Generative Adversarial Networks and Image Synthesis

Latest papers

• DIAMOND: Directed Inference for Artifact Mitigation in Flow Matching Models

  Alicja Polowczyk, Agnieszka Polowczyk, Piotr Borycki, Joanna Waczy\'nska, Jacek Tabor, Przemys{\l}aw Spurek · 3 February 2026

  Despite impressive results from recent text-to-image models like FLUX, visual and anatomical artifacts remain a significant hurdle for practical and professional use. Existing methods for artifact reduction, typically work in a post-hoc manner, consequently failing to intervene effectively during th…

• Reducing Memorisation in Generative Models via Riemannian Bayesian Inference

  Johanna Marie Gegenfurtner, Albert Kj{\o}ller Jacobsen, Naima Elosegui Borras, Alejandro Valverde Mahou, Georgios Arvanitidis · 3 February 2026

  Modern generative models can produce realistic samples, however, balancing memorisation and generalisation remains an open problem. We approach this challenge from a Bayesian perspective by focusing on the parameter space of flow matching and diffusion models and constructing a predictive posterior …

• AI-Generated Image Detectors Overrely on Global Artifacts: Evidence from Inpainting Exchange

  Elif Nebioglu, Emirhan Bilgi\c{c}, Adrian Popescu · 3 February 2026

  Modern deep learning-based inpainting enables realistic local image manipulation, raising critical challenges for reliable detection. However, we observe that current detectors primarily rely on global artifacts that appear as inpainting side effects, rather than on locally synthesized content. We s…

• Improving Flow Matching by Aligning Flow Divergence

  Yuhao Huang, Taos Transue, Shih-Hsin Wang, William Feldman, Hong Zhang, Bao Wang · 3 February 2026

  Conditional flow matching (CFM) stands out as an efficient, simulation-free approach for training flow-based generative models, achieving remarkable performance for data generation. However, CFM is insufficient to ensure accuracy in learning probability paths. In this paper, we introduce a new parti…

• Learning Sparse Visual Representations via Spatial-Semantic Factorization

  Theodore Zhengde Zhao, Sid Kiblawi, Jianwei Yang, Naoto Usuyama, Reuben Tan, Noel C Codella, Tristan Naumann, Hoifung Poon, Mu Wei · 3 February 2026

  Self-supervised learning (SSL) faces a fundamental conflict between semantic understanding and image reconstruction. High-level semantic SSL (e.g., DINO) relies on global tokens that are forced to be location-invariant for augmentation alignment, a process that inherently discards the spatial coordi…

• GuidNoise: Single-Pair Guided Diffusion for Generalized Noise Synthesis

  Changjin Kim, HyeokJun Lee, YoungJoon Yoo · 3 February 2026

  Recent image denoising methods have leveraged generative modeling for real noise synthesis to address the costly acquisition of real-world noisy data. However, these generative models typically require camera metadata and extensive target-specific noisy-clean image pairs, often showing limited gener…

• Controlling Exploration-Exploitation in GFlowNets via Markov Chain Perspectives

  Lin Chen, Samuel Drapeau, Fanghao Shao, Xuekai Zhu, Bo Xue, Yunchong Song, Mathieu Lauri\`ere, Zhouhan Lin · 3 February 2026

  Generative Flow Network (GFlowNet) objectives implicitly fix an equal mixing of forward and backward policies, potentially constraining the exploration-exploitation trade-off during training. By further exploring the link between GFlowNets and Markov chains, we establish an equivalence between GFlow…

• Learning Physics-Grounded 4D Dynamics with Neural Gaussian Force Fields

  Shiqian Li, Ruihong Shen, Junfeng Ni, Chang Pan, Chi Zhang, Yixin Zhu · 3 February 2026

  Predicting physical dynamics from raw visual data remains a major challenge in AI. While recent video generation models have achieved impressive visual quality, they still cannot consistently generate physically plausible videos due to a lack of modeling of physical laws. Recent approaches combining…

