Generative Adversarial Networks and Image Synthesis

Neueste Paper

• LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models

  Hyunsoo Han, Sangyeop Yeo, Jaejun Yoo · 20. Mai 2026

  We demonstrate that in knowledge distillation for diffusion models, the teacher network's highly complex denoising process - stemming from its substantially larger capacity - poses a significant challenge for the student model to faithfully mimic. To address this problem, we propose a coarse-to-fine…

• Activation Functions, Statistics and Learning of Higher-Order Interactions in Restricted Boltzmann Machines

  Giovanni di Sarra, Yasser Roudi · 20. Mai 2026

  The great success of neural networks in recognizing hidden patterns and correlations in complex data lies in the way they take advantage of the large number of parameters and nonlinear single-unit activation, jointly. Restricted Boltzmann Machines (RBMs) provide a simple yet powerful framework for s…

• CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation

  Gyubin Lee, Junwon Lee, Juhan Nam · 20. Mai 2026

  We investigate Counterfactual Video Foley Generation, which aims to adopt a sound-source identity that contradicts the visual evidence while remaining temporally synchronized to a silent video. Existing Video&Text-to-Audio (VT2A) models struggle with this, often remaining anchored to the visually im…

• Rebalancing Reference Frame Dominance to Improve Motion in Image-to-Video Models

  Wooseok Jeon, Seungho Park, Seunghyun Shin, Sangeyl Lee, Hyeonho Jeong, Hae-Gon Jeon · 20. Mai 2026

  Image-to-video models often generate videos that remain overly static, compared to text-to-video models. While prior approaches mitigate this issue by weakening or modifying the image-conditioning signal, they often require additional training or sacrifice fidelity to the reference image. In this wo…

• HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Heads

  Juyuan Wang, Chenxing Wang, Yuchen Fang, Huiyun Hu, Junwu Du, Aolin Li, Shunlin Rong, Haijun Wu, Jin Xu, Ligang Liu, Dongliang Liao · 20. Mai 2026

  Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over autoregressive approaches, yet suffer from attention score homogenization: middle-context documents receive near-identical scores, destroying the fine-grained dis…

• Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics

  Benjamin Sterling, M\'onica F. Bugallo, Tom Tirer · 20. Mai 2026

  Diffusion/score-based models have emerged as powerful generative models, capable of generating high-quality samples that mimic the training data distribution. However, it has been observed that they are prone to reproducing training samples-known as "memorization"-potentially violating copyright and…

• PROWL: Prioritized Regret-Driven Optimization for World Model Learning

  Ahmet H. G\"uzel, Jenny Seidenschwarz, Benjamin Graham, Jonathan Sadeghi, Jeffrey Hawke, Jack Parker-Holder, Ilija Bogunovic · 20. Mai 2026

  Modern action-conditioned video world models achieve strong short-horizon visual realism, yet remain unreliable on rare, interaction-critical transitions that dominate downstream planning and policy performance. Because passive demonstration data systematically under-samples these high-impact regime…

• EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample

  Guohao Chen, Shuaicheng Niu, Geng Li, Yunbei Zhang, Shilin Shan, Chunyan Miao, Jianfei Yang · 20. Mai 2026

  Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend on backpropagation (BP), which incurs substantial memory overhead and makes them difficult to deploy on edge devices, quantized models, specialized ac…

• LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators

  Xinhe Zhang, Yuyang Zhang, Pengfei Jin, Arnau Marin-Llobet, Na Li, Quanzheng Li · 20. Mai 2026

  High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often fail to preserve anatomical consistency across the third dimension. We propose LiFT, a framework for Lifted inter-slice Feature Tra…

• Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement

  Taegu Kang, Jaesik Yoon, Sungjin Ahn · 20. Mai 2026

  Inference-time scaling has emerged as a major approach for improving reasoning capabilities, and has been increasingly applied to diffusion models. However, existing inference-time scaling methods for diffusion models typically rely on external verifiers or reward models to rank and select samples, …

• Probability-Conserving Flow Guidance

  Parsa Esmati, Junha Hyung, Amirhossein Dadashzadeh, Jaegul Choo, Majid Mirmehdi · 20. Mai 2026

  Diffusion and flow-based generative models dominate visual synthesis, with guidance aligning samples to user input and improving perceptual quality. However, Classifier-Free Guidance (CFG) and extrapolation-based methods are heuristic linear combinations of velocities/scores that ignore the generati…

• Motif-Video 2B: Technical Report

  Junghwan Lim, Wai Ting Cheung, Minsu Ha, Beomgyu Kim, Taewhan Kim, Haesol Lee, Dongpin Oh, Jeesoo Lee, Taehyun Kim, Minjae Kim, Sungmin Lee, Hyeyeon Cho, Dahye Choi, Jaeheui Her, Jaeyeon Huh, Hanbin Jung, Changjin Kang, Dongseok Kim, Jangwoong Kim, Youngrok Kim, Hyukjin Kweon, Hongjoo Lee, Jeongdoo Lee, Junhyeok Lee, Eunhwan Park, Yeongjae Park, Bokki Ryu, Dongjoo Weon · 20. Mai 2026

  Training strong video generation models usually requires massive datasets, large parameter counts, and substantial compute. In this work, we ask whether strong text-to-video quality is possible at a much smaller budget: fewer than 10M clips and less than 100,000 H200 GPU hours. Our core claim is tha…

