Anpei Chen@AnpeiC
Too many artifacts for GS reconstruction? Please checkout GenFusion: Closing the Loop between Reconstruction and Generation via Videos
🌐 Project page:
💻 Code:
#3D #DiffusionModels #ViewSynthesis #GenFusion #CVPR2025
33719214.7K
Posts with #diffusionmodels
#diffusionmodels
Public posts on X that use #diffusionmodels.
Related hashtags
A team of researchers has introduced Animate Anyone, a new diffusion models-based solution for consistent and controllable image-to-video synthesis for character animation. More examples here: #diffusion #diffusionmodels #ai #research #tech #technology8149117.5K
💥 New paper: Think Before You Diffuse Meet DiffPhy — LLM-guided, physics-aware video diffusion 🎥🧠🌍 SOTA on real-world motion & dynamics! 🔗 @JHUCompSci @HopkinsDSAI @HopkinsEngineer @myq_1997 #DiffusionModels #VideoGeneration2231208.4K
David@LiDavid2002🚀 Today, @iNikitaGushchin and I will be presenting our work on IDLM as part of the dLLM Reading Group! We’ll discuss the main ideas behind the paper, what motivated this direction, and why we believe it is an exciting step for diffusion-based language modeling.
1391.6K- David@LiDavid2002@LiDavid2002I also shared a brief overview of the core idea in my Telegram channel for anyone curious, you can check it out here: We’ll be happy to see everyone interested in diffusion LMs, generative modeling, or just curious about where this field is heading.100107
- David@LiDavid2002@LiDavid2002📄 Paper: 💻 Code: 📢 Invitation post: Many thanks to the organizers for the invitation, @jdeschena, @ssahoo_, @zhihanyang_! 🙌 #ICML2026 #DiffusionModels #LanguageModels #GenerativeAI #MachineLearningDiscrete Diffusion Reading Group @diffusion_llms📢 May 18 (Mon): IDLM: Inverse-distilled Diffusion Language Models 🤔Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. 💡To address this, the authors extend Inverse Distillation, a technique originally developed to accelerate continuous diffusion models, to the discrete setting. However, this extension introduces both theoretical and practical challenges. 🔧To overcome these challenges, the authors first provide a theoretical result demonstrating that their inverse formulation admits a unique solution, thereby ensuring valid optimization. They then introduce gradient-stable relaxations to support effective training. 📊As a result, experiments on multiple DLMs show that their method, Inverse-distilled Diffusion Language Models (IDLM), reduces the number of inference steps by 4×—64×, while preserving the teacher model’s entropy and generative perplexity. This Monday, David Li ( and Nikita Gushchin ( will present their jointly led paper, which was recently accepted at ICML 2026. Collaborators of this work include: Dmitry Abulkhanov (@dabulkhanov_), Eric Moulines ( Ivan Oseledets (@oseledetsivan), Maxim Panov (@maxim_panov), Alexander Korotin ( Paper link:0110472
📢 May 18 (Mon): IDLM: Inverse-distilled Diffusion Language Models 🤔Diffusion Language Models (DLMs) have recently achieved strong results in text generation. However, their multi-step sampling leads to slow inference, limiting practical use. 💡To address this, the authors extend Inverse Distillation, a technique originally developed to accelerate continuous diffusion models, to the discrete setting. However, this extension introduces both theoretical and practical challenges. 🔧To overcome these challenges, the authors first provide a theoretical result demonstrating that their inverse formulation admits a unique solution, thereby ensuring valid optimization. They then introduce gradient-stable relaxations to support effective training. 📊As a result, experiments on multiple DLMs show that their method, Inverse-distilled Diffusion Language Models (IDLM), reduces the number of inference steps by 4×—64×, while preserving the teacher model’s entropy and generative perplexity. This Monday, David Li ( and Nikita Gushchin ( will present their jointly led paper, which was recently accepted at ICML 2026. Collaborators of this work include: Dmitry Abulkhanov (@dabulkhanov_), Eric Moulines ( Ivan Oseledets (@oseledetsivan), Maxim Panov (@maxim_panov), Alexander Korotin ( Paper link:
214369.9K
Wujia@whb_zjuDiffusion Models: 10 Detailed Takeaways for Application 1. "DDPM's core is just the start! To truly master diffusion models, you NEED to grasp DDIM's speed, SDE/ODE's flexibility. These shape modern architectures. Dive deep! #DiffusionModels #AIML #deeplearning201115
