Generative Adversarial Networks and Image Synthesis

Latest papers

• V-Co: A Closer Look at Visual Representation Alignment via Co-Denoising

  Han Lin, Xichen Pan, Zun Wang, Yue Zhang, Chu Wang, Jaemin Cho, Mohit Bansal · 18 March 2026

  Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained autoencoders. However, standard pixel-space diffusion models receive relatively weak semantic supervision and are not explicitly designed to capture high-lev…

• When Generative Augmentation Hurts: A Benchmark Study of GAN and Diffusion Models for Bias Correction in AI Classification Systems

  Shesh Narayan Gupta, Nik Bear Brown · 18 March 2026

  Generative models are widely used to compensate for class imbalance in AI training pipelines, yet their failure modes under low-data conditions are poorly understood. This paper reports a controlled benchmark comparing three augmentation strategies applied to a fine-grained animal classification tas…

• CompDiff: Hierarchical Compositional Diffusion for Fair and Zero-Shot Intersectional Medical Image Generation

  Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan, Michel Dumontier · 18 March 2026

  Generative models are increasingly used to augment medical imaging datasets for fairer AI. Yet a key assumption often goes unexamined: that generators themselves produce equally high-quality images across demographic groups. Models trained on imbalanced data can inherit these imbalances, yielding de…

• Demystifing Video Reasoning

  Ruisi Wang, Zhongang Cai, Fanyi Pu, Junxiang Xu, Wanqi Yin, Maijunxian Wang, Ran Ji, Chenyang Gu, Bo Li, Ziqi Huang, Hokin Deng, Dahua Lin, Ziwei Liu, Lei Yang · 18 March 2026

  Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a Chain-of-Frames (CoF) mechanism, where reasoning is assumed to unfold sequentially across video frames. In this work, w…

• Transition Flow Matching

  Chenrui Ma · 18 March 2026

  Mainstream flow matching methods typically focus on learning the local velocity field, which inherently requires multiple integration steps during generation. In contrast, Mean Velocity Flow models establish a relationship between the local velocity field and the global mean velocity, enabling the l…

• OrthoAI v2: From Single-Agent Segmentation to Dual-Agent Treatment Planning for Clear Aligners

  Lansiaux Edouard, Leman Margaux · 18 March 2026

  We present OrthoAI v2, the second iteration of our open-source pipeline for AI-assisted orthodontic treatment planning with clear aligners, substantially extending the single-agent framework previously introduced. The first version established a proof-of-concept based on Dynamic Graph Convolutional …

• Diffusion Models for Joint Audio-Video Generation

  Alejandro Paredes La Torre · 18 March 2026

  Multimodal generative models have shown remarkable progress in single-modality video and audio synthesis, yet truly joint audio-video generation remains an open challenge. In this paper, I explore four key contributions to advance this field. First, I release two high-quality, paired audio-video dat…

• Unlearning for One-Step Generative Models via Unbalanced Optimal Transport

  Hyundo Choi, Junhyeong An, Jinseong Park, Jaewoong Choi · 18 March 2026

  Recent advances in one-step generative frameworks, such as flow map models, have significantly improved the efficiency of image generation by learning direct noise-to-data mappings in a single forward pass. However, machine unlearning for ensuring the safety of these powerful generators remains enti…

• Fast-WAM: Do World Action Models Need Test-time Future Imagination?

  Tianyuan Yuan, Zibin Dong, Yicheng Liu, Hang Zhao · 18 March 2026

  World Action Models (WAMs) have emerged as a promising alternative to Vision-Language-Action (VLA) models for embodied control because they explicitly model how visual observations may evolve under action. Most existing WAMs follow an imagine-then-execute paradigm, incurring substantial test-time la…

• Form Follows Function: Recursive Stem Model

  Navid Hakimi · 18 March 2026

  Recursive reasoning models such as Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM) show that small, weight-shared networks can solve compute-heavy and NP puzzles by iteratively refining latent states, but their training typically relies on deep supervision and/or long unrolls that …

• Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods

  Hong Jeong · 18 March 2026

  Frozen encoder--decoder language models are stateless: the latent representation is discarded after every forward pass, so no information persists across sessions. This paper presents a \textbf{proof-of-concept pilot study} showing that persistent memory in the \emph{continuous latent space} of a fr…

• EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis

  Emmanuel Oladokun, Sarina Thomas, Jurica \v{S}prem, Vicente Grau · 17 March 2026

  Echocardiography is widely used for assessing cardiac function, where clinically meaningful parameters such as left-ventricular ejection fraction (EF) play a central role in diagnosis and management. Generative models capable of synthesising realistic echocardiogram videos with explicit control over…

• Generalization and Memorization in Rectified Flow

  Mingxing Rao, Daniel Moyer · 17 March 2026

  Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, while existing research heavily prioritizes generation quality and architectural scaling, the underlying dynamics of how RF …

