Cohere Labs: discrete diffusion gives lossless LLM inference speedup
Cohere_Labs · x · 2026-10-09
Cohere Labs shares researcher Sumanth Sahoo's talk on discrete diffusion: a proven, lossless speedup for language model inference that outperforms even the fastest autoregressive models. Full recording available.
More from Research
- Jensen Huang's foundation donates ~7M hours of compute to UW Institute for Protein Design — XFreeze · 2026-10-09
- Turing Institute unveils AI model for autonomous space domain awareness — turinginst · 2026-10-09
- Stanford CS336 posts 18 free lectures building LLMs from scratch, Triton to RLHF — techNmak · 2026-10-09
- evilsocket: prompt injection detection benchmarks built on mislabeled data — evilsocket · 2026-10-09
- Neural Radiance Caching variant speeds up specular lighting in real-time path tracing — ssh4net · 2026-10-09
- ABC releases open stack for scalable behavior cloning with real and sim teleoperation data — rsasaki0109 · 2026-10-09