相关论文: Interactive Multi-fidelity Learning for Cost-effec…

Multimodal Large Language Models (MLLMs) have made significant advancements, demonstrating powerful capabilities in processing and understanding multimodal data. Fine-tuning MLLMs with Federated Learning (FL) allows for expanding the…

Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…

Large Language Models (LLMs) have revolutionized intelligent services by enabling logical reasoning, tool use, and interaction with external systems as agents. The advancement of LLMs is frequently hindered by the scarcity of high-quality…

Event annotation is important for identifying market changes, monitoring breaking news, and understanding sociological trends. Although expert annotators set the gold standards, human coding is expensive and inefficient. Unlike information…

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

Fine-tuning large language models (LLMs) via federated learning, i.e., FedLLM, has been proposed to adapt LLMs for various downstream applications in a privacy-preserving way. To reduce the fine-tuning costs on resource-constrained devices,…

Instruction fine-tuning stands as a crucial advancement in leveraging large language models (LLMs) for enhanced task performance. However, the annotation of instruction datasets has traditionally been expensive and laborious, often relying…

Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence. While general artificial intelligence is leveraged by…

While large language models (LLMs) demonstrate reasonable zero-shot capability across many downstream tasks, fine-tuning is a common practice to improve their performance. However, a task's data efficiency--i.e., the number of fine-tuning…

Multi-fidelity Reinforcement Learning (RL) frameworks efficiently utilize computational resources by integrating analysis models of varying accuracy and costs. The prevailing methodologies, characterized by transfer learning, human-inspired…

Large language models (LLMs) have shown impressive capabilities across various tasks, but their performance on domain-specific tasks remains limited. While methods like retrieval augmented generation and fine-tuning can help to address…

Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have made significant advancements in reasoning capabilities. However, they still face challenges such as high computational demands and privacy concerns. This paper…

Federated learning (FL) has been intensively investigated in terms of communication efficiency, privacy, and fairness. However, efficient annotation, which is a pain point in real-world FL applications, is less studied. In this project, we…

Generalizing Multimodal Large Language Models (MLLMs) to novel video domains is essential for real-world deployment but remains challenging due to the scarcity of labeled data. While In-Context Learning (ICL) offers a training-free…

Large Language models (LLMs) usually rely on extensive training datasets. In the financial domain, creating numerical reasoning datasets that include a mix of tables and long text often involves substantial manual annotation expenses. To…

Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…

Preference-based reinforcement learning is an effective way to handle tasks where rewards are hard to specify but can be exceedingly inefficient as preference learning is often tabula rasa. We demonstrate that Large Language Models (LLMs)…

Large language models (LLMs) have become pivotal in recent research. However, during the inference process, LLMs still require substantial resources. In this paper, we propose CliqueParcel, a method designed to improve the efficiency of…

Fine-tuning pre-trained large language models (LLMs) has become a common practice for personalized natural language understanding (NLU) applications on downstream tasks and domain-specific datasets. However, there are two main challenges:…

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…