Generative Adversarial Networks and Image Synthesis

Derniers papiers

• MakeupMirror: Improving Facial Attribute Preservation in Diffusion Models for Makeup Transfer

  Nefeli Andreou, Angel Mart\'inez-Gonz\'alez, Sabine Sternig, Matthieu Guillaumin, Epameinondas Antonakos, Michael Opitz · 19 juin 2026

  Makeup transfer models enable fun augmented reality (AR) experiences as well as virtual try-on (VTO) for online makeup shopping. While recent state-of-the-art diffusion based solutions such as Stable-Makeup dramatically improve the accuracy and realism of makeup transfer, they still face limitations…

• On the Redundancy of Timestep Embeddings in Diffusion Models

  Jos\'e A. Ch\'avez · 19 juin 2026

  Diffusion models rely heavily on explicit timestep embeddings to modulate the denoising process across various noise scales. In this work, we challenge the necessity of these temporal signals by analyzing their impact on U-Net and Diffusion Transformer architectures. Beyond empirical evidence, we pr…

• How Transparent is DiffusionGemma?

  Joshua Engels, Callum McDougall, Bilal Chughtai, Janos Kramar, Senthoran Rajamanoharan, Cindy Wu, Arthur Conmy, Asic Q Chen, Jean Tarbouriech, Min Ma, Brendan O'Donoghue, Jo\~ao Gabriel Lopes de Oliveira, Rohin Shah, Neel Nanda · 19 juin 2026

  LLM reasoning transparency is a critical affordance for understanding model decisions, mitigating misuse and misalignment, and debugging surprising model behaviors. However, DiffusionGemma performs a larger fraction of its computation in a continuous latent space; does this make its reasoning less t…

• FreeStyle: Free Control of Style-Content Dual-Reference Generation from Community LoRA Mining

  Jinghong Lan, Wei Cheng, Yunuo Chen, Ziqi Ye, Peng Xing, Yixiao Fang, Rui Wang, Yufeng Yang, Xuanyang Zhang, Xianfang Zeng, Difan Zou, Gang Yu, Chi Zhang · 19 juin 2026

  Style-content dual-reference generation aims to synthesize an image that preserves the structure and semantics of a content reference while adopting the style of a separate style reference.Despite recent progress, this setting remains challenging because models must balance content fidelity, style a…

• Score Approximation for Diffusion Models on Arbitrary Low-Dimensional Structures

  Xinhe Mu, Zaijiu Shang, Zhaoqi Zhou, Chuan Zhou, Qi Meng, Guiying Yan, Zhiming Ma · 19 juin 2026

  The remarkable success of score-based diffusion models has spurred significant efforts to establish their theoretical foundations. However, existing complexity bounds for score approximation rely heavily on restrictive assumptions like Lipschitz continuous densities or smooth manifold supports, whic…

• PU-UNet: Stable Multiplicative Interactions for Medical Image Segmentation

  Ziyuan Li, Osamah Sufyan, Uwe Jaekel, Babette Dellen · 19 juin 2026

  Many dense prediction networks rely on additive feature transformations and model higher-order feature interactions only implicitly. Product units provide an explicit mechanism for multiplicative feature modeling, but their logarithmic--exponential formulation can cause numerical instability, which …

• Variable-Length Tokenization via Learnable Global Merging for Diffusion Transformers

  Dong Hoon Lee, Seunghoon Hong · 19 juin 2026

  Latent Diffusion Models (LDMs) have become dominant in visual synthesis, but their quality-compute trade-off is largely constrained by the tokenizer's fixed compression ratio. Variable-length tokenizers (VLTs) promise adaptive compression by varying token counts, allowing diffusion models to flexibl…

• TeleMorpher: Toward Robust Simultaneous Motion-Location Editing

  Haengbok Chung · 19 juin 2026

  Diffusion models have achieved remarkable success in image and video generation and editing. While recent studies have extended these efforts toward motion editing, simultaneously transforming both motion and location-despite its practical importance-remains largely unexplored. To better understand …

