Generative Adversarial Networks and Image Synthesis

Neueste Paper

• Akasha 2: Hamiltonian State Space Duality and Visual-Language Joint Embedding Predictive Architectur

  Yani Meziani · 13. Januar 2026

  We present Akasha 2, a state-of-the-art multimodal architecture that integrates Hamiltonian State Space Duality (H-SSD) with Visual-Language Joint Embedding Predictive Architecture (VL-JEPA). The system leverages the Mamba-3 Selective State Space Model (SSM) augmented by a Sparse Mixture of Hamilton…

• OSCAR: Optical-aware Semantic Control for Aleatoric Refinement in Sar-to-Optical Translation

  Hyunseo Lee, Sang Min Kim, Ho Kyung Shin, Taeheon Kim, Woo-Jeoung Nam · 13. Januar 2026

  Synthetic Aperture Radar (SAR) provides robust all-weather imaging capabilities; however, translating SAR observations into photo-realistic optical images remains a fundamentally ill-posed problem. Current approaches are often hindered by the inherent speckle noise and geometric distortions of SAR d…

• Hellinger Multimodal Variational Autoencoders

  Huyen Khanh Vo, Isabel Valera · 13. Januar 2026

  Multimodal variational autoencoders (VAEs) are widely used for weakly supervised generative learning with multiple modalities. Predominant methods aggregate unimodal inference distributions using either a product of experts (PoE), a mixture of experts (MoE), or their combinations to approximate the …

• Inference-Time Alignment for Diffusion Models via Doob's Matching

  Jinyuan Chang, Chenguang Duan, Yuling Jiao, Yi Xu, Jerry Zhijian Yang · 13. Januar 2026

  Inference-time alignment for diffusion models aims to adapt a pre-trained diffusion model toward a target distribution without retraining the base score network, thereby preserving the generative capacity of the base model while enforcing desired properties at the inference time. A central mechanism…

• Variational decomposition autoencoding improves disentanglement of latent representations

  Ioannis Ziogas, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. Hadjileontiadis · 13. Januar 2026

  Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn disentangled and interpretable representations is critical for unco…

• Forgetting Similar Samples: Can Machine Unlearning Do it Better?

  Heng Xu, Tianqing Zhu, Dayong Ye, Lefeng Zhang, Le Wang, Wanlei Zhou · 13. Januar 2026

  Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extensive research has focused on developing efficient machine unlearning strategies, we argue that these methods mainly aim a…

• Constrained Density Estimation via Optimal Transport

  Yinan Hu, Estaban Tabak · 13. Januar 2026

  A novel framework for density estimation under expectation constraints is proposed. The framework minimizes the Wasserstein distance between the estimated density and a prior, subject to the constraints that the expected value of a set of functions adopts or exceeds given values. The framework is ge…

• The Practicality of Normalizing Flow Test-Time Training in Bayesian Inference for Agent-Based Models

  Junyao Zhang, Jinglai Li, Junqi Tang · 13. Januar 2026

  Agent-Based Models (ABMs) are gaining great popularity in economics and social science because of their strong flexibility to describe the realistic and heterogeneous decisions and interaction rules between individual agents. In this work, we investigate for the first time the practicality of test-t…

• Empirical Analysis of Decoding Biases in Masked Diffusion Models

  Pengcheng Huang, Tianming Liu, Zhenghao Liu, Yukun Yan, Shuo Wang, Tong Xiao, Zulong Chen, Maosong Sun · 13. Januar 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 …

• Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers

  Binxu Wang, Jingxuan Fan, Xu Pan · 13. Januar 2026

  Diffusion Transformers (DiTs) have greatly advanced text-to-image generation, but models still struggle to generate the correct spatial relations between objects as specified in the text prompt. In this study, we adopt a mechanistic interpretability approach to investigate how a DiT can generate cor…

• Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics

  Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma · 13. Januar 2026

  Post-training activation compression is essential for deploying Large Language Models (LLMs) on resource-constrained hardware. However, standard methods like Singular Value Decomposition (SVD) are gradient-blind: they preserve high-variance dimensions regardless of their impact on factual knowledge …

• Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models

  Kaiyuan Deng, Gen Li, Yang Xiao, Bo Hui, Xiaolong Ma · 13. Januar 2026

  Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending multi-concept unlearning to large-scale scenarios remains difficult due to three challenges: (i) conflicting weight upd…

• Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint

  Zhihao Liu, Jian Lou, Yuke Hu, Xiaochen Li, Yitian Chen, Tailun Chen, Zhizhen Qin, Kui Ren, Zhan Qin · 13. Januar 2026

  Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data owners may request the removal of their data from trained models. Machine unlearning provides a practical solution by removing the influen…

