Generative Adversarial Networks and Image Synthesis

Latest papers

• Pairing Regularization for Mitigating Many-to-One Collapse in GANs

  Kuan-Yu Lin, Yu-Chih Huang, Tie Liu · 23 April 2026

  Mode collapse remains a fundamental challenge in training generative adversarial networks (GANs). While existing works have primarily focused on inter-mode collapse, such as mode dropping, intra-mode collapse-where many latent variables map to the same or highly similar outputs-has received signific…

• From Diffusion to Flow: Efficient Motion Generation in MotionGPT3

  Jaymin Ban, JiHong Jeon, SangYeop Jeong · 23 April 2026

  Recent text-driven motion generation methods span both discrete token-based approaches and continuous-latent formulations. MotionGPT3 exemplifies the latter paradigm, combining a learned continuous motion latent space with a diffusion-based prior for text-conditioned synthesis. While rectified flow …

• Local Diffusion Models and Phases of Data Distributions

  Fangjun Hu, Guangkuo Liu, Yifan F. Zhang, Xun Gao · 23 April 2026

  As a class of generative artificial intelligence frameworks inspired by statistical physics, diffusion models have shown extraordinary performance in synthesizing complicated data distributions through a denoising process gradually guided by score functions. Real-life data, like images, is often spa…

• One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models

  Chris Cameron, Wangzheng Wang, Nikita Ivanov, Ashmita Bhattacharyya, Didier Ch\'etelat, Yingxue Zhang · 22 April 2026

  Looped transformers scale computational depth without increasing parameter count by repeatedly applying a shared transformer block and can be used for iterative refinement, where each loop rewrites a full fixed-size prediction in parallel. On difficult problems, such as those that require search-lik…

• HP-Edit: A Human-Preference Post-Training Framework for Image Editing

  Fan Li, Chonghuinan Wang, Lina Lei, Yuping Qiu, Jiaqi Xu, Jiaxiu Jiang, Xinran Qin, Zhikai Chen, Fenglong Song, Zhixin Wang, Renjing Pei, Wangmeng Zuo · 22 April 2026

  Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further improved generation quality, efficiently applying Reinforce…

• Geometric Decoupling: Diagnosing the Structural Instability of Latent

  Yuanbang Liang, Zhengwen Chen, Yu-Kun Lai · 22 April 2026

  Latent Diffusion Models (LDMs) achieve high-fidelity synthesis but suffer from latent space brittleness, causing discontinuous semantic jumps during editing. We introduce a Riemannian framework to diagnose this instability by analyzing the generative Jacobian, decomposing geometry into \textit{Local…

• Streaming Structured Inference with Flash-SemiCRF

  Benjamin K. Johnson, Thomas Goralski, Ayush Semwal, Hui Shen, H. Josh Jang · 22 April 2026

  Semi-Markov Conditional Random Fields (semi-CRFs) assign labels to segments of a sequence rather than to individual positions, enabling exact inference over segment-level features and principled uncertainty estimates at their boundaries. However, existing implementations must materialize a large edg…

• Self-Improving Tabular Language Models via Iterative Group Alignment

  Yunbo Long, Tejumade Afonja, Alexandra Brintrup, Mario Fritz · 22 April 2026

  While language models have been adapted for tabular data generation, two fundamental limitations remain: (1) static fine-tuning produces models that cannot learn from their own generated samples and adapt to self-correct, and (2) autoregressive objectives preserve local token coherence but neglect g…

• Counting Worlds Branching Time Semantics for post-hoc Bias Mitigation in generative AI

  Alessandro G. Buda, Giuseppe Primiero, Leonardo Ceragioli, Melissa Antonelli · 22 April 2026

  Generative AI systems are known to amplify biases present in their training data. While several inference-time mitigation strategies have been proposed, they remain largely empirical and lack formal guarantees. In this paper we introduce CTLF, a branching-time logic designed to reason about bias in …

• Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters

  Pin-Yen Chiu, I-Sheng Fang, Jun-Cheng Chen · 22 April 2026

  Recent advances in diffusion models have significantly improved image and video synthesis. In addition, several concept control methods have been proposed to enable fine-grained, continuous, and flexible control over free-form text prompts. However, these methods not only require intensive training …

• Efficient Autoregressive Inference for Transformer Probabilistic Models

  Conor Hassan, Nasrulloh Loka, Cen-You Li, Daolang Huang, Paul E. Chang, Yang Yang, Francesco Silvestrin, Samuel Kaski, Luigi Acerbi · 22 April 2026

  Set-based transformer models for amortized probabilistic inference and meta-learning, such as neural processes, prior-fitted networks, and tabular foundation models, excel at single-pass marginal prediction. However, many applications require joint distributions over multiple predictions. Purely aut…

• Aletheia: Physics-Conditioned Localized Artifact Attention (PhyLAA-X) for End-to-End Generalizable and Robust Deepfake Video Detection

  Devendra Ghori · 21 April 2026

  State-of-the-art deepfake detectors achieve near-perfect in-domain accuracy yet degrade under cross-generator shifts, heavy compression, and adversarial perturbations. The core limitation remains the decoupling of semantic artifact learning from physical invariants: optical-flow discontinuities, spe…

• Symmetry Guarantees Statistic Recovery in Variational Inference

  Daniel Marks, Dario Paccagnan, Mark van der Wilk · 21 April 2026

  Variational inference (VI) is a central tool in modern machine learning, used to approximate an intractable target density by optimising over a tractable family of distributions. As the variational family cannot typically represent the target exactly, guarantees on the quality of the resulting appro…

