相关论文: VISPA: Pluralistic Alignment via Automatic Value S…

We propose VISP: Volatility Informed Stochastic Projection, an adaptive regularization method that leverages gradient volatility to guide stochastic noise injection in deep neural networks. Unlike conventional techniques that apply uniform…

Reliable behavior control is central to deploying large language models (LLMs) on the web. Activation steering offers a tuning-free route to align attributes (e.g., truthfulness) that ensure trustworthy generation. Prevailing approaches…

The rapid advancement of language models (LMs) necessitates robust alignment with diverse user values. However, current preference optimization approaches often fail to capture the plurality of user opinions, instead reinforcing majority…

Although large language models (LLMs) are increasingly trained using human feedback for safety and alignment with human values, alignment decisions often overlook human social diversity. This study examines how incorporating pluralistic…

This paper makes the first attempt towards unsupervised preference alignment in Vision-Language Models (VLMs). We generate chosen and rejected responses with regard to the original and augmented image pairs, and conduct preference alignment…

Large language models (LLMs) have traditionally been aligned through one-size-fits-all approaches that assume uniform human preferences, fundamentally overlooking the diversity in user values and needs. This paper introduces a comprehensive…

The development of ethical AI systems is currently geared toward setting objective functions that align with human objectives. However, finding such functions remains a research challenge, while in RL, setting rewards by hand is a fairly…

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for generalist robotic control. Built upon vision-language model (VLM) architectures, VLAs predict actions conditioned on visual observations and language…

Many NLP classification tasks, such as sexism/racism detection or toxicity detection, are based on human values. Yet, human values can vary under diverse cultural conditions. Therefore, we introduce a framework for value-aligned…

Large vision language models (VLMs) have demonstrated significant potential for integration into daily life, making it crucial for them to incorporate human values when making decisions in real-world situations. This paper introduces VIVA,…

Vision-language-action models (VLAs) have become increasingly popular in robot manipulation for their end-to-end design and remarkable performance. However, existing VLAs rely heavily on vision-language models (VLMs) that only support…

Value alignment has emerged in recent years as a basic principle to produce beneficial and mindful Artificial Intelligence systems. It mainly states that autonomous entities should behave in a way that is aligned with our human values. In…

Recent vision-language pre-training models have exhibited remarkable generalization ability in zero-shot recognition tasks. Previous open-vocabulary 3D scene understanding methods mostly focus on training 3D models using either image or…

Large language models (LLMs) have demonstrated remarkable capabilities but often struggle to align with human preferences, leading to harmful or undesirable outputs. Preference learning, which trains models to distinguish between preferred…

Large Language Models (LLMs) acquire extensive knowledge and remarkable abilities from extensive text corpora, making them powerful tools for various applications. To make LLMs more usable, aligning them with human preferences is essential.…

Despite the impressive reasoning abilities demonstrated by large language models (LLMs), empirical evidence indicates that they are not language agnostic as expected, leading to performance declines in multilingual settings, especially for…

Large foundation models pretrained on raw web-scale data are not readily deployable without additional step of extensive alignment to human preferences. Such alignment is typically done by collecting large amounts of pairwise comparisons…

In this work, we present and evaluate SELMA, a Speech-Enabled Language Model for virtual Assistant interactions that integrates audio and text as inputs to a Large Language Model (LLM). SELMA is designed to handle three primary and two…

Large language models (LLMs) can handle a wide variety of general tasks with simple prompts, without the need for task-specific training. Multimodal Large Language Models (MLLMs), built upon LLMs, have demonstrated impressive potential in…

Vision-language-action models (VLAs) have become an increasingly popular approach for addressing robot manipulation problems in recent years. However, such models need to output actions at a rate suitable for robot control, which limits the…