Awesome Training & Sampling

Key papers

• InterleaveThinker: Reinforcing Agentic Interleaved Generation (2026)
  Dian Zheng et al.
  14.38
• tempoGAN: A Temporally Coherent, Volumetric GAN for Super-resolution Fluid Flow (2018)
  You Xie et al.
  10.12
• Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection (2025)
  Shufan Li et al.
  9.29
• Qwen-Image-Flash: Beyond Objective Design (2026)
  Tianhe Wu et al.
  8.85
• Learning Few-Step Diffusion Models by Trajectory Distribution Matching (2025)
  Yihong Luo et al.
  8.84
• Invertible generative models for inverse problems: mitigating representation error and dataset bias (2019)
  Muhammad Asim et al.
  8.66
• Contrastive Flow Matching (2025)
  George Stoica et al.
  8.23
• Generative Modeling via Drifting (2026)
  Mingyang Deng et al.
  7.47
• CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer (2024)
  Zhuoyi Yang et al.
  7.30
• Deeply Supervised Flow-Based Generative Models (2025)
  Inkyu Shin et al.
  7.24
• Avatar V: Scaling Video-Reference Avatar Video Generation (2026)
  Benjamin Liang et al.
  6.97
• Bolt3D: Generating 3D Scenes in Seconds (2025)
  Stanislaw Szymanowicz and Jason Y. Zhang and Pratul Srinivasan and Ruiqi Gao and Arthur Brussee and Aleksander Holynski and Ricardo Martin-Brualla and Jonathan T. Barron and Philipp Henzler
  6.92
• On the Challenges and Opportunities in Generative AI (2024)
  Laura Manduchi et al.
  6.89
• Glance: Accelerating Diffusion Models with 1 Sample (2025)
  Zhuobai Dong et al.
  6.89
• Arbitrary-steps Image Super-resolution via Diffusion Inversion (2024)
  Zongsheng Yue et al.
  6.61
• Automated Tuning for Diffusion Inverse Problem Solvers without Generative Prior Retraining (2025)
  Ya\c{s}ar Utku Al\c{c}alar et al.
  5.98
• Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling (2025)
  Haochen You et al.
  5.93
• Fast-DDPM: Fast Denoising Diffusion Probabilistic Models for Medical Image-to-Image Generation (2024)
  Hongxu Jiang et al.
  5.40
• Recursively Trained Diffusion Models: Limiting Collapse Distribution and Spectral Characterization (2026)
  Na\"il B. Khelifa et al.
  5.01
• Adaptive Nucleus Truncation for Long-Form Reasoning (2026)
  Ousmane Amadou Dia
  5.01
• GenDR: Lighten Generative Detail Restoration (2025)
  Yan Wang et al.
  4.87
• The GAN is dead; long live the GAN! A Modern GAN Baseline (2025)
  Yiwen Huang et al.
  4.76
• Learning Diffusion Priors from Observations by Expectation Maximization (2024)
  Fran\c{c}ois Rozet et al.
  4.74
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think (2024)
  Sihyun Yu et al.
  4.60
• Nepotistically Trained Generative-AI Models Collapse (2023)
  Matyas Bohacek and Hany Farid
  4.40
• Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal (2026)
  Leon Bergen et al.
  4.39
• When Sample Selection Bias Precipitates Model Collapse (2026)
  Xinbao Qiao et al.
  4.39
• Compressing Image Style Training into a Single Model Forward (2026)
  Zhongjie Duan et al.
  4.39
• Mask, Sample, Revise: A Revisable CTMC Inference Stack for Guided Discrete Flow Matching Text-to-Speech (2026)
  Alef Iury Siqueira Ferreira et al.
  4.39
• Implicit Variational Rejection Sampling (2026)
  Jian Xu et al.
  4.39
• Neither Parallel Nor Sequential: How DiffusionGemma Actually Commits Tokens (2026)
  Ali Asaria et al.
  4.39
• Generative Models and Statistical Validation (2026)
  Sascha Diefenbacher et al.
  4.33
• Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching (2026)
  Shengyu Feng et al.
  4.33
• SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization (2025)
  Th\'eophane Vallaeys et al.
  4.28
• Diffusion Models Are Real-Time Game Engines (2024)
  Dani Valevski et al.
  3.97
• Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation (2025)
  Anshuk Uppal et al.
  3.92
• Conditional Variational Diffusion Models (2023)
  Gabriel della Maggiora et al.
  3.91
• Mean Flows for One-step Generative Modeling (2025)
  Zhengyang Geng et al.
  3.81
• DP-LDMs: Differentially Private Latent Diffusion Models (2023)
  Michael F. Liu et al.
  3.71
• It\^o maps for any-step SDEs (2026)
  Zhengkai Pan et al.
  3.51
• MP3: Multi-Period Pattern Pre-training for Spatio-Temporal Forecasting (2026)
  Lilan Peng et al.
  3.51
• Pix2Pix-Hybrid: Structure-Guided Conditional Synthesis of Hajj Crowd Images with Multi-Channel Conditioning and Weak Attribute Supervision (2026)
  Amirah F. Alshammari et al.
  3.51
• Point Cloud Upsampling through Patch-based Frequency Superposition (2026)
  Marina Ritthaler et al.
  3.51
• HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities (2026)
  Yijun Liu et al.
  3.51
• Instruct-Particulate: Scaling Feed-Forward 3D Object Articulation with Kinematic Control (2026)
  Ruining Li et al.
  3.51
• D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models (2026)
  Dengyang Jiang et al.
  3.45
• Paris 2.0: A Decentralized Diffusion Model for Video Generation (2026)
  Ali Rouzbayani et al.
  3.45
• One Step Diffusion via Shortcut Models (2024)
  Kevin Frans et al.
  3.42
• Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control (2024)
  Carles Domingo-Enrich et al.
  3.36
• Conditional Image Synthesis with Diffusion Models: A Survey (2024)
  Zheyuan Zhan et al.
  3.36
• Stop Training for the Worst: Progressive Unmasking Accelerates Masked Diffusion Training (2026)
  Jaeyeon Kim et al.
  3.28
• Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling (2026)
  Yiran Guo et al.
  3.28
• RAD: Region-Aware Diffusion Models for Image Inpainting (2024)
  Sora Kim et al.
  3.26
• DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised $h$-transform (2024)
  Alexander Denker et al.
  3.20
• Improving Diversity In Black-box Few-shot Knowledge Distillation (2026)
  Tri-Nhan Vo, Dang Nguyen, Kien Do, et al.
  3.20
• Generation of non-stationary stochastic fields using Generative Adversarial Networks (2022)
  Alhasan Abdellatif et al.
  3.19
• Home-made Diffusion Model from Scratch to Hatch (2025)
  Shih-Ying Yeh
  3.17
• Conditioning diffusion models by explicit forward-backward bridging (2024)
  Adrien Corenflos et al.
  3.14
• Bridging GANs and Bayesian Neural Networks via Partial Stochasticity (2025)
  Maurizio Filippone and Marius P. Linhard
  2.99
• Diffusion models for multivariate subsurface generation and efficient probabilistic inversion (2025)
  Roberto Miele et al.
  2.99