Generative Models

Follow this topic Ask about this topic

Recent momentum

-30%

46 papers in the last 28 days · 0.7% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

11 new papers

A weekly snapshot of new work published in Generative Models.

Period ending 2026-09-14

12 new papers

A weekly snapshot of new work published in Generative Models.

Period ending 2026-09-07

16 new papers

A weekly snapshot of new work published in Generative Models.

718 papers

Latest in Generative Models

Browse all topics →

Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models
May 20, 2026Kesong Li, Yixuan Xu, Kuo-kun Tseng +3Text-To-Image Diffusion Models Text-To-Image
Efficient Learning of Deep State Space Models via Importance Smoothing
May 20, 2026John-Joseph Brady, Nikolas Nusken, Yunpeng LiState Space Models Variational Inference
What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
May 20, 2026Hangyu Lin, Chao Wen, Chengming Xu +4Multimodal Alignment Ava-Vlm
OpenSeisML: Open Large-Scale Real Seismic and well-log Dataset for Generative AI
May 19, 2026Ipsita Bhar, Huseyin Tuna Erdinc, Thales Souza +2Full Waveform Inversion Generative Models
When Does Model Collapse Occur in Structured Interactive Learning?
May 19, 2026Yuchen Wu, Kangjie Zhou, Weijie SuCollapse Generative Models
Tail Annealing for Heavy-Tailed Flow Matching
May 19, 2026Jean PachebatLong-Tailed Distribution Conditional Flow Matching
When Preference Labels Fall Short: Aligning Diffusion Models from Real Data
May 19, 2026Weiyan Chen, Weijian Deng, Yao Xiao +5Preference Alignment Generative Models
AirfoilGen: A valid-by-construction and performance-aware latent diffusion model for airfoil generation
May 19, 2026Zhijie Yang, Min Tang, Peng Du +1Aerodynamics Generative Models
Latent Laplace Diffusion for Irregular Multivariate Time Series
May 19, 2026Zinuo You, Jin Zheng, John CartlidgeLong-Horizon Forecasting Time Series
Mechanisms of Misgeneralization in Physical Sequence Modeling
May 19, 2026Kento Nishi, Raphael Tang, Karun Kumar +2Generative Models Sequence Modeling
Adynamical systems view of training generativemodels and the memorization phenomenon
May 19, 2026Siva Athreya, Chiranjib Bhattacharya, Vivek S. BorkarStochastic Gradient Descent Memorization
Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian
May 19, 2026Wenpin Tang, Nizar Touzi, Zikun Zhang +1Stochastic Differential Equations Diffusion Dynamics
Multi-Scale Generative Modeling with Heat Dissipation Flow Matching
May 19, 2026Jun Ma, Hanquan Zhang, Yanjun Qin +2Discrete Diffusion Model Generative Models
The Economics of Model Collapse: Equilibrium, Welfare, and Optimal Provenance Subsidies in Synthetic Data Markets
May 19, 2026Gustav Olaf Yunus Laitinen-Fredriksson Lundström-ImanovSynthetic Data Distributional Fidelity
What Makes Synthetic Data Effective in Image Segmentation
May 19, 2026Jinjin Zhang, Xiefan Guo, Yizhou Jin +2Synthetic Image Detection Synthetic Data
Generative Pseudo-Force Fields for Molecular Generation
May 18, 2026Stefaan Simon Pierre Hessmann, Khaled Kahouli, Stefan Gugler +4Molecular Generation Conformational Ensembles
Semantic Generative Tuning for Unified Multimodal Models
May 18, 2026Songsong Yu, Yuxin Chen, Ying Shan +1Unified Multimodal Models Generative Models
Position: Weight Space Should Be a First-Class Generative AI Modality
May 18, 2026Zhangyang Wang, Peihao Wang, Kai WangModel Weights Generative Models
Flowing with Confidence
May 18, 2026Friso de Kruiff, Dario Coscia, Max Welling +1Generative Models Confidence Calibration
Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models
May 18, 2026Abdelhakim Ziani, Andras Horvath, Paolo BallariniLong-Tailed Distribution Generative Models
Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
May 18, 2026Grigory Bartosh, Teodora Pandeva, Sushrut Karmalkar +1Generative Models Factor
Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models
May 18, 2026Sihan Ma, Siyuan Liang, Dacheng Tao3D Assets 3D Generation
GenTS: A Comprehensive Benchmark Library for Generative Time Series Models
May 18, 2026Chenxi Wang, Xiaorong Wang, Peiyang Li +1Synthetic Time Series Time Series
TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates
May 17, 2026Meysam Alishahi, Yan Zheng, Junpeng Wang +2Synthetic Tabular Data Gaussian Copula
Venom: A PyTorch Generative Modeling Toolkit
May 17, 2026Liang YanGenerative Models Variational Autoencoder
Scale-Equivariant Generative Forecasting: Weight-Tied Dilated Convolutions, Wavelet Scattering Inputs, and Spectral-Consistency Training for Self-Similar Time Series
May 17, 2026Andrea MorandiDiscrete Wavelet Transform Exact Equivariance
PFlow-T: A Persistence-Driven Forward Process for Topology-Controlled Generation
May 17, 2026Snigdha Chandan KhilarDiscrete Diffusion Model Persistent Homology
Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling
May 17, 2026Tianyue Yang, Sandro Tacchella, Xiao XueGenerative Models Discrete Diffusion Model
SpecSem-Net: Integrating Spectral and Semantic Features for Robust AI-generated Video Detection
May 17, 2026Zixi Wei, Huixuaun Zhang, Xiaojun WanAi-Generated Image Detection Generative Models
Image-to-Video Diffusion: From Foundations to Open Frontiers
