Generative Adversarial Networks and Image Synthesis

Últimos artículos

• Energy-Entropy Regularization: The True Power of Minimal Looped Transformers

  Wai-Lun Lam · 15 de enero de 2026

  Recent research suggests that looped Transformers have superior reasoning capabilities compared to standard deep architectures. Current approaches to training single-head looped architectures on benchmark tasks frequently fail or yield suboptimal performance due to a highly non-convex and irregular …

• Sim2real Image Translation Enables Viewpoint-Robust Policies from Fixed-Camera Datasets

  Jeremiah Coholich, Justin Wit, Robert Azarcon, Zsolt Kira · 15 de enero de 2026

  Vision-based policies for robot manipulation have achieved significant recent success, but are still brittle to distribution shifts such as camera viewpoint variations. Robot demonstration data is scarce and often lacks appropriate variation in camera viewpoints. Simulation offers a way to collect r…

• Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation

  Xingyao Li, Fengzhuo Zhang, Cunxiao Du, Hui Ji · 15 de enero de 2026

  Despite significant progress in autoregressive image generation, inference remains slow due to the sequential nature of AR models and the ambiguity of image tokens, even when using speculative decoding. Recent works attempt to address this with relaxed speculative decoding but lack theoretical groun…

• Universal Dynamics of Warmup Stable Decay: understanding WSD beyond Transformers

  Annalisa Belloni, Lorenzo Noci, Antonio Orvieto · 15 de enero de 2026

  The Warmup Stable Decay (WSD) learning rate scheduler has recently become popular, largely due to its good performance and flexibility when training large language models. It remains an open question whether the remarkable performance of WSD - using a decaying learning rate for only a fraction of tr…

• Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization

  Frank R\"oder, Jan Benad, Manfred Eppe, Pradeep Kr. Banerjee · 15 de enero de 2026

  Real-world reinforcement learning demands adaptation to unseen environmental conditions without costly retraining. Contextual Markov Decision Processes (cMDP) model this challenge, but existing methods often require explicit context variables (e.g., friction, gravity), limiting their use when contex…

• TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts

  Yu Xu, Hongbin Yan, Juan Cao, Yiji Cheng, Tiankai Hang, Runze He, Zijin Yin, Shiyi Zhang, Yuxin Zhang, Jintao Li, Chunyu Wang, Qinglin Lu, Tong-Yee Lee, Fan Tang · 15 de enero de 2026

  Unified image generation and editing models suffer from severe task interference in dense diffusion transformers architectures, where a shared parameter space must compromise between conflicting objectives (e.g., local editing v.s. subject-driven generation). While the sparse Mixture-of-Experts (MoE…

• Spectral Generative Flow Models: A Physics-Inspired Replacement for Vectorized Large Language Models

  Andrew Kiruluta · 15 de enero de 2026

  We introduce Spectral Generative Flow Models (SGFMs), a physics-inspired alternative to transformer-based large language models. Instead of representing text or video as sequences of discrete tokens processed by attention, SGFMs treat generation as the evolution of a continuous field governed by con…

• R$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images

  Qingyu Liu, Zhongjie Ba, Jianmin Guo, Qiu Wang, Zhibo Wang, Jie Shi, Kui Ren · 15 de enero de 2026

  Recently, reconstruction-based methods have gained attention for AIGC image detection. These methods leverage pre-trained diffusion models to reconstruct inputs and measure residuals for distinguishing real from fake images. Their key advantage lies in reducing reliance on dataset-specific artifacts…

• Training-Free Distribution Adaptation for Diffusion Models via Maximum Mean Discrepancy Guidance

  Matina Mahdizadeh Sani, Nima Jamali, Mohammad Jalali, Farzan Farnia · 14 de enero de 2026

  Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data. Such mismatches are especially problematic in domain adaptation tasks, where only a…

• Generative Semantic Communication: Diffusion Models Beyond Bit Recovery

  Eleonora Grassucci, Sergio Barbarossa, Danilo Comminiello · 14 de enero de 2026

  Semantic communication is expected to be one of the cores of next-generation AI-based communications. One of the possibilities offered by semantic communication is the capability to regenerate, at the destination side, images or videos semantically equivalent to the transmitted ones, without necessa…

• Coupled Diffusion-Encoder Models for Reconstruction of Flow Fields

  AmirPouya Hemmasian, Amir Barati Farimani · 14 de enero de 2026

  Data-driven flow-field reconstruction typically relies on autoencoder architectures that compress high-dimensional states into low-dimensional latent representations. However, classical approaches such as variational autoencoders (VAEs) often struggle to preserve the higher-order statistical structu…

• WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation

  Zishan Shu, Juntong Wu, Wei Yan, Xudong Liu, Hongyu Zhang, Chang Liu, Youdong Mao, Jie Chen · 14 de enero de 2026

  Vision modeling has advanced rapidly with Transformers, whose attention mechanisms capture visual dependencies but lack a principled account of how semantic information propagates spatially. We revisit this problem from a wave-based perspective: feature maps are treated as spatial signals whose evol…

• Al\'em do Desempenho: Um Estudo da Confiabilidade de Detectores de Deepfakes

  Lucas Lopes, Rayson Laroca, Andr\'e Gr\'egio · 14 de enero de 2026

  Deepfakes are synthetic media generated by artificial intelligence, with positive applications in education and creativity, but also serious negative impacts such as fraud, misinformation, and privacy violations. Although detection techniques have advanced, comprehensive evaluation methods that go b…

