Generative Adversarial Networks and Image Synthesis

Derniers papiers

• Parameter-Efficient Generative Modeling with Controlled Vector Fields

  Peyman Morteza · 28 mai 2026

  We introduce a continuous-time generative modeling framework, motivated by the Chow-Rashevskii theorem, that builds expressive flows from a small set of fixed vector fields and learned scalar controls. Instead of learning an unconstrained high-dimensional vector field, our framework constructs the v…

• SmartDirector: Keyframe-Conditioned Cinematic Video Generation with Narrative Pacing Control

  Zhida Zhang, Jie Ma, Zhan Peng, Haoxue Wu, Yang Han, Jun Liang, Jie Cao, Jing Li · 28 mai 2026

  The narrative quality of a video fundamentally determines its perceptual value. Although existing video generation methods can produce visually appealing content, they predominantly rely on sparse conditioning signals such as text prompts or first/last frames, which limits precise control over narra…

• Tensor Memory: Fixed-Size Recurrent State for Long-Horizon Transformers

  Kabir Swain, Sijie Han, Daniel Karl I. Weidele, Mauro Martino, Antonio Torralba · 28 mai 2026

  Transformers process images and videos by flattening space and time into long token sequences. While attention and KV caching preserve past features, their memory grows with sequence length and they lack an explicit, persistent spatial state, making long-horizon video understanding and occlusion-sen…

• Hierarchical Synthetic Tabular Data Generation: A Hybrid Top-Down and Bottom-Up Framework

  Junfeng Nie, Alvin Jin, Xiaohui Chen · 28 mai 2026

  Existing approaches for synthetic tabular data generation are based on either purely generative models or LLMs, both of which struggle with data heterogeneity, logical consistency, rare-event coverage, and robustness in low-data regimes. In this paper, we propose a hierarchical hybrid top-down and b…

• Identifiable Bayesian Deep Generative Copulas with Unknown Layer Widths for Data with Arbitrary Marginal Distributions

  Joseph Feldman, Yuqi Gu · 28 mai 2026

  Deep generative models offer powerful tools for multivariate data analysis, but their black-box architectures are often unidentified and difficult to interpret. We introduce the Deep Discrete Encoder (DDE) Copula, an identifiable and interpretable generative model for multivariate data with arbitrar…

• Mind Dreamer: Untethering Imagination via Active Causal Intervention on Latent Manifolds

  Shaojun Xu, Xiaoling Zhou, Yihan Lin, Yapeng Meng, Xinglong Ji, Luping Shi, Rong Zhao · 28 mai 2026

  Model-Based Reinforcement Learning yields sample efficiency via latent imagination, yet remains constrained by Historical Tethering: imagination is typically initialized from observed states. This creates a learning asymmetry, where the world model's manifold discovery outpaces the policy's sparse-r…

• MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation

  Haitian Li, Yanghao Zhou, Heyan Huang, Liangji Chen, YiMing Cheng, Xu Liu, Dian Jin, Jiajun Xu, Jingyun Liao, Tian Lan, Ziqin Zhou, Yueying Liu, Yu Bai, Changsen Yuan, Jinxing Zhou, Xian-Ling Mao, Xuefeng Chen, Yousheng Feng · 28 mai 2026

  In recent years, Multi-Talker Audio-Video Generation (MTAVG) models have shown promising performance on fundamental metrics such as lip-sync and audio-visual alignment. However, these metrics remain insufficient for assessing cinematic expressiveness in scene-level generation. In multi-character sce…

• Utility-Aware Multimodal Contrastive Learning for Product Image Generation

  Xiaohang Feng, Yiling Xie · 28 mai 2026

  Product images strongly influence consumer decision-making in online marketplaces. Empowered by multimodal contrastive learning, generative AI can output images that closely align with text prompts. Yet existing generative AI models do not directly optimize marketplace performance. This is a critica…

• Measure-to-measure Regression with Transformers

  Matthew Vandergrift, Martha White, Yury Polyanskiy, Philippe Rigollet, Lazar Atanackovic · 28 mai 2026

  Many learning problems require predicting how populations evolve under an unknown transformation. A natural representation for such populations is a probability measure, with point clouds as a key example. In this work, we study the measure-to-measure (M2M) regression problem, in which one seeks to …

• Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations

  Bartosz Wieciech, Zmnako Awrahman, Marcin Czelej, Victor Hugo Jaramillo Velasquez, Wioletta Stobieniecka · 28 mai 2026

  Sparse Autoencoders (SAEs) extract interpretable features from Large Language Models, but standard variants enforce non-negativity, forcing separate latents for diametrically opposed concepts (e.g., "pressure too high" vs. "pressure too low") and wasting dictionary capacity when features are anticor…

• Stage-wise Distortion-Perception Traversal in Zero-shot Inverse Problems with Diffusion Models

  Jiawei Zhang, Ziyuan Liu, Leon Yan, Zhenyu Xiao, Yuantao Gu · 28 mai 2026

  The distortion-perception (D-P) tradeoff is a fundamental phenomenon of Bayesian inverse problems, which characterizes the inherent tension between distortion performance and perceptual quality. Enabling flexible traversal of the D-P tradeoff at inference time is crucial for practical applications. …

• Triangular-Reference Schr\"odinger Bridges for Time Series Generation

  Gabriele Bocchi · 28 mai 2026

  We introduce Triangular-Reference Schr\"odinger Bridges for Time Series (TR-SBTS), a conservative extension of the SBTS framework in which the Brownian reference is replaced by an intervalwise frozen, possibly degenerate diffusion reference, triangular across a hierarchy of latent volatility levels.…

