Suche: diffusion models

Mehr als 1.000 Paper passen: hier die 1.000 neuesten, nach Relevanz sortiert.

• Catastrophic Compositional Generation: Why Vanilla Diffusion Models Fail to Extrapolate

  Duncan Soiffer, Chandler Squires, Yuan Guan, Jason Hartford, Pradeep Ravikumar · 24. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  The task of compositional generation involves using a conditional generative model, trained only on a subset of the possible conditions, to produce samples from compositionally-defined target distributions such as a geometric combination of the source distributions. In this work, we argue that this …

• Beyond the Autoregressive Horizon: A Comprehensive Survey of Diffusion Models, World Modelling, and State Space Models for Code

  Kishan Maharaj, Ashita Saxena, Srikanth Tamilselvam · 24. Juni 2026 · Software Engineering Research

  Autoregressive (AR) language models have driven significant progress in automated software engineering, enabling powerful code generation and assistance systems. However, the next-token prediction paradigm introduces structural limitations for code reasoning, including restricted global planning, ch…

• Prob-BBDM: a Probabilistic Brownian Bridge Diffusion Model for MRI sequence image-to-image translation

  Martin Valls (UFR SFA), Pascal Bourdon (UFR SFA), Christine Fernandez-Maloigne (LabCom I3M), Guillaume Herpe (CHU Poitiers -- Radio, DACTIM-MIS), David Helbert (UFR SFA) · 24. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  AI-driven image-to-image synthesis is rapidly advancing, with growing applications in medical imaging. Multi-modal image analysis plays a crucial role in optimizing examination quality, yet acquiring multiple imaging modalities in clinical settings remains resource-intensive and time-consuming, espe…

• Vera: A Layered Diffusion Model for Content-Preserving Video Editing

  Hongkai Zheng, Ta-Ying Cheng, Benjamin Klein, Yisong Yue, Zhuoning Yuan · 23. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  Video diffusion models have enabled remarkable progress in video generation and editing. However, content preservation remains a core challenge: existing methods regenerate every pixel and often alter elements that should remain unchanged, such as characters or background scenes. We introduce Vera, …

• TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger

  Vu Tuan Truong, Long Bao Le · 23. Juni 2026 · Adversarial Robustness in Machine Learning

  Diffusion models (DMs), despite their impressive capabilities across a wide range of generative tasks, have been shown to be vulnerable to backdoor attacks. However, existing backdoor methods face critical trade-offs among key factors: attack performance, stealthiness, time complexity, and required …

• Controllable Texture Tiling with Transformed RoPE-Enhanced Diffusion Models

  Junrong Huang, Zhiyuan Zhang, Rui Tang, Hongbo Fu, Jnig Liao · 23. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  Realistic integration of user-specified textures into scene images is a fundamental task in computer graphics and image editing. While existing material transfer and reference-guided inpainting methods can edit surface appearances, they often fail to address the specific requirements of texture tili…

• Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics

  Shujia Li, Jianshu Hu, Haiyu Zhang, Yunpeng Jiang, Haoyuan Jin, Xinyuan Chen, Yaohui Wang, Yutong Ban · 23. Juni 2026 · Human Motion and Animation

  Synthesizing realistic Human-Object Interactions (HOI) is critical for creating embodied avatars and functional virtual environments. However, current data-driven approaches primarily rely on motion capture datasets, which are expensive to scale and limited in functional diversity. Models trained wi…

• Modular Diffusion Models for Structured Visual Recognition

  Siddhesh Khandelwal, Björn Ommer, Leonid Sigal · 23. Juni 2026 · Domain Adaptation and Few-Shot Learning

  Traditional supervised methods for structured visual recognition tasks -- such as object detection, segmentation, and scene graph generation -- often produce deterministic, fixed outputs, limiting their ability to capture the inherent uncertainty in complex visual scenes. As a consequence, such poin…

• Prompting Diffusion Models for Zero-Shot Instance Segmentation

  Irem Zeynep Alagöz, Nils Morbitzer, Andrea Ramazzina, Nassir Navab, Federico Tombari, Stefano Gasperini · 23. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  Several disruptive research directions have recently emerged in computer vision, including foundation models achieving previously unseen zero-shot performance in scene understanding, even interactively, and generative models that synthesize extremely realistic images. The latter have also been shown…

• Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices

  Changxiao Cai, Yuchen Jiao, Gen Li · 23. Juni 2026 · Markov Chains and Monte Carlo Methods

  Diffusion models are known to exploit unknown low-dimensional structure to accelerate sampling. However, existing convergence theory under low-dimensional data structure has largely focused on update rules with narrowly prescribed coefficient choices. This raises a fundamental question: is adaptatio…

• Robust Diffusion Models via Divergence-Induced Weighted Denoising

  Lei Li, Yuexiao Dong · 23. Juni 2026 · Stochastic Gradient Optimization Techniques

  We show that replacing the standard MSE denoising loss in diffusion models with a nonlinear transformation induced by an f-divergence yields a simple robust training surrogate that empirically improves performance under data contamination, with small additional computational overhead. The theoretica…

• Variance-Tilted Diffusion Models for Diverse Sampling

  Iskander Azangulov, Leo Zhang, Kianoosh Ashouritaklimi · 23. Juni 2026 · Bayesian Methods and Mixture Models

