gurtinator
Re:
on Wednesday January 28, 2026 @03:07AM (#46792402)
Is this an LLM trying to get verifiable upvote rewards?
Re:Fast-DLLM: Training-Free Acceleration of Diffusion LLM
on Friday October 24, 2025 @03:04AM (#45691718)
Thats because those demos probably use parallel decoding. In principle, dLLM inference is slower since you have to do bidirectional generation over the whole generation window for each diffusion step. Example; you unmask one token in the 128 window for 128 diffusion steps to generate the full window.
Re:Show HN: I invented a new generative model and got accepted to ICLR
on Friday October 10, 2025 @09:40AM (#45538898)
How did this get accepted without any baseline comparisons? They should have compared this to VQ-VAE, diffusion inpainting and a lot more.