Generative Adversarial Networks and Image Synthesis

Latest papers

• Evidential Neural Radiance Fields

  Ruxiao Duan, Alex Wong · 2 March 2026

  Understanding sources of uncertainty is fundamental to trustworthy three-dimensional scene modeling. While recent advances in neural radiance fields (NeRFs) achieve impressive accuracy in scene reconstruction and novel view synthesis, the lack of uncertainty estimation significantly limits their dep…

• DesignSense: A Human Preference Dataset and Reward Modeling Framework for Graphic Layout Generation

  Varun Gopal, Rishabh Jain, Aradhya Mathur, Nikitha SR, Sohan Patnaik, Sudhir Yarram, Mayur Hemani, Balaji Krishnamurthy, Mausoom Sarkar · 2 March 2026

  Graphic layouts serve as an important and engaging medium for visual communication across different channels. While recent layout generation models have demonstrated impressive capabilities, they frequently fail to align with nuanced human aesthetic judgment. Existing preference datasets and reward …

• DiffusionHarmonizer: Bridging Neural Reconstruction and Photorealistic Simulation with Online Diffusion Enhancer

  Yuxuan Zhang, Katar\'ina T\'othov\'a, Zian Wang, Kangxue Yin, Haithem Turki, Riccardo de Lutio, Yen-Yu Chang, Or Litany, Sanja Fidler, Zan Gojcic · 2 March 2026

  Simulation is essential to the development and evaluation of autonomous robots such as self-driving vehicles. Neural reconstruction is emerging as a promising solution as it enables simulating a wide variety of scenarios from real-world data alone in an automated and scalable way. However, while met…

• SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching

  Yasaman Haghighi, Alexandre Alahi · 2 March 2026

  Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential denoising steps. This has motivated a growing line of research on accelerating diffusion inference. Among training-free acceleration methods, caching reduce…

• Score-Regularized Joint Sampling with Importance Weights for Flow Matching

  Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei, Truong Nguyen · 2 March 2026

  Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets. Independent sampling often yields high-variance estimates, especially when rare but high-impact outcomes dominate the expect…

• Learning Generation Orders for Masked Discrete Diffusion Models via Variational Inference

  David Fox, Sam Bowyer, Song Liu, Laurence Aitchison, Raul Santos-Rodriguez, Mengyue Yang · 2 March 2026

  Masked discrete diffusion models (MDMs) are a promising new approach to generative modelling, offering the ability for parallel token generation and therefore greater efficiency than autoregressive counterparts. However, achieving an optimal balance between parallel generation and sample quality rem…

• TradeFM: A Generative Foundation Model for Trade-flow and Market Microstructure

  Maxime Kawawa-Beaudan, Srijan Sood, Kassiani Papasotiriou, Daniel Borrajo, Manuela Veloso · 2 March 2026

  Foundation models have transformed domains from language to genomics by learning general-purpose representations from large-scale, heterogeneous data. We introduce TradeFM, a 524M-parameter generative Transformer that brings this paradigm to market microstructure, learning directly from billions of …

• DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone

  Vaibhav Singh, Oleksiy Ostapenko, Pierre-Andr\'e No\"el, Eugene Belilovsky, Torsten Scholak · 2 March 2026

  Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive (AR) generation, yet their reliance on Transformer backbones limits inference efficiency due to quadratic attention or KV-cache overhead. We introduce DiffuMamba, a masked diffusion language model built on a b…

• FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA

  Haoran Zhang, Dongjun Kim, Seohyeon Cha, Haris Vikalo · 2 March 2026

  Federated LoRA provides a communication-efficient mechanism for fine-tuning large language models on decentralized data. In practice, however, a discrepancy between the factor-wise averaging used to preserve low rank and the mathematically correct aggregation of local updates can cause significant a…

• Mode Seeking meets Mean Seeking for Fast Long Video Generation

  Shengqu Cai, Weili Nie, Chao Liu, Julius Berner, Lvmin Zhang, Nanye Ma, Hansheng Chen, Maneesh Agrawala, Leonidas Guibas, Gordon Wetzstein, Arash Vahdat · 2 March 2026

  Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. To address this, we propose a training paradigm where Mode Seeking meets Mean Seeking, decoupling local…

• Who Guards the Guardians? The Challenges of Evaluating Identifiability of Learned Representations

  Shruti Joshi, Th\'eo Saulus, Wieland Brendel, Philippe Brouillard, Dhanya Sridhar, Patrik Reizinger · 2 March 2026

  Identifiability in representation learning is commonly evaluated using standard metrics (e.g., MCC, DCI, R^2) on synthetic benchmarks with known ground-truth factors. These metrics are assumed to reflect recovery up to the equivalence class guaranteed by identifiability theory. We show that this ass…

• Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstruction

  Chenhe Du, Xuanyu Tian, Qing Wu, Muyu Liu, Jingyi Yu, Hongjiang Wei, Yuyao Zhang · 27 February 2026

  Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors. However, we identify a critical flaw in prevailing PnP solvers (e.g., based on HQS or Proximal Gradient): they functio…

• Flow Matching is Adaptive to Manifold Structures

  Shivam Kumar, Yixin Wang, Lizhen Lin · 27 February 2026

  Flow matching has emerged as a simulation-free alternative to diffusion-based generative modeling, producing samples by solving an ODE whose time-dependent velocity field is learned along an interpolation between a simple source distribution (e.g., a standard normal) and a target data distribution. …

• ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation

  Ayush Roy, Wei-Yang Alex Lee, Rudrasis Chakraborty, Vishnu Suresh Lokhande · 27 February 2026

  In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compact datasets that preserve the knowledge of large-scale training sets while drastically reducing storage and computation. Recent advances in diffusion…

• Unsupervised Continual Learning for Amortized Bayesian Inference

  Aayush Mishra, \v{S}imon Kucharsk\'y, Paul-Christian B\"urkner · 27 February 2026

  Amortized Bayesian Inference (ABI) enables efficient posterior estimation using generative neural networks trained on simulated data, but often suffers from performance degradation under model misspecification. While self-consistency (SC) training on unlabeled empirical data can enhance network robu…

• Closing the gap on tabular data with Fourier and Implicit Categorical Features

  Marius Dragoi, Florin Gogianu, Elena Burceanu · 27 February 2026

  While Deep Learning has demonstrated impressive results in applications on various data types, it continues to lag behind tree-based methods when applied to tabular data, often referred to as the last "unconquered castle" for neural networks. We hypothesize that a significant advantage of tree-based…

• Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation

  Dian Xie, Shitong Shao, Lichen Bai, Zikai Zhou, Bojun Cheng, Shuo Yang, Jun Wu, Zeke Xie · 27 February 2026

  Classifier-free guidance (CFG) has helped diffusion models achieve great conditional generation in various fields. Recently, more diffusion guidance methods have emerged with improved generation quality and human preference. However, can these emerging diffusion guidance methods really achieve solid…

• Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA

  Hai Huang, Yann LeCun, Randall Balestriero · 27 February 2026

  Large Language Models (LLMs) obey consistent scaling laws -- empirical power-law fits that predict how loss decreases with compute, data, and parameters. While predictive, these laws are descriptive rather than prescriptive: they characterize typical training, not optimal training. Surprisingly few …

• BetterScene: 3D Scene Synthesis with Representation-Aligned Generative Model

  Yuci Han, Charles Toth, John E. Anderson, William J. Shuart, Alper Yilmaz · 27 February 2026

  We present BetterScene, an approach to enhance novel view synthesis (NVS) quality for diverse real-world scenes using extremely sparse, unconstrained photos. BetterScene leverages the production-ready Stable Video Diffusion (SVD) model pretrained on billions of frames as a strong backbone, aiming to…

• Entropy-Controlled Flow Matching

  Chika Maduabuchi · 27 February 2026

  Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives do not directly control the information geometry of the tra…

• Sharp Convergence Rates for Masked Diffusion Models

  Yuchen Liang, Zhiheng Tan, Ness Shroff, Yingbin Liang · 27 February 2026

  Discrete diffusion models have achieved strong empirical performance in text and other symbolic domains, with masked (absorbing-rate) variants emerging as competitive alternatives to autoregressive models. Among existing samplers, the Euler method remains the standard choice in many applications, an…

• Zero-Variance Gradients for Variational Autoencoders

  Zilei Shao, Anji Liu, Guy Van den Broeck · 27 February 2026

  Training deep generative models like Variational Autoencoders (VAEs) requires propagating gradients through stochastic latent variables, which introduces estimation variance that can slow convergence and degrade performance. In this paper, we explore an orthogonal direction, which we call Silent Gra…

• Calibrated Test-Time Guidance for Bayesian Inference

  Daniel Geyfman, Felix Draxler, Jan Groeneveld, Hyunsoo Lee, Theofanis Karaletsos, Stephan Mandt · 27 February 2026

  Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on maximizing reward rather than sampling from the true Bayesian posterior, leading to miscalibrated inference. In this work, we …

• Instruction-based Image Editing with Planning, Reasoning, and Generation

  Liya Ji, Chenyang Qi, Qifeng Chen · 27 February 2026

  Editing images via instruction provides a natural way to generate interactive content, but it is a big challenge due to the higher requirement of scene understanding and generation. Prior work utilizes a chain of large language models, object segmentation models, and editing models for this task. Ho…

• DrivePTS: A Progressive Learning Framework with Textual and Structural Enhancement for Driving Scene Generation

  Zhechao Wang, Yiming Zeng, Lufan Ma, Zeqing Fu, Chen Bai, Ziyao Lin, Cheng Lu · 27 February 2026

  Synthesis of diverse driving scenes serves as a crucial data augmentation technique for validating the robustness and generalizability of autonomous driving systems. Current methods aggregate high-definition (HD) maps and 3D bounding boxes as geometric conditions in diffusion models for conditional …