Related papers: HIVE: Harnessing Human Feedback for Instructional …

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Anime video generation faces significant challenges due to the scarcity of anime data and unusual motion patterns, leading to issues such as motion distortion and flickering artifacts, which result in misalignment with human preferences.…

We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. To obtain training data for this…

Research in Image Generation has recently made significant progress, particularly boosted by the introduction of Vision-Language models which are able to produce high-quality visual content based on textual inputs. Despite ongoing…

Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. However, human values are inherently diverse and heterogeneous, and a single reward model…

Preference learning from human feedback has the ability to align generative models with the needs of end-users. Human feedback is costly and time-consuming to obtain, which creates demand for data-efficient query selection methods. This…

Learning from human feedback has enabled the alignment of language models (LMs) with human preferences. However, collecting human preferences is expensive and time-consuming, with highly variable annotation quality. An appealing alternative…

Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values. However, RM training data is commonly recognized as low-quality, containing inductive biases…

Recent advances in video diffusion models have significantly enhanced text-to-video generation, particularly through alignment tuning using reward models trained on human preferences. While these methods improve visual quality, they can…

The performance of computer vision models in certain real-world applications (e.g., rare wildlife observation) is limited by the small number of available images. Expanding datasets using pre-trained generative models is an effective way to…

Video editing according to instructions is a highly challenging task due to the difficulty in collecting large-scale, high-quality edited video pair data. This scarcity not only limits the availability of training data but also hinders the…

While Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm for text-to-image generation, its application to image editing remains largely unexplored. A key bottleneck is the lack of a robust general reward model…

Human feedback can alter language models in unpredictable and undesirable ways, as practitioners lack a clear understanding of what feedback data encodes. While prior work studies preferences over certain attributes (e.g., length or…

As language models become more powerful, training and evaluation are increasingly bottlenecked by the data and metrics used for a particular task. For example, summarization models are often trained to predict human reference summaries and…

AI agents are commonly aligned with "human values" through reinforcement learning from human feedback (RLHF), where a single reward model is learned from aggregated human feedback and used to align an agent's behavior. However, human values…

To improve human-preference alignment training, current research has developed numerous preference datasets consisting of preference pairs labeled as "preferred" or "dispreferred". These preference pairs are typically used to encode human…

Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tuning using models trained on human feedback improves…

When developing new large language models (LLMs), a key step is evaluating their final performance, often by computing the win-rate against a reference model based on external feedback. Human feedback is the gold standard, particularly for…

Generative models have proven to be very effective in generating synthetic medical images and find applications in downstream tasks such as enhancing rare disease datasets, long-tailed dataset augmentation, and scaling machine learning…

We present an approach to robot learning from egocentric human videos by modeling human preferences in a reward function and optimizing robot behavior to maximize this reward. Prior work on reward learning from human videos attempts to…