COLM 2026 workshop NonAR-LM to spotlight diffusion and non-autoregressive LLMs
LucaAmb · x · 2026-10-10
The official COLM 2026 workshop 'NonAR-LM: Non-Autoregressive Language Models for Fast & Flexible Text Generation' takes place Oct 9, 2026 at Hilton San Francisco Union Square. Topics span masked/uniform-state diffusion, discrete flow matching, and any-order autoregression. Submissions due Jun 30, 2026 via OpenReview (non-archival); first invited talk by Shansan Gong (HKU) on flexible generation order in diffusion LMs.
More from Research
- Researcher speculates new model uses continuous diffusion with latent-thinking loops in its architecture — mblondel_ml · 2026-10-10
- FIND preprint: robot picks its own weaknesses, lifts 8-task success from 55% to 71.9% — GeorgiaChal · 2026-10-10
- Tao blog essay on LLMs lands amid OpenAI Navier-Stokes announcement and misconduct claims — gleech · 2026-10-10
- LeCun's AMI debuts H-JEPA: hierarchical world model hits 73% in maze planning — 量子位 · 2026-10-10
- 100 coding-agent runs show a shared knowledge layer lifts pass rate from 10% to 60% — BadPuzzleheaded5764 · 2026-10-10
- Indie dev open-sources Vega: an 800M-param physics-based decision model with a ball-rolling inference engine — Nandakishor_ml · 2026-10-10