English
Related papers

Related papers: DSO: Aligning 3D Generators with Simulation Feedba…

200 papers

This paper addresses the task of 3D pose estimation for a hand interacting with an object from a single image observation. When modeling hand-object interaction, previous works mainly exploit proximity cues, while overlooking the dynamical…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Rong Wang , Wei Mao , Hongdong Li

Human image generation is a key focus in image synthesis due to its broad applications, but even slight inaccuracies in anatomy, pose, or details can compromise realism. To address these challenges, we explore Direct Preference Optimization…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Sanghyeon Na , Yonggyu Kim , Hyunjoon Lee

We study an LLM fine-tuning task for designing reward functions for sequential resource allocation problems in public health, guided by human preferences expressed in natural language. This setting presents a challenging testbed for…

Machine Learning · Computer Science 2025-11-19 Cheol Woo Kim , Shresth Verma , Mauricio Tec , Milind Tambe

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…

Machine Learning · Computer Science 2024-03-26 Kai Yang , Jian Tao , Jiafei Lyu , Chunjiang Ge , Jiaxin Chen , Qimai Li , Weihan Shen , Xiaolong Zhu , Xiu Li

Direct Preference Optimization (DPO) has recently been applied as a post-training technique for text-to-video diffusion models. To obtain training data, annotators are asked to provide preferences between two videos generated from…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Ziyi Wu , Anil Kag , Ivan Skorokhodov , Willi Menapace , Ashkan Mirzaei , Igor Gilitschenski , Sergey Tulyakov , Aliaksandr Siarohin

We introduce Drag4D, an interactive framework that integrates object motion control within text-driven 3D scene generation. This framework enables users to define 3D trajectories for the 3D objects generated from a single image, seamlessly…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Minjun Kang , Inkyu Shin , Taeyeop Lee , In So Kweon , Kuk-Jin Yoon

Direct Preference Optimization (DPO), which aligns models with human preferences through win/lose data pairs, has achieved remarkable success in language and image generation. However, applying DPO to video diffusion models faces critical…

Computer Vision and Pattern Recognition · Computer Science 2025-04-14 Haoran Cheng , Qide Dong , Liang Peng , Zhizhou Sha , Weiguo Feng , Jinghui Xie , Zhao Song , Shilei Wen , Xiaofei He , Boxi Wu

Aligning language models for both helpfulness and safety typically requires complex pipelines-separate reward and cost models, online reinforcement learning, and primal-dual updates. Recent direct preference optimization approaches simplify…

Machine Learning · Computer Science 2026-05-13 Tien-Phat Nguyen , Truong Nguyen , Thin Nguyen , Duy Minh Ho Nguyen , Ngoc-Thanh Dinh , Trung Le

Recent advances in Gaussian Splatting have enabled fast, high-fidelity 3D scene generation, yet these methods remain purely visual and lack an understanding of how shapes behave in the physical world. We introduce Physics-Guided 3D Gaussian…

Computer Vision and Pattern Recognition · Computer Science 2026-05-13 Zachary Lee , Maxwell Jacobson , Yexiang Xue

The class of direct preference optimization (DPO) algorithms has emerged as a promising approach for solving the alignment problem in foundation models. These algorithms work with very limited feedback in the form of pairwise preferences…

Machine Learning · Computer Science 2026-02-03 Luca Viano , Ruida Zhou , Yifan Sun , Mahdi Namazifar , Volkan Cevher , Shoham Sabach , Mohammad Ghavamzadeh

Recent advancements in generative models have enabled the creation of dynamic 4D content - 3D objects in motion - based on text prompts, which holds potential for applications in virtual worlds, media, and gaming. Existing methods provide…

Computer Vision and Pattern Recognition · Computer Science 2025-05-28 Ohad Rahamim , Ori Malca , Dvir Samuel , Gal Chechik

This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noise, which includes…

Machine Learning · Computer Science 2025-04-21 Junkang Wu , Yuexiang Xie , Zhengyi Yang , Jiancan Wu , Jiawei Chen , Jinyang Gao , Bolin Ding , Xiang Wang , Xiangnan He

Video generative models have recently achieved notable advancements in synthesis quality. However, generating complex motions remains a critical challenge, as existing models often struggle to produce natural, smooth, and contextually…

Computer Vision and Pattern Recognition · Computer Science 2025-11-07 Guo Cheng , Danni Yang , Ziqi Huang , Jianlou Si , Chenyang Si , Ziwei Liu

This work presents DLO-Splatting, an algorithm for estimating the 3D shape of Deformable Linear Objects (DLOs) from multi-view RGB images and gripper state information through prediction-update filtering. The DLO-Splatting algorithm uses a…

Computer Vision and Pattern Recognition · Computer Science 2025-05-22 Holly Dinkel , Marcel Büsching , Alberta Longhini , Brian Coltin , Trey Smith , Danica Kragic , Mårten Björkman , Timothy Bretl

Direct mesh editing and deformation are key components in the geometric modeling and animation pipeline. Mesh editing methods are typically framed as optimization problems combining user-specified vertex constraints with a regularizer that…

Graphics · Computer Science 2024-08-05 Tianhao Xie , Eugene Belilovsky , Sudhir Mudur , Tiberiu Popa

3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Jiaqi Yao , Zhongmiao Yan , Jingyi Xu , Songpengcheng Xia , Yan Xiang , Ling Pei

Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference alignment loss. However, our systematic empirical research and…

Information Retrieval · Computer Science 2026-05-28 Chu Zhao , Enneng Yang , Jianzhe Zhao , Guibing Guo

A key challenge in music generation models is their lack of direct alignment with human preferences, as music evaluation is inherently subjective and varies widely across individuals. We introduce MR-FlowDPO, a novel approach that enhances…

Sound · Computer Science 2025-12-16 Alon Ziv , Sanyuan Chen , Andros Tjandra , Yossi Adi , Wei-Ning Hsu , Bowen Shi

Recent advancements in human preference optimization, initially developed for Language Models (LMs), have shown promise for text-to-image Diffusion Models, enhancing prompt alignment, visual appeal, and user preference. Unlike LMs,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Alexander Gambashidze , Anton Kulikov , Yuriy Sosnin , Ilya Makarov

A core capability for robot manipulation is reasoning over where and how to stably place objects in cluttered environments. Traditionally, robots have relied on object-specific, hand-crafted heuristics in order to perform such reasoning,…

Robotics · Computer Science 2023-10-27 Takuma Yoneda , Tianchong Jiang , Gregory Shakhnarovich , Matthew R. Walter