• Lossless Anti-Distillation Sampling

  Zibo Diao, Jingchu Gai, Xinyue Ai, Zhang Zhang, Zhenyu He, Di He · 20. Mai 2026

  Frontier commercial generative models face a growing threat from distillation, whereby a distiller harvests generated responses and trains a competing model of its own at drastically lower cost. Existing defenses either rely on modifying the models outputs, thereby sacrificing response quality for b…

• Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing

  Valentina Njaradi, Cl\'ementine Domin\'e, Rachel Swanson, Marco Mondelli, Andrew Saxe · 20. Mai 2026

  Learning to generalise from limited data is a fundamental challenge for both artificial and biological systems. A common strategy is to extract reusable structure from abundant unlabelled data, enabling efficient adaptation to new tasks from limited labelled data. This two-stage paradigm is now stan…

• EMO-BOOST: Emotion-Augmented Audio-Visual Features for Improved Generalization in Deepfake Detection

  Aritra Marik, Marcel Klemt, Anna Rohrbach · 20. Mai 2026

  With every advancement in generative AI models, forensics is under increasing pressure. The constant emergence of new generation techniques makes it impossible to collect data for each manipulation to train a deepfake detection model. Thus, generalizing to deepfakes unseen during training is one of …

• Simply Stabilizing the Loop via Fully Looped Transformer

  Rao Fu, Zixuan Yang, Jiankun Zhang, Jing Ma, Hechang Chen, Yu Li, Yi Chang · 20. Mai 2026

  Scaling model performance typically requires increasing model size. Looped Transformer offers a compelling alternative by iteratively reusing the same Transformer blocks, trading additional computation for improved performance without increasing parameter count or context length. Because the number …

• D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting

  Tianyu Wu, Yu Yao, Zhenting Qi, Han Zheng, Zhuohan Wang, Haoran Ma, Lawrence Liao, Himabindu Lakkaraju, Ju Li, Yilun Du · 20. Mai 2026

  Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters such as DFlash predict the full B-token block in one forward pass, enabling deeper drafters and longer accepted blocks. Ho…

• Diffusion and Flow-based Copulas: Forgetting and Remembering Dependencies

  David Huk, Theodoros Damoulas · 20. Mai 2026

  Copulas are a fundamental tool for modelling multivariate dependencies in data, forming the method of choice in diverse fields and applications. However, the adoption of existing models for multimodal and high-dimensional dependencies is hindered by restrictive assumptions and poor scaling. In this …

• Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian

  Wenpin Tang, Nizar Touzi, Zikun Zhang, Xun Yu Zhou · 20. Mai 2026

  Diffusion models have achieved remarkable success in generating samples from unknown data distributions. Most popular stochastic differential equation-based diffusion models perturb the target distribution by adding Gaussian noise, transforming it into a simple prior, and then use denoising score ma…

• Markov Chain Decoders Overcome the Heavy-Tail Limitations of Lipschitz Generative Models

  Abdelhakim Ziani (MICS), Andras Horvath (UNITO), Paolo Ballarini (MICS) · 20. Mai 2026

  Heavy-tailed distributions are prevalent in performance evaluation, network traffic, and risk modeling. This behavior poses a fundamental challenge for modern deep generative models. Standard Variational Autoencoders (VAEs) employ Gaussian decoder likelihoods and Lipschitz-constrained neural network…

• Multi-Scale Generative Modeling with Heat Dissipation Flow Matching

  Jun Ma, Hanquan Zhang, Yanjun Qin, Haoyuan Guan, Ke Zhang · 20. Mai 2026

  Diffusion models are widely used in image generation, with most relying on noise-based corruption and denoising. A distinct branch instead uses blur as the main corruption, preserving better color budgets and multi-scale detail by providing multi-scale priors. However, blur-based models remain in SD…

• PhyWorld: Physics-Faithful World Model for Video Generation

  Pu Zhao, Juyi Lin, Timothy Rupprecht, Arash Akbari, Chence Yang, Rahul Chowdhury, Elaheh Motamedi, Arman Akbari, Yumei He, Chen Wang, Geng Yuan, Weiwei Chen, Yanzhi Wang · 20. Mai 2026

  World simulators can provide safe and scalable environments for training Physical AI systems before real-world deployment. Large video generation models are emerging as a promising basis for such simulators because they can generate diverse and realistic visual futures. However, using them as world …

• Stitched Value Model for Diffusion Alignment

  Hyojun Go, Hyungjin Chung, Prune Truong, Goutam Bhat, Li Mi, Zhaochong An, Zixiang Zhao, Dominik Narnhofer, Serge Belongie, Federico Tombari, Konrad Schindler · 20. Mai 2026

  For practical use, diffusion- or flow-based generative models must be aligned with task-specific rewards, such as prompt fidelity or aesthetic preference. That alignment is challenging because the reward is defined for clean output images, but the alignment procedure requires value function estimate…

• Latent Laplace Diffusion for Irregular Multivariate Time Series

  Zinuo You, Jin Zheng, John Cartlidge · 20. Mai 2026

  Irregular multivariate time series impose a trade-off for long-horizon forecasting: discrete methods can distort temporal structure via re-gridding, while continuous-time models often require sequential solvers prone to drift. To bridge this gap, we present Latent Laplace Diffusion (LLapDiff), a gen…

• Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection

  Yunzhe Zhang, Hongfu Liu, Pengyu Hong · 20. Mai 2026

  Text-to-image diffusion models can synthesize high-quality images, yet the outcome is notoriously sensitive to the random seed: different initial seeds often yield large variations in image quality and prompt-image alignment. We revisit this "seed effect" and show that attention dynamics over prompt…