• Multi-Agent Framework for Controllable and Protected Generative Content Creation: Addressing Copyright and Provenance in AI-Generated Media

  Haris Khan, Sadia Asif, Shumaila Asif · 13. Januar 2026

  The proliferation of generative AI systems creates unprecedented opportunities for content creation while raising critical concerns about controllability, copyright infringement, and content provenance. Current generative models operate as "black boxes" with limited user control and lack built-in me…

• AGDC: Autoregressive Generation of Variable-Length Sequences with Joint Discrete and Continuous Spaces

  Yeonsang Shin, Insoo Kim, Bongkeun Kim, Keonwoo Bae, Bohyung Han · 12. Januar 2026

  Transformer-based autoregressive models excel in data generation but are inherently constrained by their reliance on discretized tokens, which limits their ability to represent continuous values with high precision. We analyze the scalability limitations of existing discretization-based approaches f…

• Compressing image encoders via latent distillation

  Caroline Mazini Rodrigues (IRISA, CNRS), Nicolas Keriven (CNRS, IRISA, COMPACT), Thomas Maugey (COMPACT) · 12. Januar 2026

  Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and require substantial training data and computational resources. We propose a metho…

• Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception

  Yuankun Xie, Ruibo Fu, Zhiyong Wang, Xiaopeng Wang, Songjun Cao, Long Ma, Haonan Cheng, Long Ye · 12. Januar 2026

  The rapid advancement of audio generation technologies has escalated the risks of malicious deepfake audio across speech, sound, singing voice, and music, threatening multimedia security and trust. While existing countermeasures (CMs) perform well in single-type audio deepfake detection (ADD), their…

• Quantifying and Inducing Shape Bias in CNNs via Max-Pool Dilation

  Takito Sawada, Akinori Iwata, Masahiro Okuda · 12. Januar 2026

  Convolutional Neural Networks (CNNs) are known to exhibit a strong texture bias, favoring local patterns over global shape information--a tendency inherent to their convolutional architecture. While this bias is beneficial for texture-rich natural images, it often degrades performance on shape-domin…

• A Bayesian Generative Modeling Approach for Arbitrary Conditional Inference

  Qiao Liu, Wing Hung Wong · 12. Januar 2026

  Modern data analysis increasingly requires flexible conditional inference P(X_B | X_A) where (X_A, X_B) is an arbitrary partition of observed variable X. Existing conditional inference methods lack this flexibility as they are tied to a fixed conditioning structure and cannot perform new conditional…

• VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

  Longbin Ji, Xiaoxiong Liu, Junyuan Shang, Shuohuan Wang, Yu Sun, Hua Wu, Haifeng Wang · 12. Januar 2026

  Recent advances in video generation have been dominated by diffusion and flow-matching models, which produce high-quality results but remain computationally intensive and difficult to scale. In this work, we introduce VideoAR, the first large-scale Visual Autoregressive (VAR) framework for video gen…

• Measurement-Consistent Langevin Corrector: A Remedy for Latent Diffusion Inverse Solvers

  Lee Hyoseok, Sohwi Lim, Eunju Cha, Tae-Hyun Oh · 9. Januar 2026

  With recent advances in generative models, diffusion models have emerged as powerful priors for solving inverse problems in each domain. Since Latent Diffusion Models (LDMs) provide generic priors, several studies have explored their potential as domain-agnostic zero-shot inverse solvers. Despite th…

• Stochastic Deep Learning: A Probabilistic Framework for Modeling Uncertainty in Structured Temporal Data

  James Rice · 9. Januar 2026

  I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal data. This approach, termed Stochastic Latent Differential Inference (SLDI), embed…

• Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models

  Zitong Huang, Kaidong Zhang, Yukang Ding, Chao Gao, Rui Ding, Ying Chen, Wangmeng Zuo · 9. Januar 2026

  Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is inefficient and often yields ambiguous global supervision. To addr…

• STDD:Spatio-Temporal Dynamics-Driven Token Refinement in Diffusion Language Models

  Xinhao Sun, Maoliang Li, Zihao Zheng, Jiayu Chen, Hezhao Xu, Yun Liang, Xiang Chen · 9. Januar 2026

  Unlike autoregressive language models, diffusion language models (DLMs) generate text by iteratively denoising all token positions in parallel. At each timestep, the remasking strategy of a DLM selects low-priority tokens to defer their decoding, thereby improving both efficiency and output quality.…

• DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights

  Saumya Gupta, Scott Biggs, Moritz Laber, Zohair Shafi, Robin Walters, Ayan Paul · 9. Januar 2026

  Building efficient and effective generative models for neural network weights has been a research focus of significant interest that faces challenges posed by the high-dimensional weight spaces of modern neural networks and their symmetries. Several prior generative models are limited to generating …