Related papers: Utility-Diversity Aware Online Batch Selection for…
Large language models (LLMs) are challenging to deploy for domain-specific tasks due to their massive scale. While distilling a fine-tuned LLM into a smaller student model is a promising alternative, the capacity gap between teacher and…
In continual instruction tuning (CIT) scenarios, where new instruction tuning data continuously arrive in an online streaming manner, training delays from large-scale data significantly hinder real-time adaptation. Data selection can…
The scaling of Large Multimodal Models (LMMs) is constrained by the quality-quantity trade-off inherent in synthetic data. Previous approaches, such as LLM-as-a-Judge, have proven their effectiveness in addressing this but suffer from…
Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying…
Speculative Decoding (SD) is a key technique for accelerating Large Language Model (LLM) inference, but it typically requires training a draft model on a large dataset. We approach this problem from a data-centric perspective, finding that…
Training diffusion models on limited datasets poses challenges in terms of limited generation capacity and expressiveness, leading to unsatisfactory results in various downstream tasks utilizing pretrained diffusion models, such as domain…
Digital Breast Tomosynthesis (DBT) is a widely used medical imaging modality for breast cancer screening and diagnosis, offering higher spatial resolution and greater detail through its 3D-like breast volume imaging capability. However, the…
Inductive transfer learning has greatly impacted computer vision, but existing approaches in NLP still require task-specific modifications and training from scratch. We propose Universal Language Model Fine-tuning (ULMFiT), an effective…
Modern instruction-tuned large language models (LLMs) have made remarkable progress in code generation. However, these LLMs fine-tuned with standard supervised fine-tuning (SFT) sometimes generate plausible-looking but functionally…
The adaptation of large-scale Vision-Language Models (VLMs) through post-training reveals a pronounced generalization gap: models fine-tuned with Reinforcement Learning (RL) consistently achieve superior out-of-distribution (OOD)…
Deep neural networks are commonly trained using stochastic non-convex optimization procedures, which are driven by gradient information estimated on fractions (batches) of the dataset. While it is commonly accepted that batch size is an…
Current AI/ML methods for data-driven engineering use models that are mostly trained offline. Such models can be expensive to build in terms of communication and computing cost, and they rely on data that is collected over extended periods…
Self-supervised learning (SSL) methods learn from unlabeled data and achieve high generalization performance on downstream tasks. However, they may also suffer from overfitting to their training data and lose the ability to adapt to new…
Knowledge extraction from database is the fundamental task in database and data mining community, which has been applied to a wide range of real-world applications and situations. Different from the support-based mining models, the…
Machine Unlearning (MU) enables Large Language Models (LLMs) to remove unsafe or outdated information. However, existing work assumes that all facts are equally forgettable and largely ignores whether the forgotten knowledge originates from…
Recent development in Large Language Models (LLMs) and Multi-modal Large Language Models (MLLMs) have leverage Attention-based Transformer architectures and achieved superior performance and generalization capabilities. They have since…
One of the key challenges of machine learning (ML) based intrusion detection system (IDS) is the expensive computational complexity which is largely due to redundant, incomplete, and irrelevant features contain in the IDS datasets. To…
Post-training of large language models involves a fundamental trade-off between supervised fine-tuning (SFT), which efficiently mimics demonstrations but tends to memorize, and reinforcement learning (RL), which achieves better…
The demand for high-resolution, non-invasive imaging continues to drive innovation in magnetic resonance imaging (MRI), but long acquisition times remain a major practical limitation. Although deep learning-based reconstruction methods have…
Over recent years, an increasing amount of compute and data has been poured into training large language models (LLMs), usually by doing one-pass learning on as many tokens as possible randomly selected from large-scale web corpora. While…