The field of deep learning has witnessed significant progress, particularly in computer vision
(CV), natural language processing (NLP), and speech. The use of large-scale models …

Large Language Models (LLMs) have been successful in mathematical reasoning tasks
such as formal theorem proving when integrated with interactive proof assistants like Lean …

Table-based fact verification focuses on determining the truthfulness of statements by cross-
referencing data in tables. This task is challenging due to the complex interactions inherent …

As a promising paradigm to collaboratively train models with decentralized data, Federated
Learning (FL) can be exploited to fine-tune Large Language Models (LLMs). While LLMs …

The rise and proliferation of Artificial Intelligence (AI) technologies are bringing
transformative changes to various sectors, signaling a new era of innovation in fields as …

Pipeline parallelism is a key mechanism to ensure the performance of large model serving
systems. These systems need to deal with unpredictable online workloads with low latency …

Efficiency is crucial in deep learning tasks and has garnered significant attention in green
deep learning research field. However, existing methods often sacrifice efficiency for slight …

Self-supervised learning (SSL) techniques have recently produced outstanding results in
learning visual representations from unlabeled videos. Despite the importance of motion in …

In this paper, we introduce** harmonic loss** as an alternative to the standard cross-entropy
loss for training neural networks and large language models (LLMs). Harmonic loss enables …

The rapid evolution of Large Language Models (LLMs) has enabled the industry to develop
various AI-based services. Instruction tuning is considered essential in adapting foundation …