  Diffusion models are typically sampled independently, even when the downstream objective is to obtain a diverse set of candidates. We introduce a variance-weighted batch distribution that favours collections of samples with large empirical spread after a prescribed linear feature map. The target is …

• PeLAP-A: Adaptive Latent Pruning for Lightweight Latent Diffusion Models

  Kissa Zahra, Zaib Un Nisa · 23. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  Latent diffusion models achieve strong generative performance by operating in a compressed latent space produced by a variational autoencoder (VAE). However, it remains unclear whether all latent channels contribute equally to the diffusion process, or whether significant redundancy exists. We intro…

• Detail++: Training-Free Detail Enhancer for T2I Diffusion Models

  Lifeng Chen, Jiner Wang, Zihao Pan, Beier Zhu, Xiaofeng Yang, Chi Zhang · 23. Juni 2026 · AI in cancer detection

  Recent advances in text-to-image (T2I) generation have led to impressive visual results. However, these models still face significant challenges when handling complex prompt, particularly those involving multiple subjects with distinct attributes. Inspired by the human drawing process, which first o…

• HyperQuant: A Rate-Distortion-Optimal Quantization Pipeline for Large Language and Diffusion Models

  Yuval Domb, Hadar Sackstein, Tomer Solberg · 23. Juni 2026 · Advanced Data Compression Techniques

  We present HyperQuant (Hadamard, optimallY Packing, Entropy Rice-coding), a unified post-training quantization pipeline for the weights and the KV cache of large language and diffusion transformers. Across a suite of self-contained experiments (Table 1), HyperQuant outperforms the recent HIGGS schem…

• CLIP-guided Diffusion Model for Backdoor Generation in Sensor-based Human Activity Recognition

  Toby Briston, Illya Kosyk, Kuniyih S · 23. Juni 2026 · Context-Aware Activity Recognition Systems

  Sensors are critical components of modern intelligent devices. The proliferation of the Internet of Things (IoT) and wearable mobile devices has enabled the integration of such sensors to monitor the environment and enable users to take predictive actions. Human activity recognition (HAR) is a popul…

• Through the PRISM: Preference Representation in Intermediate States of Video Diffusion Models

  Haoxuan Wu, Lai Man Po, Mengyang Liu, Kun Li, Hongzheng Yang, Wei Liu · 19. Juni 2026 · Image and Video Quality Assessment

  Evaluating video generation with clean, pixel-based reward models disconnects evaluation from the noisy diffusion process and incurs massive VAE decoding costs. In this paper, we challenge this paradigm by asking a fundamental question: Can a powerful video generator inherently discriminate preferen…

• FrozenDrive: Zero-Shot Text-Guided Driving Scene Generation and Data Augmentation with Parameter-Free Frozen Diffusion Model

  Yuhwan Jeong, Hyeonseong Kim, Daehyun We, Seonkyu Song, Jinnyeong Yang, Hyun-Kurl Jang, Youngho Yoon, Kuk-Jin Yoon · 19. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  Synthetic data for autonomous driving is surging, powered by diffusion models that promise scalable scene generation. Yet key obstacles remain, as enforcing multi-view and temporal consistency often relies on backbone fine-tuning or added layers, which erodes pre-trained knowledge and weakens text a…

• One-Shot Novel View and Pose Human Image Synthesis via 3D Prior Guided Diffusion Model

  Shenjian Gong, Kangkan Wang, Shanshan Zhang, Jian Yang · 19. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  This paper addresses the challenge of one-shot novel view and pose human image synthesis. The existing methods transfer the reference human image to a target pose using a set of 2D pose keypoints or synthesize human images based on generalizable human NeRF which uses human model priors to extract po…

• On the Redundancy of Timestep Embeddings in Diffusion Models

  Jos\'e A. Ch\'avez · 19. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  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…

• 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. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  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…

• Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures

  Jeeho Ryoo, Yongchan Jung, Muhammad Ali Khaliq, Weidong Zhang, Jiatong Han, Byeong Kil Lee · 19. Juni 2026 · Advanced Neuroimaging Techniques and Applications

  Diffusion models have become essential for high-fidelity 3D MRI synthesis, yet their deployment remains constrained by substantial GPU resource demands arising from hundreds of U-Net evaluations per sample and a highly heterogeneous kernel behavior. This paper performs a comprehensive performance an…

• 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. Juni 2026 · Generative Adversarial Networks and Image Synthesis

  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…

• VOiLA: Vectorized Online Planning with Learned Diffusion Model for POMDP Agents

  Marcus Hoerger, Rishikesh Joshi, Rahul Shome, Ian Manchester, Hanna Kurniawati · 19. Juni 2026 · Reinforcement Learning in Robotics

  Planning under uncertainty is an essential capability for autonomous robots. The Partially Observable Markov Decision Process (POMDP) provides a powerful framework for such a capability. Although POMDP-based planning has advanced significantly, its application to real-world problems is often limited…

• Flux-Guard: Facial Identity Protection using diffusion models

  Jie Wang, Tao Wang, Ru Zhang, Jianyi Liu · 17. Juni 2026 · Face recognition and analysis

  The widespread deployment of face recognition (FR) systems exposes personal images shared on social media and public platforms to identity linkage and privacy risks. Existing adversarial privacy protection methods can degrade unauthorized FR performance but are not compatible with generative face ed…