May 17, 2026Xianlong Wang, Wenbo Pan, Shijia Zhou +6Long Video Generation Large-Scale Image Generation
Drift Flow Matching
May 17, 2026Chenrui Ma, Xi Xiao, Lin Zhao +3Generative Models Discrete Diffusion Model
Vocabulary-size-independent Convergence of Discrete Diffusion Models: adjoint equations induce the right space
May 17, 2026Kelvin Kan, Xingjian Li, Benjamin J. Zhang +3Discrete Diffusion Model Generative Models
Weighted Flow Matching and Physics-Informed Nonlinear Filtering for Parameter Estimation in Digital Twins
May 16, 2026Yasar Yanik, Himadri Basu, Ricardo G. Sanfelice +1Digital Twin Framework Digital Twins
HYVINT: Intensity-Driven Hypergraph Generation with Variational Representations
May 16, 2026Xinyi Hong, Shuntuo Xu, Zhou YuHypergraphs Generative Models
A Survey of Advancing Audio Super-Resolution and Bandwidth Extension from Discriminative to Generative Models
May 15, 2026Ningyuan Yang, Yize Li, Diego A. Cuji +4Generative Super-Resolution Autoregressive Diffusion
GenAI-FDIA: Physics-Informed Generative Models for False Data Injection Attacks
May 15, 2026Mohammad A. Razzaque, Muta Tah HiraFault Injection Experiments Power Systems
StAD: Stein Amortized Divergence for Fast Likelihoods with Diffusion and Flow
May 15, 2026Gurjeet Jagwani, Stephen Thorp, Sinan Deger +1Likelihood Normalizing Flows
Dynamics-Level Watermarking of Flow Matching Models with Random Codes
May 15, 2026Shuchan WangWatermarks Watermarking
Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning
May 15, 2026Mengye RenCreativity Generative Models
ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation
May 15, 2026Qing Huang, Zhipei Xu, Xuanyu Zhang +2Ai-Generated Image Detection Face Forgery Detection
Intrinsic Wasserstein Rates for Score-Based Generative Models on Smooth Manifolds
May 15, 2026Guoji Fu, Taiji Suzuki, Wee Sun Lee +1Statistical Manifold Wasserstein Distance
CrystalBoltz: End-to-End Protein Structure Determination via Experiment-Guided Diffusion for X-Ray Crystallography
May 15, 2026Minseo Kim, Huanghao Mai, Jay Shenoy +3Crystallographic Plane Indices Protein Data Bank
$f$ -Trajectory Balance: A Loss Family for Tuning GFlowNets, Generative Models, and LLMs with Off- and On-Policy Data
May 14, 2026Jake Fawkes, Jason HartfordGenerative Flow Networks Time-Step-Wise Learnable Surrogate Gradient Function
Transformer Scalability Crisis: The First Comprehensive Empirical Analysis of Performance Walls in Modern Language Models
May 14, 2026Mahdi Naser Moghadasi, Faezeh GhaderiTransformer Architectures Large Models
Controllable Molecular Generative Foundation Models
May 14, 2026Yihan Zhu, Yuhan Liu, Weijiang Li +2Molecular Generation Generative Models
One Pass Is Not Enough: Recursive Latent Refinement for Generative Models
May 14, 2026Mehdi Esmaeilzadeh, Alexia Jolicoeur-Martineau, Chirag Vashist +1Large-Scale Image Generation Generative Models
Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
May 14, 2026Qiang Liu, Felix Koehler, Benjamin Holzschuh +1Masked Autoencoders 3D Foundation Models
Separating Intrinsic Ambiguity from Estimation Uncertainty in Deep Generative Models for Linear Inverse Problems
May 14, 2026Yuxin Guo, Dongrui Deng, Pulkit GroverCalibrated Uncertainty Ill-Posed Inverse Problem
Persian MusicGen: A Large-Scale Dataset and Culturally-Aware Generative Model for Persian Music
May 14, 2026Mohammad Hossein Sameti, Diba Hadi Esfangereh, Sepehr Harfi Moridani +2Music Generation Persian
Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement
May 14, 2026Nian Liu, Nikita Kazeev, Stephen Gregory Dale +8Crystal Molecular Generation
The Rate-Distortion-Polysemanticity Tradeoff in SAEs
May 14, 2026Tommaso Mencattini, Francesco Montagna, Francesco LocatelloSemantic Representations Mechanistic Interpretability
Privacy Evaluation of Generative Models for Trajectory Generation
May 14, 2026Stavros Bouras, Ioannis Kontopoulos, Chiara Pugliese +5Generative Models Latent Trajectories
Action-Inspired Generative Models
May 14, 2026Eshwar R. A., Debnath PalGenerative Models Generative Adversarial Network
A plug-and-play generative framework for multi-satellite precipitation estimation
May 14, 2026Yunfan Yang, Haofei Sun, Xiuyu Sun +7Precipitation Satellite Data
CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation
May 14, 2026Yuyang Wu, Stefano Falletta, Delia McGrath +1Crystal Structure Crystallographic Plane Indices
Generative Deep Learning for Computational Destaining and Restaining of Unregistered Digital Pathology Images
May 14, 2026Aarushi Kulkarni, Alarice Lowe, Pratik ShahComputational Pathology Dual-Domain Equivariant Generative Adversarial Network
Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
May 13, 2026Luis Lara, Aristides Milios, Zhi Hao Luo +5Floor Plan Generation Large Language Model Planning
Synthetic Sociality: How Generative Models Privatize the Social Fabric
May 13, 2026Ana Dodik, Moira WeigelSocial Dynamics Generative Models
SurF: A Generative Model for Multivariate Irregular Time Series Forecasting
May 13, 2026Mohammad R. Rezaei, Tejas Balaji, Rahul G. KrishnanMultivariate Time Series Forecasting Determinantal Point Process
Conditional Attribute Estimation with Autoregressive Sequence Models
May 13, 2026Erica Stutz, Giacomo Marino, Daniella Meeker +2Next-Token Prediction Autoregressive Model

