Double perovskites (DPs) are promising candidates for sustainable energy technologies due to their compositional tunability and compatibility with low-energy fabrication, yet their vast design space poses a major challenge for conditional materials discovery. This work introduces a multi-agent, text gradient-driven framework that performs DP composition generation under natural-language conditions by integrating three complementary feedback sources: LLM-based self-evaluation, DP-specific domain knowledge-informed feedback, and ML surrogate-based feedback. Analogous to how knowledge-informed machine learning improves the reliability of conventional data-driven models, our framework incorporates domain-informed text gradients to guide the generative process toward physically meaningful regions of the DP composition space. Systematic comparison of three incremental configurations, (i) pure LLM generation, (ii) LLM generation with LLM reasoning-based feedback, and (iii) LLM generation with domain knowledge-guided feedback, shows that iterative guidance from knowledge-informed gradients improves stability-condition satisfaction without additional training data, achieving over 98% compositional validity and up to 54% stable or metastable candidates, surpassing both the LLM-only baseline (43%) and prior GAN-based results (27%). Analyses of ML-based gradients further reveal that they enhance performance in in-distribution (ID) regions but become unreliable in out-of-distribution (OOD) regimes. Overall, this work provides the first systematic analysis of multi-agent, knowledge-guided text gradients for DP discovery and establishes a generalizable blueprint for MAS-driven generative materials design aimed at advancing sustainable technologies.
SURGIN: SURrogate-guided Generative INversion for subsurface multiphase flow with quantified uncertainty
Department of Geotechnical Engineering, College of Civil Engineering, Tongji University(同济大学土木工程学院地质工程系);Key Laboratory of Geotechnical and Underground Engineering of Ministry of Education, Tongji University(教育部同济大学地质与地下工程重点实验室);Physical Science and Engineering Division, King Abdullah University of Science and Technology (KAUST)(卡布斯科学与技术大学(KAUST)物理科学与工程系);State Key Laboratory of Marine Geology, Tongji University(同济大学海洋地质国家重点实验室);Tencent SSV(腾讯SSV);Tencent SD(腾讯SD)
CoPHo: Classifier-guided Conditional Topology Generation with Persistent Homology
School of Cyberspace Security, Beijing University of Posts and Telecommunications(网络安全学院,北京邮电大学);State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications(网络与交换技术国家重点实验室,北京邮电大学);School of Computer Science (National Pilot Software Engineering School), Beijing University of Posts and Telecommunications(计算机学院(国家级试点软件工程学院),北京邮电大学)
Conditional generation of antibody sequences with classifier-guided germline-absorbing discrete diffusion
Paul G. Allen School of Computer Science and Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);Life Sciences, Amazon Web Services(亚马逊网络服务生命科学)
Gradient-Guided Conditional Diffusion Models for Private Image Reconstruction: Analyzing Adversarial Impacts of Differential Privacy and Denoising
School of Computer and Big Data, Minjiang University(闽江学院计算机与大数据学院);School of Information, Renmin University of China(中国人民大学信息学院);RMIT University(皇家墨尔本理工大学);Victoria University(维多利亚大学)
Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University(教育区块链与智能技术重点实验室,教育部,广西师范大学);Guangxi Key Lab of Multi-Source Information Mining and Security, Guangxi Normal University(广西多源信息挖掘与安全重点实验室,广西师范大学);School of Computer Science and Technology, Hainan University(海南大学计算机科学与技术学院);UniSA STEM, University of South Australia(南澳大利亚大学UniSA STEM)
Plasma-CycleGAN: Plasma Biomarker-Guided MRI to PET Cross-modality Translation Using Conditional CycleGAN
School of Computing and Augmented Intelligence, Arizona State University(亚利桑那州立大学计算与增强智能学院);Banner Alzheimer’s Institute(班纳阿尔茨海默病研究所);Basis Scottsdale(斯科茨代尔贝斯机构);College of Health Solutions, Arizona State University(亚利桑那州立大学健康解决方案学院);Mayo Clinic Arizona(梅奥诊所亚利桑那州分院)
Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data
Seoul National University(首尔国立大学)
我们提出了Guided-TTS 2,一个基于扩散的生成模型,用于使用未转录数据的高质量自适应TTS。Guided-TTS 2将说话者条件扩散模型与说话者相关音素分类器相结合,用于自适应文本到语音。我们训练的扬声器条件扩散模型的大规模未转录的数据集的无分类器引导方法,并进一步微调的扩散模型的参考语音的目标扬声器的适应,这只需要40秒。我们证明,引导TTS 2表现出相当的性能,高质量的单扬声器TTS基线的语音质量和扬声器相似性,只有十秒的未转录数据。我们进一步表明,即使使用zero-shot自适应设置,Guided-TTS 2在多说话者数据集上的性能也优于自适应TTS基线。Guided-TTS 2仅使用未转录的语音就能适应广泛的语音,这使得能够使用\textit{"The Lord of the Rings"}中的咕噜等非人类角色的语音进行自适应TTS。
Generalizable Face Landmarking Guided by Conditional Face Warping
School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);Key Laboratory of Artificial Intelligence, Ministry of Education, Shanghai(上海 教育部人工智能重点实验室)
Conditional Vendi Score: Prompt-Aware Diversity Evaluation for Generative AI Models and LLMs
Department of Computer Science and Engineering, The Chinese University of Hong Kong(计算机科学与工程系,香港中文大学);Department of Information Engineering, The Chinese University of Hong Kong(信息工程系,香港中文大学)
针对文本提示引导的生成模型,提出条件 Vendi 和条件 RKE 分数,通过条件熵分离模型自身多样性,并证明收敛性及在多个任务中恢复真实多样性排序。
Discovery of Interpretable Physical Laws in Materials via Language-Model-Guided Symbolic Regression
Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Physics(物理学院);Hefei National Laboratory(合肥国家实验室);Institute for Advanced Study in Physics(物理高级研究学院);Shenzhen Institute of Advanced Technology(深圳先进技术研究院)
Mask, Sample, Revise: A Revisable CTMC Inference Stack for Guided Discrete Flow Matching Text-to-Speech
Federal University of Goiás(戈亚斯联邦大学);Federal University of Uberlândia(乌贝兰迪亚联邦大学);University of São Paulo(圣保罗大学);University of Brasília(巴西利亚大学);University of California, Berkeley(加利福尼亚大学伯克利分校)
Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning
Stanford University(斯坦福大学);North China Electric Power University(华北电力大学);University of Adelaide(阿德莱德大学);University of Technology Sydney(悉尼技术大学);University of Science and Technology of China(中国科学技术大学)