Decentralized Diffusion Models power stronger models trained on more... accessible infrastructure. DDMs mitigate the networking bottleneck that locks training into expensive and power-hungry centralized clusters. They scale gracefully to billions of parameters and generate photorealistic images with just a week of training on eight independent GPU nodes. They’re easy to implement, adopt DiT hyperparameters directly and outperform standard models FLOP-for-FLOP.show more

We’re not just training models anymore. We’re deploying intelligence... at scale. On the latest episode of Advanced Insights, AMD CTO MarkPapermaster sits down with Oracle's Chris Gandolfo to talk AI, infrastructure, and what it really takes to train and deploy LLMs at scale.show more

Watch the Echo-trained 30B Sokoban model outperform models many... times its size, including DeepSeek-R1 and GPT-OSS-120B. Instead of larger datacenters or more expensive GPU fleets, Echo scales reinforcement learning with consumer hardware found everywhere.show more

Switti -- a new scale-wise transformer for text-to-image generation... 🦾 🔥 Improved generation of fine-grained details. Outperforms existing T2I AR models and competes with state-of-the-art T2I diffusion models while being up to 7x faster.show more

Photorealistic Object Insertion with Diffusion-Guided Inverse Rendering discuss: The... correct insertion of virtual objects in images of real-world scenes requires a deep understanding of the scene's lighting, geometry and materials, as well as the image formation process. While recent large-scale diffusion models have shown strong generative and inpainting capabilities, we find that current models do not sufficiently "understand" the scene shown in a single picture to generate consistent lighting effects (shadows, bright reflections, etc.) while preserving the identity and details of the composited object. We propose using a personalized large diffusion model as guidance to a physically based inverse rendering process. Our method recovers scene lighting and tone-mapping parameters, allowing the photorealistic composition of arbitrary virtual objects in single frames or videos of indoor or outdoor scenes. Our physically based pipeline further enables automatic materials and tone-mapping refinement.show more

Diffusion Transformers aren't just generative models, but also powerful... multi-modal encoders. ConceptAttention creates rich heatmaps of text concepts in images from DiT representations. This even works on real images, and can be applied to tasks like segmentation! Demo 👇show more

First look at SPARTA, a distributed AI training algorithm... that avoids synchronization by randomly exchanging sparse sets of parameters ( 1,000x reduction in inter-GPU communication, enabling training of large models over slow bandwidths without specialized infrastructure. SPARTA works on its own but can also be combined with sync-based low communication training algorithms like DiLoCo for even better performance.show more

Use Your Private Models on Comfy Cloud! Continue client... work safely — or generate with your experimental private models. You can now import models directly from private Hugging Face or Civitai repos. Just add your private key and model URL, and we will bring the models to your workflow! Everything you import stays 100% private to your account.show more

LayerAI Compute: Decentralized GPU Power for AI 🧬 LayerAI... is stepping into the physical AI infrastructure game with our latest: DePin for AI Computing. This move tackles a key AI/ML market gap: instant, on-demand compute power, available worldwide with just a few clicks. We're not just decentralizing data with AI2Earn; we're now also decentralizing the compute, making the AI ecosystem stronger and more resilient. The first iteration of this product will go live in the 2nd week of February.show more

🔥Nexera & Aethir: Unleashing AI’s Next Frontier Through Tokenized... GPU Power 🤝 Nexera is proud to join forces with Aethir in a strategic partnership to make cutting-edge AI infrastructure globally accessible. By tokenizing fractional GPU ownership, we’re enabling developers, enterprises, and investors everywhere to harness the explosive growth of deep learning and generative AI without being limited by geography, scale, or cost. With transparent tokenization, innovators can access powerful GPUs for faster model training and more advanced applications. GPU providers gain streamlined funding for expansion and upgrades, and investors tap into a high-growth market with secure, compliant opportunities that can provide higher yields than other RWA products. It’s an entirely new ecosystem where everyone can thrive, fueling AI’s evolution at an unprecedented pace. By 2030, the global GPU market is projected to exceed hundreds of billions of dollars, driven by the explosive demand for AI-powered applications, deep learning, and increasingly sophisticated generative models, ensuring that tokenizing these invaluable resources is poised to tap into a massive, rapidly expanding opportunity. $NXRAshow more

🚨New paper! Generative models are often “miscalibrated”. We calibrate... diffusion models, LLMs, and more to meet desired distributional properties. E.g. we finetune protein models to better match the diversity of natural proteins.show more

2. Machine Learning with Python Topics: • ML problem... principles • Implement & analyze models • Choosing suitable models for different apps • ML project implementation: Training, validation, tuning, and feature engineering 🔗show more

Colossus 2. 1 gigawatt. Built in 122 days. Let... that sit. Seven models training at once. Not queued. Not waiting. Parallel. Up to 10 trillion parameters. Real scale, not slides. Others still stitching clusters across cloud partners. xAI just built the whole thing. xAIshow more

Want to generate images from the world's best models... like Nano Banana or GPT Image side by side? Now you can with Image Lab 🚀 Run a single prompt across up to 25 models, with up to 20 images from each, and see results in seconds. You've seen our leaderboards. Now generate and evaluate the models yourself. Link in thread 🧵👇show more

NVIDIA's CUDA Moat is becoming a Copper Moat with... scale-up networking. Bigger models demand more from the scale-up network, and we❤️ Coppershow more

1/ Happy to share VADER: Video Diffusion Alignment via... Reward Gradients. We adapt foundational video diffusion models using pre-trained reward models to generate high-quality, aligned videos for various end-applications. Below we generated a short movie using VADER 😀, we used ChatGPT to write a script and an off-the-shelf AI music generator to generate the sound. Our code & weights are open-sourced:show more

Diffusion models have amazing image creation abilities. But how... well does their generative knowledge transfer to discriminative tasks? We present Diffusion Classifier: strong classification results with pretrained conditional diffusion models, *with no additional training*! 1/9show more

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models... "Block diffusion sequentially generates blocks of tokens by performing diffusion within each block and conditioning on previous blocks. By combining strength from autoregressive and diffusion models, block diffusion overcomes the limitations of both approaches by supporting variable-length, higher-quality generation and improving inference efficiency with KV caching and parallel sampling."show more

POWER IS PLANE-SPECIFIC! In other words, you’re going to... develop much more sport-specific POWER by training in planes closely related to your sport. Baseball is a sport that relies heavily on being powerful, and efficient in the frontal and transverse plane. With that being said, a lot of our training focuses on developing power in these planes.show more

starting the week with a true groundbreaking work 💥... Large Language Diffusion Models the first billion-parameter scale diffusion model competitive with its pairs (8B model comparable to LLaMA 3 8B) it gets rid of the michael scott syndrome on existing LLMsshow more