Generative Adversarial Networks and Image Synthesis

Latest papers

• Duality Models: An Embarrassingly Simple One-step Generation Paradigm

  Peng Sun, Xinyi Shang, Tao Lin, Zhiqiang Shen · 23 February 2026

  Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such methods introduce a target time $r$ alongside the current time $t$ to modulate outputs between a local multi-step derivat…

• Variational Distributional Neuron

  Yves Ruffenach · 23 February 2026

  We propose a proof of concept for a variational distributional neuron: a compute unit formulated as a VAE brick, explicitly carrying a prior, an amortized posterior and a local ELBO. The unit is no longer a deterministic scalar but a distribution: computing is no longer about propagating values, but…

• MIST: Mutual Information Estimation Via Supervised Training

  German Gritsai, Megan Richards, Maxime M\'eloux, Kyunghyun Cho, Maxime Peyrard · 23 February 2026

  We propose a fully data-driven approach to designing mutual information (MI) estimators. Since any MI estimator is a function of the observed sample from two random variables, we parameterize this function with a neural network (MIST) and train it end-to-end to predict MI values. Training is perform…

• Amortized Inference of Multi-Modal Posteriors using Likelihood-Weighted Normalizing Flows

  Rajneil Baruah · 23 February 2026

  We present a novel technique for amortized posterior estimation using Normalizing Flows trained with likelihood-weighted importance sampling. This approach allows for the efficient inference of theoretical parameters in high-dimensional inverse problems without the need for posterior training sample…

• Agentic Unlearning: When LLM Agent Meets Machine Unlearning

  Bin Wang, Fan Wang, Pingping Wang, Jinyu Cong, Yang Yu, Yilong Yin, Zhongyi Han, Benzheng Wei · 23 February 2026

  In this paper, we introduce \textbf{agentic unlearning} which removes specified information from both model parameters and persistent memory in agents with closed-loop interaction. Existing unlearning methods target parameters alone, leaving two critical gaps: (i) parameter-memory backflow, where re…

• Dual-Channel Attention Guidance for Training-Free Image Editing Control in Diffusion Transformers

  Guandong Li, Mengxia Ye · 23 February 2026

  Training-free control over editing intensity is a critical requirement for diffusion-based image editing models built on the Diffusion Transformer (DiT) architecture. Existing attention manipulation methods focus exclusively on the Key space to modulate attention routing, leaving the Value space -- …

• Avoid What You Know: Divergent Trajectory Balance for GFlowNets

  Pedro Dall'Antonia, Tiago da Silva, Daniel Csillag, Salem Lahlou, Diego Mesquita · 23 February 2026

  Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward function. However, learning efficiency is constrained by the model's ability to rapidly explore diverse high-probability r…

• Learning Flow Distributions via Projection-Constrained Diffusion on Manifolds

  Noah Trupin, Rahul Ghosh, Aadi Jangid · 23 February 2026

  We present a generative modeling framework for synthesizing physically feasible two-dimensional incompressible flows under arbitrary obstacle geometries and boundary conditions. Whereas existing diffusion-based flow generators either ignore physical constraints, impose soft penalties that do not gua…

• Generative Model via Quantile Assignment

  Georgi Hrusanov, Oliver Y. Ch\'en, Julien S. Bodelet · 23 February 2026

  Deep Generative models (DGMs) play two key roles in modern machine learning: (i) producing new information (e.g., image synthesis) and (ii) reducing dimensionality. However, traditional architectures often rely on auxiliary networks such as encoders in Variational Autoencoders (VAEs) or discriminato…

• Parallel Complex Diffusion for Scalable Time Series Generation

  Rongyao Cai, Yuxi Wan, Kexin Zhang, Ming Jin, Zhiqiang Ge, Qingsong Wen, Yong Liu · 23 February 2026

  Modeling long-range dependencies in time series generation poses a fundamental trade-off between representational capacity and computational efficiency. Traditional temporal diffusion models suffer from local entanglement and the $\mathcal{O}(L^2)$ cost of attention mechanisms. We address these limi…

• Synergizing Transport-Based Generative Models and Latent Geometry for Stochastic Closure Modeling

  Xinghao Dong, Huchen Yang, Jin-long Wu · 20 February 2026

  Diffusion models recently developed for generative AI tasks can produce high-quality samples while still maintaining diversity among samples to promote mode coverage, providing a promising path for learning stochastic closure models. Compared to other types of generative AI models, such as GANs and …

• DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

  Dahye Kim, Deepti Ghadiyaram, Raghudeep Gadde · 20 February 2026

  Diffusion Transformers (DiTs) have achieved state-of-the-art performance in image and video generation, but their success comes at the cost of heavy computation. This inefficiency is largely due to the fixed tokenization process, which uses constant-sized patches throughout the entire denoising phas…

• VP-VAE: Rethinking Vector Quantization via Adaptive Vector Perturbation

  Linwei Zhai, Han Ding, Mingzhi Lin, Cui Zhao, Fei Wang, Ge Wang, Wang Zhi, Wei Xi · 20 February 2026

  Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental to modern generative modeling, yet they often suffer from training instability and "codebook collapse" due to the inherent coupling of representation learning and discrete codebook optimization. In this paper, we propose VP-VAE (Vec…

• Di3PO - Diptych Diffusion DPO for Targeted Improvements in Image Generation

  Sanjana Reddy (Google), Ishaan Malhi (Google DeepMind), Sally Ma (Google DeepMind), Praneet Dutta (Google DeepMind) · 20 February 2026

  Existing methods for preference tuning of text-to-image (T2I) diffusion models often rely on computationally expensive generation steps to create positive and negative pairs of images. These approaches frequently yield training pairs that either lack meaningful differences, are expensive to sample a…

• Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation

  Ruchi Sandilya, Sumaira Perez, Charles Lynch, Lindsay Victoria, Benjamin Zebley, Derrick Matthew Buchanan, Mahendra T. Bhati, Nolan Williams, Timothy J. Spellman, Faith M. Gunning, Conor Liston, Logan Grosenick · 20 February 2026

  Diffusion models excel at generation, but their latent spaces are high dimensional and not explicitly organized for interpretation or control. We introduce ConDA (Contrastive Diffusion Alignment), a plug-and-play geometry layer that applies contrastive learning to pretrained diffusion latents using …

• A Theoretical Framework for Modular Learning of Robust Generative Models

  Corinna Cortes, Mehryar Mohri, Yutao Zhong · 20 February 2026

  Training large-scale generative models is resource-intensive and relies heavily on heuristic dataset weighting. We address two fundamental questions: Can we train Large Language Models (LLMs) modularly-combining small, domain-specific experts to match monolithic performance-and can we do so robustly…

• Unified Latents (UL): How to train your latents

  Jonathan Heek, Emiel Hoogeboom, Thomas Mensink, Tim Salimans · 20 February 2026

  We present Unified Latents (UL), a framework for learning latent representations that are jointly regularized by a diffusion prior and decoded by a diffusion model. By linking the encoder's output noise to the prior's minimum noise level, we obtain a simple training objective that provides a tight u…

• Inference-Time Search Using Side Information for Diffusion-Based Image Reconstruction

  Mahdi Farahbakhsh, Vishnu Teja Kunde, Dileep Kalathil, Krishna Narayanan, Jean-Francois Chamberland · 20 February 2026

  Diffusion models have been widely used as powerful priors for solving inverse problems. However, existing approaches typically overlook side information that could significantly improve reconstruction quality, especially in severely ill-posed settings. In this work, we propose a novel inference-time…

• Variational Grey-Box Dynamics Matching

  Gurjeet Sangra Singh, Frantzeska Lavda, Giangiacomo Mercatali, Alexandros Kalousis · 20 February 2026

  Deep generative models such as flow matching and diffusion models have shown great potential in learning complex distributions and dynamical systems, but often act as black-boxes, neglecting underlying physics. In contrast, physics-based simulation models described by ODEs/PDEs remain interpretable,…

• Stage-wise Dynamics of Classifier-Free Guidance in Diffusion Models

  Cheng Jin, Qitan Shi, Yuantao Gu · 19 February 2026

  Classifier-Free Guidance (CFG) is widely used to improve conditional fidelity in diffusion models, but its impact on sampling dynamics remains poorly understood. Prior studies, often restricted to unimodal conditional distributions or simplified cases, provide only a partial picture. We analyze CFG …

• Steering diffusion models with quadratic rewards: a fine-grained analysis

  Ankur Moitra, Andrej Risteski, Dhruv Rohatgi · 19 February 2026

  Inference-time algorithms are an emerging paradigm in which pre-trained models are used as subroutines to solve downstream tasks. Such algorithms have been proposed for tasks ranging from inverse problems and guided image generation to reasoning. However, the methods currently deployed in practice a…

• CHAI: CacHe Attention Inference for text2video

  Joel Mathew Cherian, Ashutosh Muralidhara Bharadwaj, Vima Gupta, Anand Padmanabha Iyer · 19 February 2026

  Text-to-video diffusion models deliver impressive results but remain slow because of the sequential denoising of 3D latents. Existing approaches to speed up inference either require expensive model retraining or use heuristic-based step skipping, which struggles to maintain video quality as the numb…

• Fast and Scalable Analytical Diffusion

  Xinyi Shang, Peng Sun, Jingyu Lin, Zhiqiang Shen · 19 February 2026

  Analytical diffusion models offer a mathematically transparent path to generative modeling by formulating the denoising score as an empirical-Bayes posterior mean. However, this interpretability comes at a prohibitive cost: the standard formulation necessitates a full-dataset scan at every timestep,…

• GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation

  Nicolas Salvy, Hugues Talbot, Bertrand Thirion · 19 February 2026

  Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset representations in these spaces are affected by the hubness phenomenon, which distorts nearest neighbor relationships and biases distance-based metrics. Buildin…

• DiffusionBlocks: Block-wise Neural Network Training via Diffusion Interpretation

  Makoto Shing, Masanori Koyama, Takuya Akiba · 19 February 2026

  End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability. Existing block-wise training methods offer means to alleviate this problem, but they rely on ad-hoc local objectives and remain largely unexplored beyond classific…