图像生成

LOTA: Bit-Planes Guided AI-Generated Image Detection

Hongsong Wang, Renxi Cheng, Yang Zhang, Chaolei Han, Jie Gui

机构 * School of Computer Science and Engineering, Southeast University, Nanjing 210096, China（东南大学计算机科学与工程学院） ； Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及其交叉应用重点实验室） ； School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China（东南大学网络安全工程学院） ； School of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China（深圳大学计算机科学与软件工程学院） ； Purple Mountain Laboratories, Nanjing 210000, China（紫金山实验室） ； Engineering Research Center of Blockchain Application, Supervision And Management (Southeast University), Ministry of Education, China（区块链应用、监督与管理工程研究中心） 纠错

专题命中 扩散模型 ：image generation(abstract)；diffusion(abstract)；分类 cs.CV

Comments Published in the ICCV2025, COde is https://github.com/hongsong-wang/LOTA

WorldSplat: Gaussian-Centric Feed-Forward 4D Scene Generation for Autonomous Driving

Ziyue Zhu, Zhanqian Wu, Zhenxin Zhu, Lijun Zhou, Haiyang Sun, Bing Wan, Kun Ma, Guang Chen, Hangjun Ye, Jin Xie, jian Yang

机构 * Nankai University（南开大学） ； Nanjing University, Suzhou（南京大学苏州校区） 纠错

专题命中 扩散模型 ：diffusion(abstract)；分类 cs.CV

UniEgoMotion: A Unified Model for Egocentric Motion Reconstruction, Forecasting, and Generation

Chaitanya Patel, Hiroki Nakamura, Yuta Kyuragi, Kazuki Kozuka, Juan Carlos Niebles, Ehsan Adeli

机构 * Stanford University（斯坦福大学） ； Panasonic Holdings Corporation（松下控股公司） ； Panasonic R&D Company of America（美国松下研发公司） 纠错

专题命中 扩散模型 ：diffusion(abstract)；分类 cs.CV

Comments ICCV 2025. Project Page: https://chaitanya100100.github.io/UniEgoMotion/

Emergent Visual Grounding in Large Multimodal Models Without Grounding Supervision

Shengcao Cao, Liang-Yan Gui, Yu-Xiong Wang

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） 纠错

专题命中 扩散模型 ：diffusion(abstract)；分类 cs.CV

Comments ICCV 2025 Findings

Transport with noise in dilute gases: Effect of Langevin thermostat on transport coefficients

Alejandro Alés, Juan Ignacio Cerato, Leandro Marchioni, Miguel Hoyuelos

专题命中 扩散模型 ：diffusion(abstract)

Comments 10 pages, 7 figures, preprint

Multiscale Models For Perovskite Optimisation

Philippe Baranek, James P. Connolly, Antoine Gissler, Philip Schulz, Michel Rérat, Roberto Dovesi

专题命中 扩散模型 ：diffusion(abstract)

Journal ref EUPVSEC 2025 42nd European Photovoltaic Solar Energy Conference and Exhibition, WIP Renewable Energies, Sep 2025, Bilbao, Spain

Propagation speed of traveling waves for diffusive Lotka-Volterra system with strong competition

Ken-Ichi Nakamura, Toshiko Ogiwara

专题命中 扩散模型 ：diffusion(abstract)

Comments 15 pages, 2 figures

Low-Energy DNA Bubble Dynamics via the Quantum Coulomb Potential

Juan D. García-Muñoz, A. Contreras-Astorga, L. M. Nieto

专题命中 扩散模型 ：diffusion(abstract)

Latent Retrieval Augmented Generation of Cross-Domain Protein Binders

Zishen Zhang, Xiangzhe Kong, Wenbing Huang, Yang Liu

机构 * Dept. of Comp. Sci. & Tech., Tsinghua University（计算机科学与技术系，清华大学） ； Institute for AIR, Tsinghua University（空气智能研究所，清华大学） ； Gaoling School of Artificial Intelligence, Renmin University of China（北京理工大学人工智能学院） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Synaptic shot-noise triggers fast and slow global oscillations in balanced neural networks

Denis S. Goldobin, Maria V. Ageeva, Matteo di Volo, Ferdinand Tixidre, Alessandro Torcini

专题命中 扩散模型 ：diffusion(abstract)

Comments 28 pages, 14 figures, submitted to Physical Review E

Journal ref Physical Review E 112, 034301 (2025)

Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping

Pu Yang, Yunzhen Feng, Ziyuan Chen, Yuhang Wu, Zhuoyuan Li

机构 * Peking University（北京大学） ； New York University（纽约大学） ； UC Berkeley（加州大学伯克利分校） ； National University of Singapore（新加坡国立大学） 纠错

专题命中 扩散模型 ：diffusion(abstract)

Comments NeurIPS 2025 (spotlight)

Langevin equations and a geometric integration scheme for the overdamped limit of rotational Brownian motion of axisymmetric particles

Felix Höfling, Arthur V. Straube

专题命中 扩散模型 ：diffusion(abstract)

Comments accepted for publication

Journal ref Phys. Rev. Research 7, 043034 (2025)