• PLACID: Identity-Preserving Multi-Object Compositing via Video Diffusion with Synthetic Trajectories

  Gemma Canet Tarr\'es, Manel Baradad, Francesc Moreno-Noguer, Yumeng Li · 3 February 2026

  Recent advances in generative AI have dramatically improved photorealistic image synthesis, yet they fall short for studio-level multi-object compositing. This task demands simultaneous (i) near-perfect preservation of each item's identity, (ii) precise background and color fidelity, (iii) layout an…

• Latent Shadows: The Gaussian-Discrete Duality in Masked Diffusion

  Guinan Chen, Xunpeng Huang, Ying Sun, Shijin Wang, Yanyong Zhang, Chao Wang · 3 February 2026

  Masked discrete diffusion is a dominant paradigm for high-quality language modeling where tokens are iteratively corrupted to a mask state, yet its inference efficiency is bottlenecked by the lack of deterministic sampling tools. While diffusion duality enables deterministic distillation for uniform…

• PACER: Blockwise Pre-verification for Speculative Decoding with Adaptive Length

  Situo Zhang, Yifan Zhang, Zichen Zhu, Hankun Wang, Da Ma, Danyang Zhang, Lu Chen, Kai Yu · 3 February 2026

  Speculative decoding (SD) is a powerful technique for accelerating the inference process of large language models (LLMs) without sacrificing accuracy. Typically, SD employs a small draft model to generate a fixed number of draft tokens, which are then verified in parallel by the target model. Howeve…

• Making Avatars Interact: Towards Text-Driven Human-Object Interaction for Controllable Talking Avatars

  Youliang Zhang, Zhengguang Zhou, Zhentao Yu, Ziyao Huang, Teng Hu, Sen Liang, Guozhen Zhang, Ziqiao Peng, Shunkai Li, Yi Chen, Zixiang Zhou, Yuan Zhou, Qinglin Lu, Xiu Li · 3 February 2026

  Generating talking avatars is a fundamental task in video generation. Although existing methods can generate full-body talking avatars with simple human motion, extending this task to grounded human-object interaction (GHOI) remains an open challenge, requiring the avatar to perform text-aligned int…

• Rethinking Genomic Modeling Through Optical Character Recognition

  Hongxin Xiang, Pengsen Ma, Yunkang Cao, Di Yu, Haowen Chen, Xinyu Yang, Xiangxiang Zeng · 3 February 2026

  Recent genomic foundation models largely adopt large language model architectures that treat DNA as a one-dimensional token sequence. However, exhaustive sequential reading is structurally misaligned with sparse and discontinuous genomic semantics, leading to wasted computation on low-information ba…

• F-scheduler: illuminating the free-lunch design space for fast sampling of diffusion models

  Zilai Li, Lujia Bai · 3 February 2026

  Diffusion models are the state-of-the-art generative models for high-resolution images, but sampling from pretrained models is computationally expensive, motivating interest in fast sampling. Although Free-U Net is a training-free enhancement for improving image quality, we find it ineffective under…

• Inference-Only Prompt Projection for Safe Text-to-Image Generation with TV Guarantees

  Minhyuk Lee, Hyekyung Yoon, Myungjoo Kang · 3 February 2026

  Text-to-Image (T2I) diffusion models enable high-quality open-ended synthesis, but their real-world deployment demands safeguards that suppress unsafe generations without degrading benign prompt-image alignment. We formalize this tension through a total variation (TV) lens: once the reference condit…

• Supervised sparse auto-encoders as unconstrained feature models for semantic composition

  Ouns El Harzli, Hugo Wallner, Yoonsoo Nam, Haixuan Xavier Tao · 3 February 2026

  Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack of alignment between learned features and human semantics. I…

• SIDiffAgent: Self-Improving Diffusion Agent

  Shivank Garg, Ayush Singh, Gaurav Kumar Nayak · 3 February 2026

  Text-to-image diffusion models have revolutionized generative AI, enabling high-quality and photorealistic image synthesis. However, their practical deployment remains hindered by several limitations: sensitivity to prompt phrasing, ambiguity in semantic interpretation (e.g., ``mouse" as animal vs. …

• Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention

  Dvir Samuel, Issar Tzachor, Matan Levy, Micahel Green, Gal Chechik, Rami Ben-Ari · 3 February 2026

  Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines. However, their core attention layers become a major bottleneck at inference time: as generation progresses, the KV cache grows, causing…

• TABES: Trajectory-Aware Backward-on-Entropy Steering for Masked Diffusion Models

  Shreshth Saini, Avinab Saha, Balu Adsumilli, Neil Birkbeck, Yilin Wang, Alan C. Bovik · 3 February 2026

  Masked Diffusion Models (MDMs) have emerged as a promising non-autoregressive paradigm for generative tasks, offering parallel decoding and bidirectional context utilization. However, current sampling methods rely on simple confidence-based heuristics that ignore the long-term impact of local decisi…

• BOLT-GAN: Bayes-Error-Motivated Objective for Stable GAN Training

  Mohammadreza Tavasoli Naeini, Ali Bereyhi, Morteza Noshad, Ben Liang, Alfred O. Hero III · 3 February 2026

  We introduce BOLT-GAN, a novel framework for stable GAN training using the Bayes optimal learning threshold (BOLT). The discriminator is trained via the BOLT loss under a standard 1-Lipschitz constraint. This guides the generator to maximize the Bayes error of the discrimination task. We show that t…

• TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation

  Ariel Shaulov, Eitan Shaar, Amit Edenzon, Lior Wolf · 3 February 2026

  Auto-regressive video generation enables long video synthesis by iteratively conditioning each new batch of frames on previously generated content. However, recent work has shown that such pipelines suffer from severe temporal drift, where errors accumulate and amplify over long horizons. We hypothe…

• Beyond the Loss Curve: Scaling Laws, Active Learning, and the Limits of Learning from Exact Posteriors

  Arian Khorasani, Nathaniel Chen, Yug D Oswal, Akshat Santhana Gopalan, Egemen Kolemen, Ravid Shwartz-Ziv · 3 February 2026

  How close are neural networks to the best they could possibly do? Standard benchmarks cannot answer this because they lack access to the true posterior p(y|x). We use class-conditional normalizing flows as oracles that make exact posteriors tractable on realistic images (AFHQ, ImageNet). This enable…

• Supervised Fine-Tuning Needs to Unlock the Potential of Token Priority

  Zhanming Shen, Zeyu Qin, Jiaqi Hu, Wentao Ye, Hao Chen, Xiaomeng Hu, Haokai Xu, Gang Chen, Yi R. Fung, Haobo Wang · 3 February 2026

  The transition from fitting empirical data to achieving true human utility is fundamentally constrained by a granularity mismatch, where fine-grained autoregressive generation is often supervised by coarse or uniform signals. This position paper advocates Token Priority as the essential bridge, form…

• PromptRL: Prompt Matters in RL for Flow-Based Image Generation

  Fu-Yun Wang, Han Zhang, Michael Gharbi, Hongsheng Li, Taesung Park · 3 February 2026

  Flow matching models (FMs) have revolutionized text-to-image (T2I) generation, with reinforcement learning (RL) serving as a critical post-training strategy for alignment with reward objectives. In this research, we show that current RL pipelines for FMs suffer from two underappreciated yet importan…

• Generation Order and Parallel Decoding in Masked Diffusion Models: An Information-Theoretic Perspective

  Shaorong Zhang, Longxuan Yu, Rob Brekelmans, Luhan Tang, Salman Asif, Greg Ver Steeg · 3 February 2026

  Masked Diffusion Models (MDMs) significantly accelerate inference by trading off sequential determinism. However, the theoretical mechanisms governing generation order and the risks inherent in parallelization remain under-explored. In this work, we provide a unified information-theoretic framework …