Related papers: Toward Privileged Foundation Models:LUPI for Accel…

Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of inefficient data utilization. It relies on a single…

Federated learning (FL) is a popular privacy-preserving paradigm that enables distributed clients to collaboratively train models with a central server while keeping raw data locally. In practice, distinct model architectures, varying data…

Multimodal pretraining is effective for building general-purpose representations, but in many practical deployments, only one modality is heavily used during downstream fine-tuning. Standard pretraining strategies treat all modalities…

Federated learning (FL) is recently surging as a promising decentralized deep learning (DL) framework that enables DL-based approaches trained collaboratively across clients without sharing private data. However, in the context of the…

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…

Hyperspectral imaging (HSI) enables detailed land cover classification, yet low spatial resolution and sparse annotations pose significant challenges. We present a label-efficient framework that leverages spatial features from a frozen…

Recent studies have shown that large language models (LLMs), when customized with post-training on tabular data, can acquire general tabular in-context learning (TabICL) capabilities. These models are able to transfer effectively across…

Philosophy-informed machine learning (PhIML) directly infuses core ideas from analytic philosophy into ML model architectures, objectives, and evaluation protocols. Therefore, PhIML promises new capabilities through models that respect…

We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to…

When learning new tasks in a sequential manner, deep neural networks tend to forget tasks that they previously learned, a phenomenon called catastrophic forgetting. Class incremental learning methods aim to address this problem by keeping a…

Federated learning (FL) is a paradigm where many clients collaboratively train a model under the coordination of a central server, while keeping the training data locally stored. However, heterogeneous data distributions over different…

Pre-trained model-based continual learning (PTMCL) has garnered growing attention, as it enables more rapid acquisition of new knowledge by leveraging the extensive foundational understanding inherent in pre-trained model (PTM). Most…

In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Diversity among in-context exemplars. InSQuAD achieves this…

Investigating better ways to reuse the released pre-trained language models (PLMs) can significantly reduce the computational cost and the potential environmental side-effects. This paper explores a novel PLM reuse paradigm, Knowledge…

Positive-unlabeled (PU) learning addresses binary classification when only a set of labeled positives is available alongside a pool of unlabeled samples drawn from a mixture of positives and negatives. Existing PU methods typically require…

Hierarchical reinforcement learning (HRL) leverages temporal abstraction to efficiently tackle complex long-horizon tasks. However, HRL often collapses because the continual updates of the low-level primitive make earlier sub-goals issued…

We present a semi-supervised fine-tuning framework for foundation models that utilises mutual information decomposition to address the challenges of training for a limited amount of labelled data. Our approach derives two distinct lower…

Although large language models (LLMs) have demonstrated remarkable capabilities in recent years, the potential of information theory (IT) to enhance LLM development remains underexplored. This paper introduces the information theoretic…

We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods. TabPFN performs…

Federated learning client selection is crucial for determining participant clients while balancing model accuracy and communication efficiency. Existing methods have limitations in handling data heterogeneity, computational burdens, and…