Related papers: Transporting Task Vectors across Different Archite…

Adapting neural networks to new tasks typically requires task-specific fine-tuning, which is time-consuming and reliant on labeled data. We explore a generative alternative that produces task-specific parameters directly from task identity,…

Transfer in reinforcement learning refers to the notion that generalization should occur not only within a task but also across tasks. We propose a transfer framework for the scenario where the reward function changes between tasks but the…

The growing use of permanent monitoring systems has increased data availability, offering new opportunities for structural assessment but also posing scalability challenges, especially across large bridge networks. Managing multiple…

We explore multitask models for neural translation of speech, augmenting them in order to reflect two intuitive notions. First, we introduce a model where the second task decoder receives information from the decoder of the first task,…

We propose a new architecture called Memory-Augmented Encoder-Solver (MAES) that enables transfer learning to solve complex working memory tasks adapted from cognitive psychology. It uses dual recurrent neural network controllers, inside…

Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence…

For years the model performance in machine learning obeyed a power-law relationship with the model size. For the consideration of parameter efficiency, recent studies focus on increasing model depth rather than width to achieve better…

In the burgeoning field of intelligent transportation systems, enhancing vehicle-driver interaction through facial attribute recognition, such as facial expression, eye gaze, age, etc., is of paramount importance for safety,…

Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works on neural network parameterisations, such as $\mu$P, have enabled transfer of optimal global hyperparameters across…

To optimize large Transformer model training, both efficient parallel computing and advanced data management are indispensable. However, current methods often assume a stable and uniform training workload, neglecting data-induced…

Identifying beneficial tasks to transfer from is a critical step toward successful intermediate-task transfer learning. In this work, we experiment with 130 source-target task combinations and demonstrate that the transfer performance…

Despite the remarkable success of text-to-image diffusion models, their output of a single, flattened image remains a critical bottleneck for professional applications requiring layer-wise control. Existing solutions either rely on…

Transfer learning is a popular technique for improving the performance of neural networks. However, existing methods are limited to transferring parameters between networks with same architectures. We present a method for transferring…

Training autonomous agents that can learn new tasks from only a handful of demonstrations is a long-standing problem in machine learning. Recently, transformers have been shown to learn new language or vision tasks without any weight…

Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in…

Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger…

Meta-learning optimizes the hyperparameters of a training procedure, such as its initialization, kernel, or learning rate, based on data sampled from a number of auxiliary tasks. A key underlying assumption is that the auxiliary tasks,…

Large AI models have been widely adopted in wireless communications for channel modeling, beamforming, and resource optimization. However, most existing efforts remain limited to single-modality inputs and channel-specific objec- tives,…

When finetuning multiple tasks altogether, it is important to carefully weigh them to get a good performance, but searching for good weights can be difficult and costly. Here, we propose to aid the search with fast previews to quickly get a…

Text-based 3D human motion editing is a critical yet challenging task in computer vision and graphics. While training-free approaches have been explored, the recent release of the MotionFix dataset, which includes source-text-motion…