相关论文: Implicit Preference Alignment for Human Image Anim…

Human preference alignment is essential to improve the interaction quality of large language models (LLMs). Existing alignment methods depend on manually annotated preference data to guide the LLM optimization directions. However,…

Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle this problem, we…

Human alignment in large language models (LLMs) is an active area of research. A recent groundbreaking work, direct preference optimization (DPO), has greatly simplified the process from past work in reinforcement learning from human…

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. While it enables LLMs to achieve human-level alignment, it often incurs significant…

Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt…

Preference optimization is a critical post-training technique used to align large language models (LLMs) with human preferences, typically by fine-tuning on ranked response pairs. While methods like Direct Preference Optimization (DPO) have…

The field of image-to-video generation has made remarkable progress. However, challenges such as human limb twisting and facial distortion persist, especially when generating long videos or modeling intensive motions. Existing human image…

Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to their simplicity, efficiency, and stability. However, the…

Fine-tuning text-to-image diffusion models with human feedback is an effective method for aligning model behavior with human intentions. However, this alignment process often suffers from slow convergence due to the large size and noise…

Establishing a reliable and iteratively refined robotic system is essential for deploying real-world applications. While Vision-Language-Action (VLA) models are widely recognized as the foundation model for such robotic deployment, their…

Manual assembly workers face increasing complexity in their work. Human-centered assistance systems could help, but object recognition as an enabling technology hinders sophisticated human-centered design of these systems. At the same time,…

Preference optimization has emerged as an efficient alternative to online reinforcement learning from human feedback (RLHF) for aligning text-to-image diffusion models. However, existing methods largely reduce supervision to binary pairwise…

Reward modeling represents a long-standing challenge in reinforcement learning from human feedback (RLHF) for aligning language models. Current reward modeling is heavily contingent upon experimental feedback data with high collection…

Direct preference optimization methods have emerged as a computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) for aligning Large Language Models (LLMs). Latest approaches have streamlined the alignment…

Visual preference alignment involves training Large Vision-Language Models (LVLMs) to predict human preferences between visual inputs. This is typically achieved by using labeled datasets of chosen/rejected pairs and employing optimization…

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…

Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time. We introduce Adaptive Pluralistic Alignment (APA), a modular pipeline for updating pluralistically…

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between…