The bi-dimensional Directed IDLA forest

Nicolas Chenavier, David Coupier, Arnaud Rousselle

专题命中 扩散模型 ：diffusion(abstract)

Comments 40 pages, 7 figures, corrected version

ComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation

Guocheng Gordon Qian, Daniil Ostashev, Egor Nemchinov, Avihay Assouline, Sergey Tulyakov, Kuan-Chieh Jackson Wang, Kfir Aberman

机构 * Snap Inc. 纠错

专题命中 可控生成 ：image generation(title)；text-to-image(abstract)；diffusion(abstract)；image synthesis(abstract)

Comments Accepted to SIGGRAPH Asia 2025, webpage: https://snap-research.github.io/composeme/

WithAnyone: Towards Controllable and ID Consistent Image Generation

Hengyuan Xu, Wei Cheng, Peng Xing, Yixiao Fang, Shuhan Wu, Rui Wang, Xianfang Zeng, Daxin Jiang, Gang Yu, Xingjun Ma, Yu-Gang Jiang

机构 * Fudan University（复旦大学） ； StepFun Project（StepFun项目） ； MultiID-2M ； MultiID-Bench 纠错

专题命中 可控生成 ：image generation(title)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Comments 23 Pages; Project Page: https://doby-xu.github.io/WithAnyone/; Code: https://github.com/Doby-Xu/WithAnyone

Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures

Yuancheng Xu, Wenqi Xian, Li Ma, Julien Philip, Ahmet Levent Taşel, Yiwei Zhao, Ryan Burgert, Mingming He, Oliver Hermann, Oliver Pilarski, Rahul Garg, Paul Debevec, Ning Yu

机构 * Eyeline Labs（Eyeline实验室） 纠错

专题命中 可控生成 ：diffusion(title,abstract)；分类 cs.CV

Comments Accepted to SIGGRAPH Asia 2025

ScaleWeaver: Weaving Efficient Controllable T2I Generation with Multi-Scale Reference Attention

Keli Liu, Zhendong Wang, Wengang Zhou, Shaodong Xu, Ruixiao Dong, Houqiang Li

机构 * University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 可控生成 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；分类 cs.CV

Ponimator: Unfolding Interactive Pose for Versatile Human-human Interaction Animation

Shaowei Liu, Chuan Guo, Bing Zhou, Jian Wang

专题命中 可控生成 ：diffusion(abstract)；分类 cs.CV、cs.GR

Comments Accepted to ICCV 2025. Project page: https://stevenlsw.github.io/ponimator/

TOUCH: Text-guided Controllable Generation of Free-Form Hand-Object Interactions

Guangyi Han, Wei Zhai, Yuhang Yang, Yang Cao, Zheng-Jun Zha

机构 * University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 可控生成 ：diffusion(abstract)；分类 cs.CV

Exploring Image Representation with Decoupled Classical Visual Descriptors

Chenyuan Qu, Hao Chen, Jianbo Jiao

机构 * The MIx Group University of Birmingham, UK（米克斯小组英国伯明翰大学） ； University of Cambridge Cambridge, UK（剑桥大学） ； Allsee Technologies Ltd Birmingham, UK（Allsee技术有限公司） 纠错

专题命中 可控生成 ：image generation(abstract)；分类 cs.CV

Comments Accepted by The 36th British Machine Vision Conference (BMVC 2025)

Control of Conditional Processes and Fleming--Viot Dynamics

Philipp Jettkant

专题命中 可控生成 ：diffusion(abstract)

PIA: Deepfake Detection Using Phoneme-Temporal and Identity-Dynamic Analysis

Soumyya Kanti Datta, Tanvi Ranga, Chengzhe Sun, Siwei Lyu

机构 * University at Buffalo, SUNY Buffalo, NY, USA（布法罗大学） 纠错

专题命中 个性化与一致性 ：diffusion(abstract)；分类 cs.CV

CAP: Evaluation of Persuasive and Creative Image Generation

Aysan Aghazadeh, Adriana Kovashka

机构 * University of Pittsburgh（匹兹堡大学） 纠错

专题命中 图像生成评测 ：image generation(title,abstract)；text-to-image(abstract)；分类 cs.CV、cs.GR

FraQAT: Quantization Aware Training with Fractional bits

Luca Morreale, Alberto Gil C. P. Ramos, Malcolm Chadwick, Mehid Noroozi, Ruchika Chavhan, Abhinav Mehrotra, Sourav Bhattacharya

机构 * Samsung AI Center Cambridge, UK（三星人工智能中心） 纠错

专题命中 效率与蒸馏 ：diffusion(abstract)；image synthesis(abstract)；分类 cs.CV

Protenix-Mini+: efficient structure prediction model with scalable pairformer

Bo Qiang, Chengyue Gong, Xinshi Chen, Yuxuan Zhang, Wenzhi Xiao

机构 * University of Washington（华盛顿大学） 纠错

专题命中 效率与蒸馏 ：diffusion(abstract)

One-Step Flow Policy Mirror Descent

Tianyi Chen, Haitong Ma, Na Li, Kai Wang, Bo Dai

机构 * Georgia Institute of Technology（佐治亚理工学院） ； Harvard University（哈佛大学） 纠错

专题命中 效率与蒸馏 ：diffusion(abstract)