Ye Zhu@szyezhuExcited to share our NeurIPS 2025 paper Dynamic Diffusion Schrödinger Bridge in Astrophysical Observational Inversions! #neurips2025 #DiffusionModels #AstroML In this work, we introduce Astro-DSB, a novel diffusion bridge-based approach designed to tackle astrophysical inversion problems in the context of Giant Molecular Clouds (GMCs) for star formation. Our goal is to infer underlying physical states (e.g., density and magnetic fields) from projected, partial observations. We train Astro-DSB on both simulated density and magnetic field data, and test its in-distribution (ID) and out-of-distribution (OOD) performance on new simulations, as well as real observational data from Taurus B213. We show that Astro-DSB achieves substantially better OOD generalization than both traditional astrostatistical methods and state-of-the-art conditional diffusion models. It also reduces the required training time by 75% compared to cDDPMs. Paper and code are available! Check out at and
67747.4K
👋ML Applied Researcher needed! Join M-XR in London to: - Work with diffusion & image models - Refine CLIP, SAM & DINO - Transform photography into accurate PBR materials Link bellow 👇 #MachineLearning #DiffusionModels #3D #JobOpportunity18403.2K
Monte Carlo Seminar@OnlineMCSeminarJoin our next Monte Carlo seminar (Tue, Jan 20, 2026)! Speaker: Jiequn Han (Flatiron Institute) Talk: “DriftLite: Lightweight drift control for inference-time scaling of diffusion models” Time: 8:30am PT / 11:30am ET / 4:30pm London / 5:30pm Paris #DiffusionModels #MonteCarlo
03203.2K
🎉 Thrilled to share our latest work on solving inverse problems via diffusion-based priors — without heuristic approximations of the measurement matching score! 📄 Link: (1/6) #DiffusionModels #InverseProblems #Guidance #SequentialMonteCarlo
Lexing Ying @lexing_ying52216132.1K
Wei Huang@WeiHuang_USTCExcited to share our new work: “Scaling Diffusion Transformers Efficiently via μP” Grateful for the amazing co-authors! 📄 Paper: 💻 Code: #DiffusionModels #Transformers #muP #AIresearch #scaling #MachineLearning #GenerativeAI112288
Alejandro Pardo@PardoAlejo🚀 Our MatchDiffusion was accepted to ICCV 2025 in Hawaii! 🌺 We generate two synchronized videos from text prompts—designed for match-cuts. Results: Paper: #MatchDiffusion #ICCV2025 #DiffusionModels #TextToVideo #GenerativeAI35374.3K
Noah Ladner | AI & IT News Expert@AILadner🚨 #DiffusionModels Explained in 20 Seconds!🤯 > Makes images from noise > Powers tools like @StableDiffusion > Revolutionizes #AIart #ArtificialIntelligence #MachineLearning #Innovation cc: @Analytics_699 @Farooq_AI @CsharpCorner @khalide_f1 @ricardo_ik_ahau @AIEnthusiastIM048163
Pedram Ghamisi@GhamisiPedram[New Paper] For those interested in diffusion models, their theory, and their applications in Earth observation! Paper: Journal: IEEE TGRS @IEEE_GRSS #remotesensing #diffusionmodels #earthobservation #AI4EO #deepgenerative #imageprocessing
16346K
Utkarsha@UtkarshaNerleHow does AI turn pure static into a photo? 🌫️➡️🖼️ Diffusion models: 1⃣ Add noise to real data until only static is left 2⃣ Train a U-Net to predict that noise 3⃣ Start from noise, denoise step by step → new image #GenAI #DiffusionModels00123
#DiffusionModels Big thanks to @OPatashnik for the insightful guest lecture in our diffusion models course on using attention layers in diffusion networks for image manipulation. Don’t miss the recording! 🎥:011554.9K
Yizhe Zhang@YizheZhangNLPExcited to introduce our 7B Coding Diffusion LLM, DiffuCoder — advancing open-source diffusion models for high-quality code generation! Diffusion offers powerful global planning via iterative generation, and code is the perfect testbed to push its limits! #DiffusionModelsSansa Gong @sansa19739319🤖Can diffusion models write code competitively? Excited to share our latest 7B coding diffusion LLM!!💻 With DiffuCoder, we explore how they decode, why temperature🔥 matters, and how to improve them via coupled-GRPO that speaks diffusion!!📈 Code: 🧵211675.4K
🤖Can diffusion models write code competitively? Excited to share our latest 7B coding diffusion LLM!!💻 With DiffuCoder, we explore how they decode, why temperature🔥 matters, and how to improve them via coupled-GRPO that speaks diffusion!!📈 Code: 🧵
511256949.6K
Hackster.io@HacksterioRunning generative AI usually requires massive compute. So how do you build an offline AI art generator using hardware you already have? #HardwareEngineering #RaspberryPi #DiffusionModels #EdgeAI #Hackster13274.2K
How can we speed up #DiffusionModels and find better model families? To this end, let's talk about "A Complete Recipe for Diffusion Generative Models" (#ICCV Oral). To this end, let's focus on the stochastic process that converts data to random noise (1/7). @kpandey008378318.4K- Show more posts
