Refining Few-Step Text-to-Multiview Diffusion via Reinforcement Learning
School of Computer Science, National Engineering Research Center for Multimedia Software and Hubei Key Laboratory of Multimedia and Network Communication Engineering, Wuhan University(计算机学院、多媒体软件国家工程研究中心和湖北多媒体与网络通信工程重点实验室、武汉大学);School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University(中山大学信息科学与技术学院深圳校区);Tencent Inc.(腾讯公司);Xiaomi Inc., China(小米公司,中国)
Ziyi Zhang, Li Shen, Deheng Ye, Yong Luo, Huangxuan Zhao, Meng Liu, Wei Yu, Lefei Zhang
Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation quality, such as per-view fidelity and cross-view consistency. Reinforcement learning (RL) finetuning offers a potential solution, yet existing approaches designed for single-image diffusion do not readily extend to the few-step T2MV setting, as they neglect cross-view coordination and suffer from weak learning signals in few-step regimes. To address this, we propose MVC-ZigAL, a tailored RL finetuning framework for few-step T2MV diffusion models. Specifically, its core insights are: (1) a new MDP formulation that jointly models all generated views and assesses their collective quality via a joint-view reward; (2) a novel advantage learning strategy that exploits the performance gains of a self-refinement sampling scheme over standard sampling, yielding stronger learning signals for effective RL finetuning; and (3) a unified RL framework that extends advantage learning with a Lagrangian dual formulation for multiview-constrained optimization, balancing single-view and joint-view objectives through adaptive primal-dual updates under a self-paced threshold curriculum that harmonizes exploration and constraint enforcement. Collectively, these designs enable robust and balanced RL finetuning for few-step T2MV diffusion models, yielding substantial gains in both per-view fidelity and cross-view consistency. Code is available at https://github.com/ZiyiZhang27/MVC-ZigAL.
IVR-R1: Refining Trajectories through Iterative Visual-Grounded Reasoning in Reinforcement Learning
Hangzhou International Innovation Institute, Beihang University(北京航空航天大学杭州国际创新研究院);School of Artificial Intelligence, Beihang University(北京航空航天大学人工智能学院);Kuaishou Technology(快手科技);Shenzhen Institute of Advanced Integration Technology, Shenzhen(深圳先进集成技术研究院)
Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM
School of Teacher Education, Nanjing University of Information Science and Technology, China(南京信息工程大学教师教育学院);Nanyang Technological University, Singapore(新加坡南洋理工大学);Singapore Management University, Singapore(新加坡管理大学)
GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching
City University of Hong Kong(香港城市大学);Jilin University(吉林大学);Zhejiang University of Technology(浙江工业大学);Southern University of Science and Technology(南方科技大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Alibaba Group(阿里巴巴集团)
Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization
Leibniz University Hannover(汉诺威莱布尼茨大学);Jožef Stefan International Postgraduate School(约热夫·斯泰凡国际研究生学院);Jožef Stefan Institute(约热夫·斯泰凡研究所);L3S Research Center(L3S研究中心)
Fisher Decorator: Refining Flow Policy via A Local Transport Map
University College London(伦敦大学学院);Shanghai Jiao Tong University(上海交通大学);King’s College London(伦敦国王学院);Peking University(北京大学);Shanghai University of Finance and Economics(上海财经大学);Imperial College London(伦敦帝国学院)
Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory
University of California, Santa Barbara(加州大学圣巴巴拉分校);Jefferson National Laboratory(杰斐逊国家实验室);Pacific Northwest National Laboratory(太平洋西北国家实验室);Oak Ridge National Laboratory(橡树岭国家实验室)
RLGT: A reinforcement learning framework for extremal graph theory
Faculty of Electronic Engineering, University of Niš(尼什大学电子工程学院);Faculty of Mathematics, Natural Sciences and Information Technologies, University of Primorska(普里摩尔卡大学数学、自然科学与信息科技学院);Mathematical Institute of the Serbian Academy of Sciences and Arts(塞尔维亚科学院数学研究所)
Deep Reinforcement Learning for Dynamic Origin-Destination Matrix Estimation in Microscopic Traffic Simulations Considering Credit Assignment
Department of Civil and Environmental Engineering, Seoul National University(首尔国立大学土木与环境工程系);Institute of Construction and Environmental Engineering, Seoul National University(首尔国立大学建设与环境工程院);Department of Civil, Environmental, and Geo-Engineering, University of Minnesota(明尼苏达大学土木、环境与地球工程系)
Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization
C 2 DL, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉学科学院);Department of Computer Science and Technology, Tsinghua University(清华大学计算机科学与技术系)