Thousands of people believe chatbots like ChatGPT are conscious, yet no one attributes the same to image generators like Midjourney, despite similar underlying technology. This dichotomy highlights a …
ByteDance and Renmin University researchers released iLLaDA, an 8B diffusion language model that matches Qwen2.5 on base benchmarks but lags after fine-tuning. The model, trained from scratch on 12 tr…
Diffusion Language Models (dLLMs) offer a faster alternative to autoregressive LLMs by generating multiple tokens in parallel, but face consistency challenges. Recent innovations like DFlash, Diffusio…
Researchers introduced Reflective Masking (RM), a post-training method that enables Mask Diffusion Models to iteratively revise their own outputs by re-masking uncertain tokens and remembering previou…
Inception Labs' Mercury 2 diffusion language model outperforms Google DeepMind's DiffusionGemma on reasoning benchmarks while achieving parallel text generation speeds of over 1,000 tokens per second.…
Google DeepMind researchers audited DiffusionGemma, a text diffusion model, and found it is not significantly less transparent than Gemma in terms of variable interpretability, but algorithmic transpa…
Researchers at Google DeepMind instrumented DiffusionGemma 26B, a masked discrete-diffusion mixture-of-experts model, and found its decoding is neither parallel nor sequential but follows a partial le…
Google DeepMind released DiffusionGemma on June 10, 2026, a 26B open-weight text diffusion model that generates 256 tokens simultaneously, achieving up to 1,008 tokens per second on an H100—4-5x faste…
The US government barred foreign users from accessing Anthropic's Fable 5 and Mythos 5 models, including Anthropic's own foreign-national employees. Meanwhile, Moonshot AI released the open-weights co…
Google has unveiled DiffusionGemma, an experimental open model that generates text up to 4x faster than traditional auto-regressive models by processing entire blocks of text simultaneously using diff…
Google DeepMind released DiffusionGemma, an open-source Apache 2.0-licensed diffusion-based large language model that generates text at over 1,000 tokens per second on a single H100 GPU, achieving up …
Google's DiffusionGemma, an experimental open model using discrete diffusion for text generation, offers a parallel approach that can outperform token-by-token LLMs in throughput-sensitive workloads. …
DeepMind released DiffusionGemma, a new large language model that uses discrete diffusion to generate entire sequences in parallel instead of autoregressive token-by-token generation. The model achiev…
A developer achieved 775 tokens per second running the full BF16 DiffusionGemma model on an Nvidia RTX 6000 Pro using a Red Hat fork of vLLM, demonstrating extremely fast local AI inference at short c…
Google has released DiffusionGemma, an experimental text-generation model built on the Gemma 4 architecture that generates text in parallel blocks rather than token-by-token, enabling faster inference…
Anthropic launched Claude Fable 5, its first publicly available Mythos-class model, on June 9, 2026, triggering controversies over a mandatory 30-day data retention policy that overrides enterprise ze…
Google released DiffusionGemma, a new open-weight AI model under the Apache 2 license, available on Hugging Face. NVIDIA is hosting the model for free on its NIM cloud API, where it generated 2,409 to…
Google DeepMind released DiffusionGemma, a new AI model that generates text in parallel blocks rather than sequentially, achieving up to 700 tokens per second on an RTX 5090 GPU and over 1,000 tokens …
Google released DiffusionGemma, a 26-billion-parameter open model that generates text through a diffusion process rather than token-by-token, achieving roughly 1,000 tokens per second on a single Nvid…
Google AI and Google DeepMind researchers released DiffusionGemma, an experimental 26-billion-parameter Mixture of Experts open model that uses text diffusion to generate entire blocks of text simulta…