相关论文: Gradient-Sign Masking for Task Vector Transport Ac…

Graph-structured data is ubiquitous in the world which models complex relationships between objects, enabling various Web applications. Daily influxes of unlabeled graph data on the Web offer immense potential for these applications. Graph…

With too few samples or too many model parameters, overfitting can inhibit the ability to generalise predictions to new data. Within medical imaging, this can occur when features are incorrectly assigned importance such as distinct hospital…

Vision foundation models exhibit impressive power, benefiting from the extremely large model capacity and broad training data. However, in practice, downstream scenarios may only support a small model due to the limited computational…

Deep learning models are often deployed in downstream tasks that the training procedure may not be aware of. For example, models solely trained to achieve accurate predictions may struggle to perform well on downstream tasks because…

This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i.e., datasets with different object categories) or domains (i.e., datasets with the same categories but different environments) into one unified…

Deep feedforward and recurrent networks have achieved impressive results in many perception and language processing applications. This success is partially attributed to architectural innovations such as convolutional and long short-term…

Neural signed distance functions (SDFs) have shown remarkable capability in representing geometry with details. However, without signed distance supervision, it is still a challenge to infer SDFs from point clouds or multi-view images using…

Instruction tuning -- tuning large language models on instruction-output pairs -- is a promising technique for making models better adapted to the real world. Yet, the key factors driving the model's capability to understand and follow…

Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack…

The pretrain-transfer paradigm, which underpins the success of large language models (LLMs), has demonstrated the immense power of creating foundation models that learn generalizable representations from vast datasets. However, extending…

The last decade has witnessed the success of deep learning and the surge of publicly released trained models, which necessitates the quantification of the model functional distance for various purposes. However, quantifying the model…

Many large language model applications require conditioning on long contexts. Transformers typically support this by storing a large per-layer KV-cache of past activations, which incurs substantial memory overhead. A desirable alternative…

End-to-end optimization has achieved state-of-the-art performance on many specific problems, but there is no straight-forward way to combine pretrained models for new problems. Here, we explore improving modularity by learning a post-hoc…

Deep neural networks are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations to the benign input. After achieving nearly 100% attack success rates in white-box setting, more focus is shifted to…

Communication has been seen as a significant bottleneck in industrial applications over large-scale networks. To alleviate the communication burden, sign-based optimization algorithms have gained popularity recently in both industrial and…

A foundation model like GPT elicits many emergent abilities, owing to the pre-training with broad inclusion of data and the use of the powerful Transformer architecture. While foundation models in natural languages are prevalent, can we…

Graph neural networks (GNNs) is widely used to learn a powerful representation of graph-structured data. Recent work demonstrates that transferring knowledge from self-supervised tasks to downstream tasks could further improve graph…

Large language models have demonstrated promising performance across various software engineering tasks. While fine-tuning is a common practice to adapt these models for downstream tasks, it becomes challenging in resource-constrained…

Availability of labelled data is the major obstacle to the deployment of deep learning algorithms for computer vision tasks in new domains. The fact that many frameworks adopted to solve different tasks share the same architecture suggests…

We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions. Unlike conventional long-tail classifiers which operate on converged - and possibly…