Generative Adversarial Networks and Image Synthesis

Últimos artículos

• RAC: Rectified Flow Auto Coder

  Sen Fang, Yalin Feng, Yanxin Zhang, Dimitris N. Metaxas · 9 de marzo de 2026

  In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step decoding by applying the decoder to flow timesteps. Its decoding path is straight and correctable, enabling step-by-step refinement. 2. The model inherentl…

• Reflective Flow Sampling Enhancement

  Zikai Zhou, Muyao Wang, Shitong Shao, Lichen Bai, Haoyi Xiong, Bo Han, Zeke Xie · 9 de marzo de 2026

  The growing demand for text-to-image generation has led to rapid advances in generative modeling. Recently, text-to-image diffusion models trained with flow matching algorithms, such as FLUX, have achieved remarkable progress and emerged as strong alternatives to conventional diffusion models. At th…

• Self-Speculative Masked Diffusions

  Andrew Campbell, Valentin De Bortoli, Jiaxin Shi, Arnaud Doucet · 9 de marzo de 2026

  We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict factorized logits over currently masked positions. A number of masked…

• Text-Driven Emotionally Continuous Talking Face Generation

  Hao Yang, Yanyan Zhao, Tian Zheng, Hongbo Zhang, Bichen Wang, Di Wu, Xing Fu, Xuda Zhi, Yongbo Huang, Hao He · 9 de marzo de 2026

  Talking Face Generation (TFG) strives to create realistic and emotionally expressive digital faces. While previous TFG works have mastered the creation of naturalistic facial movements, they typically express a fixed target emotion in synthetic videos and lack the ability to exhibit continuously cha…

• StreamWise: Serving Multi-Modal Generation in Real-Time at Scale

  Haoran Qiu, Gohar Irfan Chaudhry, Chaojie Zhang, \'I\~nigo Goiri, Esha Choukse, Rodrigo Fonseca, Ricardo Bianchini · 9 de marzo de 2026

  Advances in multi-modal generative models are enabling new applications, from storytelling to automated media synthesis. Most current workloads generate simple outputs (e.g., image generation from a prompt) in batch mode, often requiring several seconds even for basic results. Serving real-time mult…

• Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence

  Bingji Yi, Qiyuan Liu, Yuwei Cheng, Haifeng Xu · 9 de marzo de 2026

  Synthetic data has been increasingly used to train frontier generative models. However, recent studies raise key concerns that iteratively retraining a generative model on its self-generated synthetic data may keep deteriorating model performance, a phenomenon often coined model collapse. In this pa…

• Dynamic Chunking Diffusion Transformer

  Akash Haridas, Utkarsh Saxena, Parsa Ashrafi Fashi, Mehdi Rezagholizadeh, Vikram Appia, Emad Barsoum · 9 de marzo de 2026

  Diffusion Transformers process images as fixed-length sequences of tokens produced by a static $\textit{patchify}$ operation. While effective, this design spends uniform compute on low- and high-information regions alike, ignoring that images contain regions of varying detail and that the denoising …

• Place-it-R1: Unlocking Environment-aware Reasoning Potential of MLLM for Video Object Insertion

  Bohai Gu, Taiyi Wu, Dazhao Du, Jian Liu, Shuai Yang, Xiaotong Zhao, Alan Zhao, Song Guo · 9 de marzo de 2026

  Modern video editing techniques have achieved high visual fidelity when inserting video objects. However, they focus on optimizing visual fidelity rather than physical causality, leading to edits that are physically inconsistent with their environment. In this work, we present Place-it-R$1$, an end-…

• Physical Simulator In-the-Loop Video Generation

  Lin Geng Foo, Mark He Huang, Alexandros Lattas, Stylianos Moschoglou, Thabo Beeler, Christian Theobalt · 9 de marzo de 2026

  Recent advances in diffusion-based video generation have achieved remarkable visual realism but still struggle to obey basic physical laws such as gravity, inertia, and collision. Generated objects often move inconsistently across frames, exhibit implausible dynamics, or violate physical constraints…

• Score-Guided Proximal Projection: A Unified Geometric Framework for Rectified Flow Editing

  Vansh Bansal, James G Scott · 9 de marzo de 2026

  Rectified Flow (RF) models achieve state-of-the-art generation quality, yet controlling them for precise tasks -- such as semantic editing or blind image recovery -- remains a challenge. Current approaches bifurcate into inversion-based guidance, which suffers from "geometric locking" by rigidly adh…

• Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR

  Ajinkya Kulkarni, Sandipana Dowerah, Atharva Kulkarni, Tanel Alum\"ae, Mathew Magimai Doss · 9 de marzo de 2026

  Self-supervised learning (SSL) underpins modern audio deepfake detection, yet most prior work centers on a single large wav2vec2-XLSR backbone, leaving compact under studied. We present RAPTOR, Representation Aware Pairwise-gated Transformer for Out-of-domain Recognition a controlled study of compac…

• Omni-C: Compressing Heterogeneous Modalities into a Single Dense Encoder

  Kin Wai Lau, Yasar Abbas Ur Rehman, Lai-Man Po, Pedro Porto Buarque de Gusm\~ao · 9 de marzo de 2026

  Recent multimodal systems often rely on separate expert modality encoders which cause linearly scaling complexity and computational overhead with added modalities. While unified Omni-models address this via Mixture-of-Expert (MoE) architectures with specialized experts and routing, they still inflat…

• Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion

  Zahra Karimaghaloo, Dumitru Fetco, Haz-Edine Assemlal, Hassan Rivaz, Douglas L. Arnold · 9 de marzo de 2026

  Accurate longitudinal analysis of brain MRI is often hindered by evolving lesions, which bias automated neuroimaging pipelines. While deep generative models have shown promise in inpainting these lesions, most existing methods operate cross-sectionally or lack 3D anatomical continuity. We present a …

• Functionality-Oriented LLM Merging on the Fisher--Rao Manifold

  Jiayu Wang, Zuojun Ye, Wenpeng Yin · 6 de marzo de 2026

  Weight-space merging aims to combine multiple fine-tuned LLMs into a single model without retraining, yet most existing approaches remain fundamentally parameter-space heuristics. This creates three practical limitations. First, linear averaging, task vectors, and related rules operate on Euclidean …

• Harnessing Synthetic Data from Generative AI for Statistical Inference

  Ahmad Abdel-Azim, Ruoyu Wang, Xihong Lin · 6 de marzo de 2026

  The emergence of generative AI models has dramatically expanded the availability and use of synthetic data across scientific, industrial, and policy domains. While these developments open new possibilities for data analysis, they also raise fundamental statistical questions about when synthetic data…

• RelaxFlow: Text-Driven Amodal 3D Generation

  Jiayin Zhu, Guoji Fu, Xiaolu Liu, Qiyuan He, Yicong Li, Angela Yao · 6 de marzo de 2026

  Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we formalize text-driven amodal 3D generation, where text prompts steer the completion of unseen regions while strictly preservi…

• Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling

  Tal Daniel, Carl Qi, Dan Haramati, Amir Zadeh, Chuan Li, Aviv Tamar, Deepak Pathak, David Held · 6 de marzo de 2026

  We introduce Latent Particle World Model (LPWM), a self-supervised object-centric world model scaled to real-world multi-object datasets and applicable in decision-making. LPWM autonomously discovers keypoints, bounding boxes, and object masks directly from video data, enabling it to learn rich scen…

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

  Qingyong Zhu, Yumin Tan, Xiang Gu, Dong Liang · 6 de marzo de 2026

  Fully unsupervised deep generative modeling (FU-DGM) is promising for compressively sampled MRI (CS-MRI) when training data or compute are limited. Classical FU-DGMs such as DIP and INR rely on architectural priors, but the ill-conditioned inverse problem often demands many iterations and easily ove…

• Hyperspherical Latents Improve Continuous-Token Autoregressive Generation

  Guolin Ke, Hui Xue · 6 de marzo de 2026

  Autoregressive (AR) models are promising for image generation, yet continuous-token AR variants often trail latent diffusion and masked-generation models. The core issue is heterogeneous variance in VAE latents, which is amplified during AR decoding, especially under classifier-free guidance (CFG), …

• Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts

  Samandar Samandarov, Nazirjon Ismoiljonov, Abdullah Sattorov, Temirlan Sabyrbayev · 6 de marzo de 2026

  In the landscape of modern machine learning, frozen pre-trained models provide stability and efficiency but often underperform on specific tasks due to mismatched data distributions. This paper introduces the Whisperer, a novel visual prompting framework that learns diffusion-based preprocessors to …

• Latent Wasserstein Adversarial Imitation Learning

  Siqi Yang, Kai Yan, Alexander G. Schwing, Yu-Xiong Wang · 6 de marzo de 2026

  Imitation Learning (IL) enables agents to mimic expert behavior by learning from demonstrations. However, traditional IL methods require large amounts of medium-to-high-quality demonstrations as well as actions of expert demonstrations, both of which are often unavailable. To reduce this need, we pr…

• Probabilistic Dreaming for World Models

  Gavin Wong · 6 de marzo de 2026

  "Dreaming" enables agents to learn from imagined experiences, enabling more robust and sample-efficient learning of world models. In this work, we consider innovations to the state-of-the-art Dreamer model using probabilistic methods that enable: (1) the parallel exploration of many latent states; a…

• CubeComposer: Spatio-Temporal Autoregressive 4K 360{\deg} Video Generation from Perspective Video

  Lingen Li, Guangzhi Wang, Xiaoyu Li, Zhaoyang Zhang, Qi Dou, Jinwei Gu, Tianfan Xue, Ying Shan · 5 de marzo de 2026

  Generating high-quality 360{\deg} panoramic videos from perspective input is one of the crucial applications for virtual reality (VR), whereby high-resolution videos are especially important for immersive experience. Existing methods are constrained by computational limitations of vanilla diffusion …

• Kaleido: Open-Sourced Multi-Subject Reference Video Generation Model

  Zhenxing Zhang, Jiayan Teng, Zhuoyi Yang, Tiankun Cao, Cheng Wang, Xiaotao Gu, Jie Tang, Dan Guo, Meng Wang · 5 de marzo de 2026

  We present Kaleido, a subject-to-video~(S2V) generation framework, which aims to synthesize subject-consistent videos conditioned on multiple reference images of target subjects. Despite recent progress in S2V generation models, existing approaches remain inadequate at maintaining multi-subject cons…

• Weight Space Representation Learning via Neural Field Adaptation

  Zhuoqian Yang, Mathieu Salzmann, Sabine S\"usstrunk · 5 de marzo de 2026

  In this work, we investigate the potential of weights to serve as effective representations, focusing on neural fields. Our key insight is that constraining the optimization space through a pre-trained base model and low-rank adaptation (LoRA) can induce structure in weight space. Across reconstruct…