相关论文: FuseRL: Dense Preference Optimization for Heteroge…

Federated Learning (FL) is a distributed machine learning approach that enables devices to collaboratively train models without sharing their local data, ensuring user privacy and scalability. However, applying FL to real-world data…

Resource-efficient training optimization techniques are becoming increasingly important as the size of large language models (LLMs) continues to grow. In particular, batch packing is commonly used in pre-training and supervised fine-tuning…

Deep neural networks achieve state-of-the-art performance for a range of classification and inference tasks. However, the use of stochastic gradient descent combined with the nonconvexity of the underlying optimization problems renders…

Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync…

Instruction following (IF) is a critical capability for large language models (LLMs). However, handling complex instructions with multiple constraints remains challenging. Previous methods typically select preference pairs based on the…

Personalized Federated Learning (PFL) enables clients to collaboratively train personalized models tailored to their individual objectives, addressing the challenge of model generalization in traditional Federated Learning (FL) due to high…

This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-design of transformer blocks with an optimization pipeline that reduces computational and…

In this work, we investigate how to leverage pre-trained visual-language models (VLM) for online Reinforcement Learning (RL). In particular, we focus on sparse reward tasks with pre-defined textual task descriptions. We first identify the…

Edge intelligence has emerged as a promising strategy to deliver low-latency and ubiquitous services for mobile devices. Recent advances in fine-tuning mechanisms of foundation models have enabled edge intelligence by integrating low-rank…

Reinforcement learning (RL) in few-shot scenarios with limited sensor data is challenging due to insufficient training samples, particularly in applications like Dynamic Voltage and Frequency Scaling (DVFS) where sensor readings are…

Large Language Models (LLMs) as autonomous agents are increasingly tasked with solving complex, long-horizon problems. Aligning these agents via preference-based offline methods like Direct Preference Optimization (DPO) is a promising…

Federated fine-tuning (FFT) of large language models (LLMs) has recently emerged as a promising solution to enable domain-specific adaptation while preserving data privacy. Despite its benefits, FFT on resource-constrained clients relies on…

The integration of different learning paradigms has long been a focus of machine learning research, aimed at overcoming the inherent limitations of individual methods. Fuzzy rule-based models excel in interpretability and have seen…

Graph based molecular representation learning is essential for accurately predicting molecular properties in drug discovery and materials science; however, it faces significant challenges due to the intricate relationships among molecules…

Preference optimization has made significant progress recently, with numerous methods developed to align language models with human preferences. This paper introduces $f$-divergence Preference Optimization ($f$-PO), a novel framework that…

Supervised fine-tuning (SFT) is a pivotal approach to adapting large language models (LLMs) for downstream tasks; however, performance often suffers from the ``seesaw phenomenon'', where indiscriminate parameter updates yield progress on…

Recent Large Reasoning Models (LRMs) have achieved remarkable performance in solving complex problems via supervised fine-tuning (SFT) and reinforcement learning (RL). Although existing RL algorithms significantly enhance model accuracy,…

Vision-language models (VLMs) are prone to hallucinations that critically compromise reliability in medical applications. While preference optimization can mitigate these hallucinations through clinical feedback, its implementation faces…

Reward models are fundamental to Reinforcement Learning from Human Feedback (RLHF), yet real-world datasets are inevitably corrupted by noisy preference. Conventional training objectives tend to overfit these errors, while existing…

Reinforcement Learning with Human Feedback (RLHF) enhances the alignment of Large Language Models (LLMs). However, its limitations have led to the development of Direct Preference Optimization (DPO), an RL-free approach designed to overcome…