Related papers: Specialized Foundation Models Struggle to Beat Sup…

When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on…

Recent empirical studies have explored the idea of continuing to train a model at test-time for a given task, known as test-time training (TTT), and have found it to yield significant performance improvements. However, there is limited…

Driven by the recent advances in deep learning methods and, in particular, by the development of modern self-supervised learning algorithms, increased interest and efforts have been devoted to build foundation models (FMs) for medical…

Foundation models for tabular data, such as the Tabular Prior-data Fitted Network (TabPFN), are pre-trained on a massive number of synthetic datasets generated by structural causal models (SCM). They leverage in-context learning to offer…

Federated learning (FL) has emerged as a promising paradigm for enabling the collaborative training of models without centralized access to the raw data on local devices. In the typical FL paradigm (e.g., FedAvg), model weights are sent to…

Large pre-trained models have been vital in recent advancements in domains like language and vision, making model training for individual downstream tasks more efficient and provide superior performance. However, tackling time-series…

Artificial intelligence (AI) has emerged as a pivotal enabler for next-generation wireless communication systems. However, conventional AI-based models encounter several limitations, such as heavy reliance on labeled data, limited…

Recent work suggests that large-scale, multi-animal modeling can significantly improve neural recording analysis. However, for functional calcium traces, existing approaches remain task-specific, limiting transfer across common neuroscience…

Recent advances in machine learning have made revolutionary breakthroughs in computer games, image and natural language understanding, and scientific discovery. Foundation models and large-scale language models (LLMs) have recently achieved…

Over the past decades, computer-aided diagnosis tools for breast cancer have been developed to enhance screening procedures, yet their clinical adoption remains challenged by data variability and inherent biases. Although foundation models…

Recently, several studies have reported on the fine-tuning of foundation models for image-text modeling in the field of medicine, utilizing images from online data sources such as Twitter and PubMed. Foundation models are large, deep…

The recent development of foundation models for time series data has generated considerable interest in using such models across a variety of applications. Although foundation models achieve state-of-the-art predictive performance, their…

Foundation models pretrained on diverse data at scale have demonstrated extraordinary capabilities in a wide range of vision and language tasks. When such models are deployed in real world environments, they inevitably interface with other…

Foundation models (FMs) have shown remarkable capabilities in generalized intelligence, multimodal understanding, and adaptive learning across a wide range of domains. However, their deployment in harsh or austere environments --…

Natural products, as metabolites from microorganisms, animals, or plants, exhibit diverse biological activities, making them crucial for drug discovery. Nowadays, existing deep learning methods for natural products research primarily rely…

Since the emergence of the ImageNet dataset, the pretraining and fine-tuning approach has become widely adopted in computer vision due to the ability of ImageNet-pretrained models to learn a wide variety of visual features. However, a…

Foundation Models (FMs) such as GPT-4 encoded with vast knowledge and powerful emergent abilities have achieved remarkable success in various natural language processing and computer vision tasks. Grounding FMs by adapting them to…

Foundation models (FMs), including large language models, have become increasingly popular due to their wide-ranging applicability and ability to understand human-like semantics. While previous research has explored the use of FMs in…

The increasing realism and accessibility of deepfakes have raised critical concerns about media authenticity and information integrity. Despite recent advances, deepfake detection models often struggle to generalize beyond their training…

The intersection of Foundation Model (FM) and Federated Learning (FL) presents a unique opportunity to unlock new possibilities for real-world applications. On the one hand, FL, as a collaborative learning paradigm, help address challenges…