May 20, 2026 · cs.CVJ/K move · Enter open · S save

Linear-DPO: Linear Direct Preference Optimization for Diffusion and Flow-Matching Generative Models

Kesong Li, Yixuan Xu, Kuo-kun Tseng, Weiyi Lu+2

School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China · Alibaba Group, Hangzhou, Zhejiang, China

Direct Preference Optimization (DPO) is successful for alignment in LLMs but still faces challenges in text-to-image generation. Existing studies are confined to denoising diffusion models while overlooking flow-matching, and suffer from an objective mismatch when applying discrete NLP-based DPO to regression-based generative tasks.\ In this paper, we derive a generalized DPO objective that covers both diffusion and flow-matching via a unified reverse-time SDE framework, and point out from a gradient perspective that the standard DPO objective is suboptimal for text-to-image generation. Consequently, we propose Linear-DPO, which replaces the aggressive sigmoid-based utility function with a sustained linear utility and incorporates an EMA-updated reference model. Qualitative and quantitative experiments on diffusion models (SD1.5, SDXL) and flow-matching model (SD3-Medium) demonstrate the superiority of our approach over existing baselines.

Text-To-Image Diffusion Models Text-To-Image Generative Models Direct Preference Optimization

Open paper Ask about it PDF

Recent momentum

Neighbouring directions

Recent digests

11 new papers

12 new papers

16 new papers

Latest in Generative Models