• Diffusion Models Generalize but Not in the Way You Might Think

  Tim Kaiser, Markus Kollmann · 17 March 2026

  Standard evaluation metrics suggest that Denoising Diffusion Models based on U-Net or Transformer architectures generalize well in practice. However, as it can be shown that an optimal Diffusion Model fully memorizes the training data, the model error determines generalization. Here, we show that al…

• Beyond Attention: True Adaptive World Models via Spherical Kernel Operator

  Vladimer Khasia · 17 March 2026

  The pursuit of world model based artificial intelligence has predominantly relied on projecting high-dimensional observations into parameterized latent spaces, wherein transition dynamics are subsequently learned. However, this conventional paradigm is mathematically flawed: it merely displaces the …

• When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators

  Krzysztof Adamkiewicz, Brian Moser, Stanislav Frolov, Tobias Christian Nauen, Federico Raue, Andreas Dengel · 17 March 2026

  Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision data generators? In this work, we revisit the promise of synthetic data as a scalable substitute for real training sets and uncover a …

• RBF-Solver: A Multistep Sampler for Diffusion Probabilistic Models via Radial Basis Functions

  Soochul Park, Yeon Ju Lee, SeongJin Yoon, Jiyub Shin, Juhee Lee, Seongwoon Jo · 17 March 2026

  Diffusion probabilistic models (DPMs) are widely adopted for their outstanding generative fidelity, yet their sampling is computationally demanding. Polynomial-based multistep samplers mitigate this cost by accelerating inference; however, despite their theoretical accuracy guarantees, they generate…

• PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers

  Eshed Gal, Moshe Eliasof, Siddharth Rout, Eldad Haber · 17 March 2026

  The success of vision transformers-especially for generative modeling-is limited by the quadratic cost and weak spatial inductive bias of self-attention. We propose PDE-SSM, a spatial state-space block that replaces attention with a learnable convection-diffusion-reaction partial differential equati…

• MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation

  Byungjun Kim, Soobin Um, Jong Chul Ye · 17 March 2026

  Despite recent advances in Text-to-Video (T2V) synthesis, generating high-fidelity and dynamic motion remains a significant challenge. Existing methods primarily rely on Classifier-Free Guidance (CFG), often with explicit negative prompts (e.g. "static", "blurry"), to suppress undesired artifacts. H…

• Seeking Physics in Diffusion Noise

  Chujun Tang, Lei Zhong, Fangqiang Ding · 17 March 2026

  Do video diffusion models encode signals predictive of physical plausibility? We probe intermediate denoising representations of a pretrained Diffusion Transformer (DiT) and find that physically plausible and implausible videos are partially separable in mid-layer feature space across noise levels. …

• Steer Away From Mode Collisions: Improving Composition In Diffusion Models

  Debottam Dutta, Jianchong Chen, Rajalaxmi Rajagopalan, Yu-Lin Wei, Romit Roy Choudhury · 17 March 2026

  We propose to improve multi-concept prompt fidelity in text-to-image diffusion models. We begin with common failure cases - prompts like "a cat and a dog" that sometimes yields images where one concept is missing, faint, or colliding awkwardly with another. We hypothesize that this happens when the …

• CSD-VAR: Content-Style Decomposition in Visual Autoregressive Models

  Quang-Binh Nguyen, Minh Luu, Quang Nguyen, Anh Tran, Khoi Nguyen · 17 March 2026

  Disentangling content and style from a single image, known as content-style decomposition (CSD), enables recontextualization of extracted content and stylization of extracted styles, offering greater creative flexibility in visual synthesis. While recent personalization methods have explored the dec…

• Discriminative Flow Matching Via Local Generative Predictors

  Om Govind Jha, Manoj Bamniya, Ayon Borthakur · 17 March 2026

  Traditional discriminative computer vision relies predominantly on static projections, mapping input features to outputs in a single computational step. Although efficient, this paradigm lacks the iterative refinement and robustness inherent in biological vision and modern generative modelling. In t…

• FlashHead: Efficient Drop-In Replacement for the Classification Head in Language Model Inference

  Wilhelm Tranheden, Shahnawaz Ahmed, Devdatt Dubhashi, Jonna Matthiesen, Hannes von Essen · 17 March 2026

  Language models are increasingly adopting smaller architectures optimized for consumer devices. In this setting, inference efficiency is the primary constraint. Meanwhile, vocabulary sizes continue to grow rapidly, making the classification head a critical bottleneck that accounts for up to 60\% of …

• The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics

  Xiangbo Gao, Mingyang Wu, Siyuan Yang, Jiongze Yu, Pardis Taghavi, Fangzhou Lin, Zhengzhong Tu · 17 March 2026

  While recent generative video models have achieved remarkable visual realism and are being explored as world models, true physical simulation requires mastering both space and time. Current models can produce visually smooth kinematics, yet they lack a reliable internal motion pulse to ground these …