive Language-Image Pre-training (CLIP) has …