Related papers: Finetune Once: Decoupling General & Domain Learnin…
Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical application of…
Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra…
Efficient beam alignment is fundamental to high-throughput and reliable connectivity in Vehicle-to-Everything (V2X) systems. However, conventional beam management in dynamic vehicular topologies incurs prohibitive alignment overhead and…
The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this…
This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…
Many continual-learning methods modify gradients upstream (e.g., projection, penalty rescaling, replay mixing) while treating Adam as a neutral backend. We show this composition has a hidden failure mode. In a high-overlap, non-adaptive…
Unsupervised Domain Adaptation (UDA) endeavors to adjust models trained on a source domain to perform well on a target domain without requiring additional annotations. In the context of domain adaptive semantic segmentation, which tackles…
Multi-task learning (MTL), instruction tuning, and prompting have recently been shown to improve the generalizability of large language models to new tasks. However, the benefits of such methods are less well-documented in smaller language…
Recently, Deep Neural Networks (DNNs) have recorded great success in handling medical and other complex classification tasks. However, as the sizes of a DNN model and the available dataset increase, the training process becomes more complex…
Most existing image keypoint detection and description methods rely on datasets with accurate pose and depth annotations, limiting scalability and generalization, and often degrading navigation and localization performance. We propose ViBA,…
Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities, especially for complex tasks. Synthesizing tool-use data through real-world simulations is an effective way to achieve this.…
Large Language Models (LLMs) fine-tuned for specific domains exhibit strong performance; however, the underlying mechanisms by which this fine-tuning reshapes their parametric space are not well understood. Prior works primarily focus on…
Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Current mainstream DA strategies are synthetic-based methods,…
Although distributed computing can significantly reduce the training time of deep neural networks, scaling the training process while maintaining high efficiency and final accuracy is challenging. Distributed asynchronous training enjoys…
Data Augmentation (DA) is known to improve the generalizability of deep neural networks. Most existing DA techniques naively add a certain number of augmented samples without considering the quality and the added computational cost of these…
Unsupervised Domain Adaptation (UDA) is essential for enabling semantic segmentation in new domains without requiring costly pixel-wise annotations. State-of-the-art (SOTA) UDA methods primarily use self-training with architecturally…
We present Dynamic Skill Adaptation (DSA), an adaptive and dynamic framework to adapt novel and complex skills to Large Language Models (LLMs). Compared with previous work which learns from human-curated and static data in random orders, we…
Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data…
When domains, which represent underlying data distributions, vary during training and testing processes, deep neural networks suffer a drop in their performance. Domain generalization allows improvements in the generalization performance…
Despite the impressive capabilities of large language models across various tasks, their continued scaling is severely hampered not only by data scarcity but also by the performance degradation associated with excessive data repetition…