• NeSyCat Torch: A Differentiable Tensor Implementation of Categorical Semantics for Neurosymbolic Learning

  Daniel Romero Schellhorn, Till Mossakowski, Bj\"orn Gehrke · 18 juin 2026

  Neurosymbolic semantics is fragmented: classical, fuzzy, probabilistic and neural systems each define truth by their own inductive rules. NeSyCat, extending ULLER, subsumes them under a single inductive definition of truth, parametric in a strong monad and an aggregation structure on truth-values. N…

• When AUC Misleads: Polarization-Aware Evaluation of Deepfake Detectors under Domain Shift

  Dat Nguyen, Cosmin Radoi, Romain Hermary, Marcella Astrid, Nesryne Mejri, Enjie Ghorbel, Djamila Aouada · 18 juin 2026

  Recent advances in generative AI, such as diffusion models and face-swapping tools, have enabled the creation of highly realistic deepfakes, leading to real-world harms including financial fraud and non-consensual explicit content. In response, deepfake detection has become an active research area, …

• HAARES Half-Split Residual Basis Routing for Deep Transformers

  Kehan Wang · 18 juin 2026

  Block-level residual routing makes learned residual aggregation practical by routing over block summaries, but each summary compresses an ordered sequence of attention and MLP updates into one cumulative vector. We propose \method{}, a lightweight residual basis router that keeps the cumulative bloc…

• Dual-Channel Grounded World Modeling (DCGWM): Structural Prevention of Objective Interference Collapse via Heterogeneous External Grounding with Inward-Only Gradient Flow

  Akshay Hazare · 18 juin 2026

  Joint Embedding Predictive Architectures (JEPAs) are a leading approach to world model representation learning. We identify a failure mode in JEPA-based world models grounded against two qualitatively distinct external signals: physical dynamics (sparse, high-magnitude, constraint-satisfying gradien…

• Looped World Models

  Hongyuan Adam Lu, Z. L. Victor Wei, Qun Zhang, Jinrui Zeng, Bowen Cao, Lingwei Meng, Mocheng Li, Zezhong Wang, Haonan Yin, Naifu Xue, Minyu Chen, Cenyuan Zhang, Zefan Zhang, Hao Wei, Jiawei Zhou, Haoran Xu, Hao Yang, Ronglai Zuo, Tongda Xu, Yonghao Li, Jian Chen, Hebin Wang, Zeyu Gao, Yang Li, Wei Zhao, Qimin Zhong, Siqi Liu, Yumeng Zhang, Leyan Cui, Zhangyu Wang, Wai Lam · 17 juin 2026

  Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding errors. We resolve this by introducing Looped World Models (LoopWM), which are the first looped architectures for world model…

• Blind Recovery of Latent Domains via Unsupervised Symmetry Discovery

  Onur Efe, Arkadas Ozakin · 17 juin 2026

  Primary motivation in blind inverse problems is to recover signals of interest from corrupted observations without knowing the obfuscating mechanism. Blind deconvolution is a prominent approach when the corruption is convolutional, but it is not applicable when general linear transformations obfusca…

• CogGen: Cognitive-Load-Inspired Fully Unsupervised Deep Generative Modeling for Compressively Sampled MRI Reconstruction

  Qingyong Zhu, Yumin Tan, Xiang Gu, Dong Liang · 17 juin 2026

  Fully unsupervised deep generative modeling (FU-DGM) offers significant potential for compressively sampled magnetic resonance imaging (CS-MRI) reconstruction. Representative FU-DGM formulations, such as deep image prior (DIP) and implicit neural representation (INR), employ architectural bias to in…

• NoiseTilt: Noise-Tilted Reverse Kernels for Diffusion Reward Alignment

  Jisung Hwang, Yunhong Min, Jaihoon Kim, I-Chao Shen, Minhyuk Sung · 17 juin 2026

  We introduce the Noise-Tilted Reverse Kernel (NTRK), a reward-guided diffusion sampler that injects reward gradients through the noise term, leaving the pretrained reverse kernel unchanged and requiring only a single sample per step. Reward-guided sampling at inference time has greatly expanded the …

