AURORA-LM: A Continuous-Latent Diffusion Language Model
liuziwei7 · x · 2026-08-09
AURORA-LM is a novel continuous-latent diffusion language model. It directly learns text distributions using a block-causal diffusion transformer while preserving a high-capacity, decodable text latent representation, offering a new direction for language model architectures.
More from Research
- Netflix details its production LLM judge: hundreds of thousands of recommendations scored weekly — omarsar0 · 2026-08-24
- Nature Comment: Provenance, not interpretability, grounds trust in autonomous science — gabepgomes · 2026-08-24
- New Architecture RHEA: Train 1B Model on 8GB VRAM — zemondza · 2026-08-24
- Trained two 16M-param models to do generative CAD with real physics — debreuil · 2026-08-24
- Claude model helps discover complex structure on S^6, solving 60-year-old math problem — Singularitarian · 2026-08-24
- Study: Agents read instructions/notes 60.5% of the time, rarely touch API docs — dair_ai · 2026-08-24