• Towards Generalizable Deepfake Image Detection with Vision Transformers

  Kaliki V Srinanda, M Manvith Prabhu, Hemanth K Mogilipalem, Jayavarapu S Abhinai, Vaibhav Santhosh, Aryan Herur, Deepu Vijayasenan · 21 April 2026

  In today's day and age, we face a challenge in detecting deepfake images because of the fast evolution of modern generative models and the poor generalization capability of existing methods. In this paper, we use an ensemble of fine-tuned vision transformers like DINOv2, AIMv2 and OpenCLIP's ViT-L/1…

• Grokking of Diffusion Models: Case Study on Modular Addition

  Joon Hyeok Kim, Yong-Hyun Park, Mattis Dals{\ae}tra {\O}stby, Jiatao Gu · 21 April 2026

  Despite their empirical success, how diffusion models generalize remains poorly understood from a mechanistic perspective. We demonstrate that diffusion models trained with flow-matching objectives exhibit grokking--delayed generalization after overfitting--on modular addition, enabling controlled a…

• Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation

  Tianshi Cao, Jiawei Ren, Yuxuan Zhang, Jaewoo Seo, Jiahui Huang, Shikhar Solanki, Haotian Zhang, Mingfei Guo, Haithem Turki, Muxingzi Li, Yue Zhu, Sipeng Zhang, Zan Gojcic, Sanja Fidler, Kangxue Yin · 21 April 2026

  Closed-loop simulation is a core component of autonomous vehicle (AV) development, enabling scalable testing, training, and safety validation before real-world deployment. Neural scene reconstruction converts driving logs into interactive 3D environments for simulation, but it does not produce compl…

• A Universal Avoidance Method for Diverse Multi-branch Generation

  Kyeongman Park, Minha Jhang, Kyomin Jung · 21 April 2026

  Modern generative models still lack human-level creativity, particularly in multi-branch diversity. Prior approaches to address this problem often incur heavy computation or strong dependency on model architecture. Therefore, we introduce UAG(Universal Avoidance Generation), a model-agnostic and com…

• The Topological Trouble With Transformers

  Michael C. Mozer, Shoaib Ahmed Siddiqui, Rosanne Liu · 21 April 2026

  Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dynamic state tracking. State tracking -- the iterative updating of latent variables reflecting an evolving environment -- involves inherently sequentia…

• Projected Coupled Diffusion for Test-Time Constrained Joint Generation

  Hao Luan, Yi Xian Goh, See-Kiong Ng, Chun Kai Ling · 21 April 2026

  Modifications to test-time sampling have emerged as an important extension to diffusion algorithms, with the goal of biasing the generative process to achieve a given objective without having to retrain the entire diffusion model. However, generating jointly correlated samples from multiple pre-trai…

• Unveiling Deepfakes: A Frequency-Aware Triple Branch Network for Deepfake Detection

  Qihao Shen, Jiaxing Xuan, Zhenguang Liu, Sifan Wu, Yutong Xie, Zhaoyan Ming, Yingying Jiao, kui Ren · 21 April 2026

  Advanced deepfake technologies are blurring the lines between real and fake, presenting both revolutionary opportunities and alarming threats. While it unlocks novel applications in fields like entertainment and education, its malicious use has sparked urgent ethical and societal concerns ranging fr…

• R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation

  William Ljungbergh, Bernardo Taveira, Wenzhao Zheng, Adam Tonderski, Chensheng Peng, Fredrik Kahl, Christoffer Petersson, Michael Felsberg, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan · 21 April 2026

  Validating autonomous driving (AD) systems requires diverse and safety-critical testing, making photorealistic virtual environments essential. Traditional simulation platforms, while controllable, are resource-intensive to scale and often suffer from a domain gap with real-world data. In contrast, n…

• NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization

  Enshu Liu, Xuefei Ning, Yu Wang, Zinan Lin · 21 April 2026

  Discrete diffusion language models (dLLMs) have recently emerged as a promising alternative to traditional autoregressive approaches, offering the flexibility to generate tokens in arbitrary orders and the potential of parallel decoding. However, existing heuristic sampling strategies remain ineffic…

• Decomposing the Depth Profile of Fine-Tuning

  Jayadev Billa · 21 April 2026

  Fine-tuning adapts pretrained networks to new objectives. Whether the resulting depth profile of representational change reflects an intrinsic property of the model or the magnitude of gradient flow has not been tested directly. We measure this profile across 240 fine-tuning runs spanning 15 models …

• Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models

  Jeongjae Lee, Jinho Chang, Jeongsol Kim, Jong Chul Ye · 21 April 2026

  Reward-based fine-tuning aims to steer a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are motivated by different perspectives such as Soft RL, GFlowNets, etc., we show that many can be writte…

• CLIMB: Controllable Longitudinal Brain Image Generation using Mamba-based Latent Diffusion Model and Gaussian-aligned Autoencoder

  Duy-Phuong Dao, Muhammad Taqiyuddin, Jahae Kim, Sang-Heon Lee, Hye-Won Jung, Jaehoo Choi, Hyung-Jeong Yang · 20 April 2026

  Latent diffusion models have emerged as powerful generative models in medical imaging, enabling the synthesis of high quality brain magnetic resonance imaging scans. In particular, predicting the evolution of a patients brain can aid in early intervention, prognosis, and treatment planning. In this …