Related papers: Personalized Preference Fine-tuning of Diffusion M…

Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the…

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal tool for aligning large language models (LLMs) with human preferences. Direct Preference Optimization (DPO), one of the most popular approaches, formulates RLHF as a…

Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from…

Preference learning algorithms (e.g., RLHF and DPO) are frequently used to steer LLMs to produce generations that are more preferred by humans, but our understanding of their inner workings is still limited. In this work, we study the…

Pre-trained Language Models (LMs) exhibit strong zero-shot and in-context learning capabilities; however, their behaviors are often difficult to control. By utilizing Reinforcement Learning from Human Feedback (RLHF), it is possible to…

Preference-based reinforcement learning (RL) is a key paradigm for aligning policies with human judgments, yet its theoretical behavior in distributed settings where preference data are fragmented across heterogeneous users remains poorly…

Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) are widely used, they often…

In this paper, we take a step towards a deeper understanding of learning from human preferences by systematically comparing the paradigm of reinforcement learning from human feedback (RLHF) with the recently proposed paradigm of direct…

Direct Preference Optimization (DPO) has recently emerged as a simple and effective alternative to reinforcement learning from human feedback (RLHF) for aligning large language models (LLMs) with user preferences. However, existing DPO…

Personalized retrieval and segmentation aim to locate specific instances within a dataset based on an input image and a short description of the reference instance. While supervised methods are effective, they require extensive labeled data…

Memory-efficient personalization is critical for adapting text-to-image diffusion models while preserving user privacy and operating within the limited computational resources of edge devices. To this end, we propose a selective…

Despite recent advances in Large Video Language Models (LVLMs), they still struggle with fine-grained temporal understanding, hallucinate, and often make simple mistakes on even simple video question-answering tasks, all of which pose…

Post-training of language models, either through reinforcement learning, preference optimization or supervised finetuning, tends to sharpen the output probability distribution and reduce the diversity of generated responses. This is…

Radiography Report Generation (RRG) has gained significant attention in medical image analysis as a promising tool for alleviating the growing workload of radiologists. However, despite numerous advancements, existing methods have yet to…

Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable. To remedy this issue, we develop the first…

Reinforcement Learning from Human Feedback (RLHF) is currently the most widely used method to align large language models (LLMs) with human preferences. Existing RLHF methods can be roughly categorized as either reward-based or reward-free.…

Forecasting multi-step user behavior trajectories requires reasoning over structured preferences across future actions, a challenge overlooked by traditional sequential recommendation. This problem is critical for applications such as…

Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…

Preference modeling techniques, such as direct preference optimization (DPO), has shown effective in enhancing the generalization abilities of large language model (LLM). However, in tasks involving video instruction-following, providing…