Related papers: Human-assisted Robotic Policy Refinement via Actio…

Alignment in artificial intelligence pursues the consistency between model responses and human preferences as well as values. In practice, the multifaceted nature of human preferences inadvertently introduces what is known as the "alignment…

Vision-language-action (VLA) models have shown strong potential for generalist robot manipulation, yet they remain limited by insufficient spatial reasoning, particularly in determining where to interact in complex visual scenes. While…

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

We propose a framework for online meta-optimization of parameters that govern optimization, called Amortized Proximal Optimization (APO). We first interpret various existing neural network optimizers as approximate stochastic proximal point…

While Masked Diffusion Models (MDMs), such as LLaDA, present a promising paradigm for language modeling, there has been relatively little effort in aligning these models with human preferences via reinforcement learning. The challenge…

Hyperparameter optimization (HPO) is generally treated as a bi-level optimization problem that involves fitting a (probabilistic) surrogate model to a set of observed hyperparameter responses, e.g. validation loss, and consequently…

Preference optimization methods typically begin training with a well-trained SFT model as a reference model. In RLHF and DPO, a regularization term is used during the preference optimization process to prevent the policy model from…

The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominance of Supervised Fine-Tuning (SFT) methods in current GUI…

In recent years, trust region on-policy reinforcement learning has achieved impressive results in addressing complex control tasks and gaming scenarios. However, contemporary state-of-the-art algorithms within this category primarily…

Learned language-conditioned robot policies often struggle to effectively adapt to new real-world tasks even when pre-trained across a diverse set of instructions. We propose a novel approach for few-shot adaptation to unseen tasks that…

Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and semantic generalization. Despite these…

In this paper, we introduce \emph{refined Direct Preference Optimization} (rDPO), a method for improving the behavioral alignment of Large Language Models (LLMs) without the need for human-annotated data. The method involves creating…

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…

Despite the efficacy of Direct Preference Optimization (DPO) in aligning Large Language Models (LLMs), reward hacking remains a pivotal challenge. This issue emerges when LLMs excessively reduce the probability of rejected completions to…

Robotic foundation models require reasoning over complex visual scenes to execute adaptive actions in dynamic environments. While recent studies on latent-reasoning Vision-Language-Action (VLA) models have demonstrated the capability to…

As large language models (LLMs) become more capable, fine-tuning techniques for aligning with human intent are increasingly important. A key consideration for aligning these models is how to most effectively use human resources, or model…

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…

Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means…

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

For robots to be effectively deployed in novel environments and tasks, they must be able to understand the feedback expressed by humans during intervention. This can either correct undesirable behavior or indicate additional preferences.…