• Conservation Laws for Modern Neural Architectures

  Viet-Hoang Tran, Vinh Khanh Bui, Tan Lai Ngoc, Nam Nguyen, Tuan Dam, Tan M. Nguyen · 17 juin 2026

  Understanding gradient descent dynamics is key to explaining the success of over-parameterized models, where implicit bias manifests through conservation laws in gradient flow. While such laws are well understood for linear and ReLU networks, they remain largely unexplored for modern architectures. …

• OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation

  Zijie Meng, Yufei Liu, Chengqian Ma, Zhiyu Li, Jiyuan Liu, Wenhua Nie, Bingcai Wei, Shuqin Chen, Weichen Xu, Jiquan Yuan, Miao Zhang · 17 juin 2026

  Generative world models for autonomous driving face two unresolved tensions: heterogeneous control injection, where free-form language, HD-maps, trajectories, and camera poses reside in incompatible representational spaces, and post-hoc cross-view fusion, where per-camera latents fail to encode glob…

• Recover Semantics First, Generate Better: Improved Latent Modeling for 3D MRI Reconstruction and Cross-Contrast Synthesis

  Yonghao Chen, Sicheng Yang, Rui Tang, Lei Zhu · 17 juin 2026

  Multi-contrast magnetic resonance imaging (MRI) provides complementary information for clinical diagnosis. However, acquiring all MRI sequences is often time-consuming and costly. Recent generative models perform cross-contrast synthesis to address this issue by inferring absent contrasts from the a…

• Recursive Scaling in Masked Diffusion Models

  Alba Carballo-Castro, Julianna Piskorz, Paulius Rauba, Mihaela van der Schaar, Pascal Frossard · 17 juin 2026

  Masked diffusion models (MDMs) have recently emerged as a promising paradigm for sequence generation. Scaling MDMs is conventionally achieved by increasing the parameter count or the number of denoising steps. We introduce Recursive Masked Diffusion Models (R-MDMs), which add recursive depth as a th…

• Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering

  Rohit Kundu, Arindam Dutta, Sarosij Bose, Athula Balachandran, Amit K. Roy-Chowdhury · 17 juin 2026

  Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing defenses either require expensive safety fine-tuning that degrades general capability, or apply external filters that are trivially bypassed by adversarial prompts. We present…

• STAR: SpatioTemporal Adaptive Reward Allocation for Text-to-Image RL Post-Training

  Jinjie Shen, Wei Deng, Xian Hu, Daiguo Zhou, Jian Luan · 17 juin 2026

  Existing RL post-training methods for text-to-image generation usually convert the final-image reward into a single scalar advantage and apply it with the same strength to the entire generative trajectory. However, text-to-image generation naturally has temporal and spatial structure: different deno…

• TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations

  Zikang Xiong, Weixin Li, Zhouchonghao Wu, Akshay Rangesh, Saarth Bonde, Grantland Hall, Chen Tang, Yihan Hu, Wei Zhan · 17 juin 2026

  End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all stages: collecting and labeling millions of driving frames is costly, and closed-loop RL on images is bottlenecked by the p…

• Volterra Generative Models

  Yusen Jia, Bingyan Han · 17 juin 2026

  Score-based diffusion models typically use Brownian perturbations, which provide tractable reverse-time dynamics but impose memoryless noising. We introduce Volterra generative models, a continuous-time score-based framework whose forward process injects path-dependent noise through fractional kerne…

• Recursive Learning Without Collapse: A Weighting-Based Stabilization Framework

  Hengzhi He, Shirong Xu, Guang Cheng · 17 juin 2026

  Recent studies identified an intriguing phenomenon in recursive generative model training known as model collapse, where models trained on data generated by previous models exhibit severe performance degradation. Addressing this issue and developing more effective training strategies have become cen…