• Structure over Pixels: Learning Variable-Length Visual Programs

  Piotr Wyrwi\'nski, Kacper Dobek, Krzysztof Krawiec · 28 mai 2026

  Discrete visual tokenizers translate images into ordered sequences of codes, providing a natural representation for structural description of scenes. Yet existing adaptive tokenizers either require post-hoc search or select among a discrete set of pre-trained rates, rather than learning a continuous…

• Conservative neural posterior estimation via distributionally robust training

  William Laplante, Yuga Hikida, Charita Dellaporta, Fran\c{c}ois-Xavier Briol, Ayush Bharti · 28 mai 2026

  Simulation-based inference with neural posterior estimation (NPE) often yields overconfident and unreliable posteriors under limited simulation budgets. To address this, we propose DRO-NPE, a distributionally robust approach that replaces the standard NPE objective with a worst-case loss over a Wass…

• From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection

  Ke Liu, Jiwei Wei, Wenyu Zhang, Shuchang Zhou, Ruikun Chai, Yutao Dai, Chaoning Zhang, Yang Yang · 28 mai 2026

  With rapid advances in audio-visual generative models, reliable forgery detection becomes increasingly critical. Existing methods for audio-visual deepfake detection typically rely on cross-modal inconsistencies. In singing, rhythmic vocalization weakens this coupling and introduces a nontrivial dom…

• Learn from your own latents and not from tokens: A sample-complexity theory

  Daniel J. Korchinski, Alessandro Favero, Matthieu Wyart · 28 mai 2026

  Generative models, from diffusion models to large language models, achieve remarkable performance but at a cost in training data orders of magnitude larger than what biological learners require. An alternative paradigm has emerged in which networks are trained to predict their \emph{own} latent repr…

• Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024

  Nuria Alina Chandra, Hannah Lee, Ryan Murtfeldt, Lin Qiu, Arnab Karmakar, Emmanuel Tanumihardja, Kevin Farhat, Ben Caffee, Changyeon Lee, Jongwook Choi, Sejin Paik, Aerin Kim, Oren Etzioni · 28 mai 2026

  In the age of increasingly realistic generative AI, robust deepfake detection is essential for mitigating fraud and disinformation. While many deepfake detectors report high accuracy on academic datasets, we show that these academic benchmarks are out of date and not representative of real-world dee…

• BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models

  Fei Deng, Yanwu Xu, Zhipeng Bao, Zhixing Zhang, Haolin Jia, Karthik Raveendran, Jianing Wei · 28 mai 2026

  The remarkable generation quality of modern diffusion models often comes at the cost of massive parameter counts, which necessitate server-side inference with significant computational costs and potential privacy risks. Consequently, there is growing momentum toward developing efficient on-device al…

• Noise Scheduling as Information-Guided Allocation in Diffusion Training

  Gabriel Raya, Bac Nguyen, Georgios Batzolis, Yuhta Takida, Dejan Stancevic, Naoki Murata, Chieh-Hsin Lai, Yuki Mitsufuji, Luca Ambrogioni · 28 mai 2026

  We introduce InfoNoise, an online adaptive noise schedule for diffusion training that reallocates optimization effort toward noise levels where denoising is most informative. Together with loss weighting, a noise schedule induces an effective allocation across denoising problems, often fixed before …

• GenSBI: Generative Methods for Simulation-Based Inference in JAX

  Aurelio Amerio · 28 mai 2026

  Flow and diffusion generative models have established themselves as widely adopted density estimators for simulation-based inference (SBI), extending naturally from neural posterior estimation to likelihood and joint density estimation. Their principled optimization objectives and freedom from archi…

• Continual Model Routing in Evolving Model Hubs

  Jack Bell, Giacomo Carf\`i, Gerlando Gramaglia, Vincenzo Lomonaco · 28 mai 2026

  AI model hubs provide access to a rapidly growing collection of powerful pre-trained models, enabling off-the-shelf mixture-of-experts systems with different routing strategies. However, this rapid growth poses two fundamental challenges: scaling model selection across thousands of experts and conti…

• Representation-Conditioned Diffusion Models for Guided Training Data Generation

  Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen · 28 mai 2026

  Data availability remains a critical bottleneck in many deep learning applications. Large-scale datasets are often expensive to collect, curate and annotate, which can limit the scalability and applicability of supervised learning methods. In this work, we evaluate the classification performance of …

• Transformers Provably Learn to Internalize Chain-of-Thought

  Yixiao Huang, Hanlin Zhu, Zixuan Wang, Jiantao Jiao, Stuart Russell, Somayeh Sojoudi, Song Mei · 28 mai 2026

  Chain-of-Thought (CoT) prompting substantially improves the sample efficiency of transformers, reducing the complexity of tasks like parity learning from exponential to polynomial in the input length. However, generating explicit reasoning steps at inference is computationally expensive. Implicit Ch…

• JLT: Clean-Latent Prediction in Latent Diffusion Transformers

  Funing Fu, Tenghui Wang, Junyong Cen, Qichao Zhu, Guanyu Zhou · 27 mai 2026

  Flow matching with clean-data prediction has shown that regressing the clean point can exploit low-dimensional structure more effectively than predicting an ambient noised quantity. We ask whether this principle remains useful after images are mapped into a learned latent space, where compression ha…

• From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models

  Yuchen Liang, Ness Shroff, Yingbin Liang · 27 mai 2026

  Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, but, especially for uniform-rate models, they often require many steps to generate a single sample. Existing acceleration methods either rely on training additional quantities or suffer from slow…