11 stories tagged Diffusion Models
Hugging Face has integrated Nunchaku 4-bit Diffusion into its Diffusers library, enabling high-quality AI image generation on consumer hardware. The open-source tool uses 4-bit quantization to dramatically reduce memory and compute requirements, making diffusion models accessible to users without expensive GPUs.
Researchers are exploring a new approach to AI-generated radiology reports using a diffusion technique. The model, DiffusionGemma-26B, gradually refines text on a 'canvas' rather than writing left-to-right. Initial benchmarks on medical visual question answering tasks show it is competitive with traditional autoregressive models of the same size.
Researchers found that placing questions in the right spot within AI prompts can significantly improve answers. This discovery is especially important for newer AI models that process information differently than older ones.
Researchers have analyzed how Diffusion Language Models (DLMs) differ from traditional AI models. DLMs generate text by gradually refining entire sequences, potentially offering new advantages over current methods.
Researchers introduced DiBS, a new AI method that merges diffusion models with traditional logic to solve Sudoku more efficiently. This hybrid approach aims to overcome the limitations of pure learning-based or symbolic solvers.
Scientists found that diffusion language models can recall training data better than previously believed. This discovery highlights potential privacy risks for AI systems.
NVIDIA has introduced Nemotron-Labs, a new type of AI model that generates text at near light-speed. This could revolutionize how we interact with AI assistants and tools. The models are open-source, making them accessible to everyone.
Researchers introduced FlowLM, a new AI model that simplifies text generation using a novel technique. It transforms existing diffusion models into more efficient flow models, reducing the steps needed for high-quality text generation.
Researchers have developed a new approach to AI text generation that combines the speed of diffusion models with the quality of traditional methods. This could lead to faster, more diverse AI writing tools in the future.
A new study reveals a vulnerability in diffusion-based language models (dLLMs) that allows attackers to override safety mechanisms. The exploit achieves a 76.1% attack success rate on HarmBench, challenging assumptions about model alignment.
Researchers introduce AGD-MBRL, a new method that uses advantage estimates to guide diffusion models in reinforcement learning, reducing compounding errors. This approach outperforms traditional policy-only and reward-based guides.