paper-with-me

Papers

MVReward: Better Aligning and Evaluating Multi-View Diffusion Models with Human Preferences

2024-12-09 · Weitao Wang, Haoran Xu, Yuxiao Yang, Zhifang Liu, Jun Meng, Haoqian Wang

Recent years have witnessed remarkable progress in 3D content generation. However, corresponding evaluation methods struggle to keep pace. Automatic approaches have proven challenging to align with human preferences, and the mixed comparison of text- and image-driven methods often leads to unfair evaluations. In this paper, we present a comprehensive framework to better align and evaluate multi-view diffusion models with human preferences. To begin with, we first collect and filter a standardized image prompt set from DALL$\cdot$E and Objaverse, which we then use to generate multi-view assets with several multi-view diffusion models. Through a systematic ranking pipeline on these assets, we obtain a human annotation dataset with 16k expert pairwise comparisons and train a reward model, coined MVReward, to effectively encode human preferences. With MVReward, image-driven 3D methods can be evaluated against each other in a more fair and transparent manner. Building on this, we further propose Multi-View Preference Learning (MVP), a plug-and-play multi-view diffusion tuning strategy. Extensive experiments demonstrate that MVReward can serve as a reliable metric and MVP consistently enhances the alignment of multi-view diffusion models with human preferences.

📄 PDF Abstract BibTeX arXiv:2412.06614

Code (0)

등록된 구현이 없습니다.

Tasks

16k

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Aligning Large Language Models by On-Policy Self-Judgment

2024-02-17 · Sangkyu Lee, Sungdong Kim, Ashkan Yousefpour, Minjoon Seo 외

Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we present a novel alignment framework, SEL…

Instruction Following

Aligning Speakers: Evaluating and Visualizing Text-based Diarization Using Efficient Multiple Sequence Alignment (Extended Version)

2023-09-14 · Chen Gong, Peilin Wu, Jinho D. Choi

This paper presents a novel evaluation approach to text-based speaker diarization (SD), tackling the limitations of traditional metrics that do not account for any contextual information in text. Two new metrics are prop…

Multiple Sequence Alignmentspeaker-diarizationSpeaker Diarization

Reconsidering Representation Alignment for Multi-view Clustering

2021-03-13 · CVPR 2021 1 · Daniel J. Trosten, Sigurd Løkse, Robert Jenssen, Michael Kampffmeyer

Aligning distributions of view representations is a core component of today's state of the art models for deep multi-view clustering. However, we identify several drawbacks with na\"ively aligning representation distribu…

ClusteringContrastive Learning

What Matters in Evaluating Book-Length Stories? A Systematic Study of Long Story Evaluation

2025-12-14 · Dingyi Yang, Qin Jin arxiv

In this work, we conduct systematic research in a challenging area: the automatic evaluation of book-length stories (>100K tokens). Our study focuses on two key questions: (1) understanding which evaluation aspects matte…

Aligning Large Language Models with Human: A Survey

2023-07-24 · YuFei Wang, Wanjun Zhong, Liangyou Li, Fei Mi 외

Large Language Models (LLMs) trained on extensive textual corpora have emerged as leading solutions for a broad array of Natural Language Processing (NLP) tasks. Despite their notable performance, these models are prone …

Survey