相关论文: Model Agnostic Preference Optimization for Medical…

Accurate exploration of protein conformational ensembles is essential for uncovering function but remains hard because molecular-dynamics (MD) simulations suffer from high computational costs and energy-barrier trapping. This paper presents…

Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is…

Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology:…

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization (DPO) to diffusion…

Recent alignment methods based on Direct Preference Optimization (DPO) reformulate preference learning as supervised optimization over pairwise comparisons, offering improved efficiency and stability over reinforcement learning from human…

This paper presents a model-agnostic ensemble approach for supervised learning. The proposed approach is based on a parametric version of Random Subspace, in which each base model is learned from a feature subset sampled according to a…

Existing preference datasets for text-to-image models typically store only the final winner/loser images. This representation is insufficient for rectified flow (RF) models, whose generation is naturally indexed by a specific prior noise…

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play…

Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and…

Multi-objective Bayesian optimization (MOBO) provides a principled framework for optimizing expensive black-box functions with multiple objectives. However, existing MOBO methods often struggle with coverage, scalability with respect to the…

Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These methods improve training stability by avoiding the REINFORCE…

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…

Direct Preference Optimization (DPO) has recently been extended from text-only models to vision-language models. However, existing methods rely on oversimplified pairwise comparisons, generating a single negative image via basic…

Large-scale text-to-image foundation models have achieved remarkable visual realism, yet generating human images with correct anatomical structures remains challenging. Existing approaches enforce anatomical constraints through…

In recent years, the field of image generation has witnessed significant advancements, particularly in fine-tuning methods that align models with universal human preferences. This paper explores the critical role of preference data in the…

The Segment Anything Model (SAM), a foundation model for general image segmentation, has demonstrated impressive zero-shot performance across numerous natural image segmentation tasks. However, SAM's performance significantly declines when…

Medical image segmentation methods generally assume that the process from medical image to segmentation is unbiased, and use neural networks to establish conditional probability models to complete the segmentation task. This assumption does…

Modern preference alignment methods, such as DPO, rely on divergence regularization to a reference model for training stability-but this creates a fundamental problem we call "reference mismatch." In this paper, we investigate the negative…

Aligning large-scale text-to-image diffusion models with nuanced human preferences remains challenging. While direct preference optimization (DPO) is simple and effective, large-scale finetuning often shows a generalization gap. We take…

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…