Related papers: Multi-dimensional Preference Alignment by Conditio…

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…

Conditional image generation enhances text-to-image synthesis with structural, spatial, or stylistic priors, but current methods face challenges in handling conflicts between sources. These include 1) input-level conflicts, where the…

Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenarios, achieving strong…

Diffusion models have achieved state-of-the-art performance across multiple domains, with recent advancements extending their applicability to discrete data. However, aligning discrete diffusion models with task-specific preferences remains…

Modeling human preferences is crucial for aligning foundation models with human values. Traditional reward modeling methods, such as the Bradley-Terry (BT) reward model, fall short in expressiveness, particularly in addressing intransitive…

DPO has become a widely adopted alternative to RLHF for aligning LLMs with human preferences, eliminating the need for a separate reward model or RL loop. Recent theoretical analysis uncovers an asymmetric gradient behavior in DPO: the loss…

Large Language Models (LLMs) have demonstrated unprecedented generative capabilities, yet their alignment with human values remains critical for ensuring helpful and harmless deployments. While Reinforcement Learning from Human Feedback…

Sequential decision-making is desired to align with human intents and exhibit versatility across various tasks. Previous methods formulate it as a conditional generation process, utilizing return-conditioned diffusion models to directly…

Post-training alignment of diffusion models relies on simplified signals, such as scalar rewards or binary preferences. This limits alignment with complex human expertise, which is hierarchical and fine-grained. To address this, we first…

Existing multi-objective preference alignment methods for large language models (LLMs) face limitations: (1) the inability to effectively balance various preference dimensions, and (2) reliance on auxiliary reward/reference models…

Direct Preference Optimization (DPO) has become a prominent method for aligning Large Language Models (LLMs) with human preferences. While DPO has enabled significant progress in aligning English LLMs, multilingual preference alignment is…

Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to…

Direct Preference Optimization (DPO) is a widely adopted offline algorithm for preference-based reinforcement learning from human feedback (RLHF), designed to improve training simplicity and stability by redefining reward functions.…

Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…

Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes training sensitive to imperfect supervision. Existing robust DPO methods often address this…

Model-based reinforcement learning (RL) can be effectively supported at scale through the use of world models. However, in practice, scaling such approaches remains fundamentally limited. A commonly recognized challenge is model bias and…

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive training of a base model…

As the era of large language models (LLMs) unfolds, Preference Optimization (PO) methods have become a central approach to aligning LLMs with human preferences and improving performance. We propose Maximum a Posteriori Preference…

Diffusion Models have revolutionized the field of human motion generation by offering exceptional generation quality and fine-grained controllability through natural language conditioning. Their inherent stochasticity, that is the ability…