Related papers: CPO: Condition Preference Optimization for Control…

Direct Preference Optimization (DPO) has shown strong potential for mitigating hallucinations in Multimodal Large Language Models (MLLMs). However, existing multimodal DPO approaches often suffer from overfitting due to the difficulty…

The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also…

Large Language Models (LLMs) rely on Human Preference Alignment (HPA) to ensure the generation of safe content. Due to the heavy cost associated with fine-tuning, fine-tuning-free methods have emerged, typically modifying LLM decoding with…

Foreground-conditioned inpainting, which aims at generating a harmonious background for a given foreground subject based on the text prompt, is an important subfield in controllable image generation. A common challenge in current methods,…

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress…

Policy gradient methods usually rely on entropy regularization to prevent premature convergence. However, maximizing entropy indiscriminately pushes the policy towards a uniform distribution, often overriding the reward signal if not…

Preference optimization has made significant progress recently, with numerous methods developed to align language models with human preferences. This paper introduces $f$-divergence Preference Optimization ($f$-PO), a novel framework that…

Direct Preference Optimization (DPO) has become the de facto standard for offline preference alignment of large language models, but its reliance on a reference policy introduces a critical tension. DPO weighs each update relative to a…

Preference optimization (PO) is indispensable for large language models (LLMs), with methods such as direct preference optimization (DPO) and proximal policy optimization (PPO) achieving great success. A common belief is that DPO is…

In recent years, prompt tuning has proven effective in adapting pre-trained vision-language models to downstream tasks. These methods aim to adapt the pre-trained models by introducing learnable prompts while keeping pre-trained weights…

Many applications of large language models (LLMs), ranging from chatbots to creative writing, require nuanced subjective judgments that can differ significantly across different groups. Existing alignment algorithms can be expensive to…

Generating accurate glyphs for visual text rendering is essential yet challenging. Existing methods typically enhance text rendering by training on a large amount of high-quality scene text images, but the limited coverage of glyph…

Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the explicit reference…

The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) have achieved…

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…

Direct Preference Optimization (DPO) has become a widely used training method for the instruction fine-tuning of large language models (LLMs). In this work, we explore an under-investigated aspect of DPO - its dependency on the reference…

Iterative data generation and model retraining are widely used to align large language models (LLMs). It typically involves a policy model to generate on-policy responses and a reward model to guide training data selection. Direct…

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…

While Direct Preference Optimization (DPO) has become the de facto approach for aligning Large Vision-Language Models (LVLMs), it suffers from Likelihood Displacement, where the probability of both chosen and rejected responses collapses.…

Recent advancements in video-audio joint generation have achieved remarkable success in semantic correspondence. However, achieving precise temporal synchronization, which requires fine-grained alignment between audio events and their…