• Deconstructing Pre-training: Knowledge Attribution Analysis in MoE and Dense Models

  Bo Wang, Junzhuo Li, Hong Chen, Yuanlin Chu, Yuxuan Fan, Xuming Hu · 14 de enero de 2026

  Mixture-of-Experts (MoE) architectures decouple model capacity from per-token computation, enabling scaling beyond the computational limits imposed by dense scaling laws. Yet how MoE architectures shape knowledge acquisition during pre-training, and how this process differs from dense architectures,…

• Deep Exploration of Epoch-wise Double Descent in Noisy Data: Signal Separation, Large Activation, and Benign Overfitting

  Tomoki Kubo, Ryuken Uda, Yusuke Iida · 14 de enero de 2026

  Deep double descent is one of the key phenomena underlying the generalization capability of deep learning models. In this study, epoch-wise double descent, which is delayed generalization following overfitting, was empirically investigated by focusing on the evolution of internal structures. Fully c…

• DGAE: Diffusion-Guided Autoencoder for Efficient Latent Representation Learning

  Dongxu Liu, Jiahui Zhu, Yuang Peng, Haomiao Tang, Yuwei Chen, Chunrui Han, Zheng Ge, Daxin Jiang, Mingxue Liao · 14 de enero de 2026

  Autoencoders empower state-of-the-art image and video generative models by compressing pixels into a latent space through visual tokenization. Although recent advances have alleviated the performance degradation of autoencoders under high compression ratios, addressing the training instability cause…

• Multi-Personality Generation of LLMs at Decoding-time

  Rongxin Chen, Yunfan Li, Yige Yuan, Bingbing Xu, Huawei Shen · 14 de enero de 2026

  Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are costly and poorly scalable, while decoding-time methods often rely on external models or heuristics, limiting flexibili…

• IGAN: A New Inception-based Model for Stable and High-Fidelity Image Synthesis Using Generative Adversarial Networks

  Ahmed A. Hashim, Ali Al-Shuwaili, Asraa Saeed, Ali Al-Bayaty · 14 de enero de 2026

  Generative Adversarial Networks (GANs) face a significant challenge of striking an optimal balance between high-quality image generation and training stability. Recent techniques, such as DCGAN, BigGAN, and StyleGAN, improve visual fidelity; however, such techniques usually struggle with mode collap…

• SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models

  Renyang Liu, Kangjie Chen, Han Qiu, Jie Zhang, Kwok-Yan Lam, Tianwei Zhang, See-Kiong Ng · 14 de enero de 2026

  Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from their training data, leading to the reproduction of unsafe content such as NSFW imagery and copyrighted artistic styles. Such behaviors pose persistent…

• HIPPO: Accelerating Video Large Language Models Inference via Holistic-aware Parallel Speculative Decoding

  Qitan Lv, Tianyu Liu, Wen Wu, Xuenan Xu, Bowen Zhou, Feng Wu, Chao Zhang · 14 de enero de 2026

  Speculative decoding (SD) has emerged as a promising approach to accelerate LLM inference without sacrificing output quality. Existing SD methods tailored for video-LLMs primarily focus on pruning redundant visual tokens to mitigate the computational burden of massive visual inputs. However, existin…

• TP-Blend: Textual-Prompt Attention Pairing for Precise Object-Style Blending in Diffusion Models

  Xin Jin, Yichuan Zhong, Yapeng Tian · 14 de enero de 2026

  Current text-conditioned diffusion editors handle single object replacement well but struggle when a new object and a new style must be introduced simultaneously. We present Twin-Prompt Attention Blend (TP-Blend), a lightweight training-free framework that receives two separate textual prompts, one …

• Revealing the Attention Floating Mechanism in Masked Diffusion Models

  Xin Dai, Pengcheng Huang, Zhenghao Liu, Shuo Wang, Yukun Yan, Chaojun Xiao, Yu Gu, Ge Yu, Maosong Sun · 14 de enero de 2026

  Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This paper investigates the attention behaviors in MDMs, revealing …

• Motion Attribution for Video Generation

  Xindi Wu, Despoina Paschalidou, Jun Gao, Antonio Torralba, Laura Leal-Taix\'e, Olga Russakovsky, Sanja Fidler, Jonathan Lorraine · 14 de enero de 2026

  Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework that scales to modern, large, high-quality video datasets and m…

• Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function

  Hyeongyu Kang, Jaewoo Lee, Woocheol Shin, Kiyoung Om, Jinkyoo Park · 14 de enero de 2026

  Diffusion models excel at generating high-likelihood samples but often require alignment with downstream objectives. Existing fine-tuning methods for diffusion models significantly suffer from reward over-optimization, resulting in high-reward but unnatural samples and degraded diversity. To mitigat…

• FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training

  Fuhan Cai, Yong Guo, Jie Li, Wenbo Li, Jian Chen, Xiangzhong Fang · 14 de enero de 2026

  Recent advancements in text-to-image (T2I) generation have led to the emergence of highly expressive models such as diffusion transformers (DiTs), exemplified by FLUX. However, their massive parameter sizes lead to slow inference, high memory usage, and poor deployability. Existing acceleration meth…