Generative Adversarial Networks and Image Synthesis

Latest papers

• Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach

  Zijian Zhao, Dian Jin, Zijing Zhou · 17 April 2026

  Recently, Image-to-Music (I2M) generation has garnered significant attention, with potential applications in fields such as gaming, advertising, and multi-modal art creation. However, due to the ambiguous and subjective nature of I2M tasks, most end-to-end methods lack interpretability, leaving user…

• RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing

  Liting Gao, Yi Yuan, Yaru Chen, Yuelan Cheng, Zhenbo Li, Juan Wen, Shubin Zhang, Wenwu Wang · 17 April 2026

  Diffusion models have shown remarkable progress in text-to-audio generation. However, text-guided audio editing remains in its early stages. This task focuses on modifying the target content within an audio signal while preserving the rest, thus demanding precise localization and faithful editing ac…

• Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching

  Aihua Li · 17 April 2026

  Flow matching retains the generation quality of diffusion models while enabling substantially faster inference, making it a compelling paradigm for generative modeling. However, when applied to language modeling, it exhibits fundamental limitations in representing complex latent distributions with i…

• Diffusion Crossover: Defining Evolutionary Recombination in Diffusion Models via Noise Sequence Interpolation

  Chisatao Kumada, Satoru Hiwa, Tomoyuki Hiroyasu · 17 April 2026

  Interactive Evolutionary Computation (IEC) provides a powerful framework for optimizing subjective criteria such as human preferences and aesthetics, yet it suffers from a fundamental limitation: in high-dimensional generative representations, defining crossover in a semantically consistent manner i…

• Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting

  Inseok Jeon, Minhyeok Lee, Seunghoon Lee, Minseok Kang, Suhwan Cho, Sangyoun Lee · 17 April 2026

  Video outpainting aims to expand the visible content of a video beyond the original frame boundaries while preserving spatial fidelity and temporal coherence across frames. Existing methods primarily rely on large-scale generative models, such as diffusion models. However, generationbased approaches…

• Controllable Video Object Insertion via Multiview Priors

  Xia Qi, Peishan Cong, Yichen Yao, Ziyi Wang, Yaoqin Ye, Yuexin Ma · 17 April 2026

  Video object insertion is a critical task for dynamically inserting new objects into existing environments. Previous video generation methods focus primarily on synthesizing entire scenes while struggling with ensuring consistent object appearance, spatial alignment, and temporal coherence when inse…

• Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching

  Zhengyan Wan, Yidong Ouyang, Liyan Xie, Fang Fang, Hongyuan Zha, Guang Cheng · 16 April 2026

  Guidance provides a simple and effective framework for posterior sampling by steering the generation process towards the desired distribution. When modeling discrete data, existing approaches mostly focus on guidance with the first-order approximation to improve the sampling efficiency. However, suc…

• MaMe & MaRe: Matrix-Based Token Merging and Restoration for Efficient Visual Perception and Synthesis

  Simin Huo, Ning Li · 16 April 2026

  Token compression is crucial for mitigating the quadratic complexity of self-attention mechanisms in Vision Transformers (ViTs), which often involve numerous input tokens. Existing methods, such as ToMe, rely on GPU-inefficient operations (e.g., sorting, scattered writes), introducing overheads that…

• Frozen Forecasting: A Unified Evaluation

  Jacob C Walker, Pedro V\'elez, Luisa Polania Cabrera, Guangyao Zhou, Sayna Ebrahimi, Rishabh Kabra, Carl Doersch, Maks Ovsjanikov, Jo\~ao Carreira, Shiry Ginosar · 16 April 2026

  Forecasting future events is a fundamental capability for general-purpose systems that plan or act across different levels of abstraction. Yet, evaluating whether a forecast is "correct" remains challenging due to the inherent uncertainty of the future. We propose a unified evaluation framework for …

• ART-VITON: Measurement-Guided Latent Diffusion for Artifact-Free Virtual Try-On

  Junseo Park, Hyeryung Jang · 15 April 2026

  Virtual try-on (VITON) aims to generate realistic images of a person wearing a target garment, requiring precise garment alignment in try-on regions and faithful preservation of identity and background in non-try-on regions. While latent diffusion models (LDMs) have advanced alignment and detail syn…

• SOAR: Self-Correction for Optimal Alignment and Refinement in Diffusion Models

  You Qin, Linqing Wang, Hao Fei, Roger Zimmermann, Liefeng Bo, Qinglin Lu, Chunyu Wang · 15 April 2026

  The post-training pipeline for diffusion models currently has two stages: supervised fine-tuning (SFT) on curated data and reinforcement learning (RL) with reward models. A fundamental gap separates them. SFT optimizes the denoiser only on ground-truth states sampled from the forward noising process…

• VideoFlexTok: Flexible-Length Coarse-to-Fine Video Tokenization

  Andrei Atanov, Jesse Allardice, Roman Bachmann, O\u{g}uzhan Fatih Kar, R Devon Hjelm, David Griffiths, Peter Fu, Afshin Dehghan, Amir Zamir · 15 April 2026

  Visual tokenizers map high-dimensional raw pixels into a compressed representation for downstream modeling. Beyond compression, tokenizers dictate what information is preserved and how it is organized. A de facto standard approach to video tokenization is to represent a video as a spatiotemporal 3D …

• Interpretable Relational Inference with LLM-Guided Symbolic Dynamics Modeling

  Xiaoxiao Liang, Juyuan Zhang, Liming Pan, Linyuan L\"u · 15 April 2026

  Inferring latent interaction structures from observed dynamics is a fundamental inverse problem in many-body interacting systems. Most neural approaches rely on black-box surrogates over trainable graphs, achieving accuracy at the expense of mechanistic interpretability. Symbolic regression offers e…

• LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models

  Haocheng Xi, Harman Singh, Yuezhou Hu, Coleman Hooper, Rishabh Tiwari, Aditya Tomar, Minjae Lee, Wonjun Kang, Michael Mahoney, Chenfeng Xu, Kurt Keutzer, Amir Gholami · 15 April 2026

  Block-wise diffusion language models (DLMs) generate multiple tokens in any order, offering a promising alternative to the autoregressive decoding pipeline. However, they still remain bottlenecked by memory-bound attention in long-context scenarios. Naive sparse attention fails on DLMs due to a KV I…

• Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling

  Tianyu Xie, Shuchen Xue, Zijin Feng, Tianyang Hu, Jiacheng Sun, Zhenguo Li, Cheng Zhang · 15 April 2026

  Discrete diffusion models have recently shown great promise for modeling complex discrete data, with masked diffusion models (MDMs) offering a compelling trade-off between quality and generation speed. MDMs denoise by progressively unmasking multiple dimensions from an all-masked input, but their pe…

• MAST: Mask-Guided Attention Mass Allocation for Training-Free Multi-Style Transfer

  Dongkyung Kang, Jaeyeon Hwang, Junseo Park, Minji Kang, Yeryeong Lee, Beomseok Ko, Hanyoung Roh, Jeongmin Shin, Hyeryung Jang · 15 April 2026

  Style transfer aims to render a content image with the visual characteristics of a reference style while preserving its underlying semantic layout and structural geometry. While recent diffusion-based models demonstrate strong stylization capabilities by leveraging powerful generative priors and con…

• MVAdapt: Zero-Shot Multi-Vehicle Adaptation for End-to-End Autonomous Driving

  Haesung Oh, Jaeheung Park · 15 April 2026

  End-to-End (E2E) autonomous driving models are usually trained and evaluated with a fixed ego-vehicle, even though their driving policy is implicitly tied to vehicle dynamics. When such a model is deployed on a vehicle with different size, mass, or drivetrain characteristics, its performance can deg…

• Ride the Wave: Precision-Allocated Sparse Attention for Smooth Video Generation

  Wentai Zhang, Ronghui Xi, Shiyao Peng, Jiayu Huang, Haoran Luo, Zichen Tang, Haihong E · 15 April 2026

  Video Diffusion Transformers have revolutionized high-fidelity video generation but suffer from the massive computational burden of self-attention. While sparse attention provides a promising acceleration solution, existing methods frequently provoke severe visual flickering caused by static sparsit…

• BiasIG: Benchmarking Multi-dimensional Social Biases in Text-to-Image Models

  Hanjun Luo, Zhimu Huang, Haoyu Huang, Ziye Deng, Ruizhe Chen, Xinfeng Li, Zuozhu Liu, Hanan Salam · 15 April 2026

  Text-to-Image (T2I) generative models have revolutionized content creation, yet they inherently risk amplifying societal biases. While sociological research provides systematic classifications of bias, existing T2I benchmarks largely conflate these nuances or focus narrowly on occupational stereotyp…

• Curvelet-Based Frequency-Aware Feature Enhancement for Deepfake Detection

  Salar Adel Sabri, Ramadhan J. Mstafa · 15 April 2026

  The proliferation of sophisticated generative models has significantly advanced the realism of synthetic facial content, known as deepfakes, raising serious concerns about digital trust. Although modern deep learning-based detectors perform well, many rely on spatial-domain features that degrade und…

• SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation

  Yexiong Lin, Jia Shi, Shanshan Ye, Wanyu Wang, Yu Yao, Tongliang Liu · 15 April 2026

  Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlooked limitation: these models suffer from severe diversity degradation, concentrating samples on dominant modes while negl…

• FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer

  Shenghe Zheng, Minyu Zhang, Tianhao Liu, Hongzhi Wang · 14 April 2026

  With the growing availability of open-sourced adapters trained on the same diffusion backbone for diverse scenes and objects, combining these pretrained weights enables low-cost customized generation. However, most existing model merging methods are designed for classification or text generation, an…

• KL Divergence Between Gaussians: A Step-by-Step Derivation for the Variational Autoencoder Objective

  Andr\'es Mu\~noz, Rodrigo Ramele · 14 April 2026

  Kullback-Leibler (KL) divergence is a fundamental concept in information theory that quantifies the discrepancy between two probability distributions. In the context of Variational Autoencoders (VAEs), it serves as a central regularization term, imposing structure on the latent space and thereby ena…

• Generative Path-Finding Method for Wasserstein Gradient Flow

  Chengyu Liu, Xiang Zhou · 14 April 2026

  Wasserstein gradient flows (WGFs) describe the evolution of probability distributions in Wasserstein space as steepest descent dynamics for a free energy functional. Computing the full path from an arbitrary initial distribution to equilibrium is challenging, especially in high dimensions. Eulerian …

• Post-Processing Methods for Improving Accuracy in MRI Inpainting

  Nishad Kulkarni, Krithika Iyer, Austin Tapp, Abhijeet Parida, Daniel Capell\'an-Mart\'in, Zhifan Jiang, Mar\'ia J. Ledesma-Carbayo, Syed Muhammad Anwar, Marius George Linguraru · 14 April 2026

  Magnetic Resonance Imaging (MRI) is the primary imaging modality used in the diagnosis, assessment, and treatment planning for brain pathologies. However, most automated MRI analysis tools, such as segmentation and registration pipelines, are optimized for healthy anatomies and often fail when confr…