AI & ML
Measured Coupling for Parallel Decoding in Diffusion Language Models
arXiv cs.DC0 views
arXiv:2611.08307v1 Announce Type: cross Abstract: Diffusion language models can write many tokens per step, but must choose which tokens are safe to commit together. Mean-field decoding penalizes pairs of positions whose predictions look alike. We replace this proxy with the coupling itself: how much committing one token changes the model's confidence at another. Cheap probes inside the main forward pass measure it, with no training or extra model, and it plugs into the same mean-field rule. On three models and four benchmarks, our method needs far fewer steps than mean-field decoding and is faster in most settings, also with a key-value cache, at an average accuracy cost of 1.1 points. Shuffling the couplings or replacing them with a uniform bonus loses this gain.
Source：https://arxiv.org/abs/2611.08307PreviousGINGER: Spicing Up Graph-Based Vector SearchNextStrataFlux: Memory-Hierarchy-Native Low-Bit LLM Inference
Related posts
I’ve reviewed almost every Android foldable this year — here’s how the iPhone Duo compares
0The Verge
Physicl raises $10M to make the digital world real enough for robots
0TechCrunch
Kubernetes, mark II? Why Google’s giving away gVisor, a code sandbox used by Anthropic and OpenAI
0The New Stack
AI helps find better recipes for 3D-printing titanium parts
0Phys.org Tech
Newly-developed paint could keep your home cooler and lower energy bills
0Phys.org Tech
Warhammer 40,000: Dawn of War 4 creative director explains how core 40K tabletop features like ‘Armor of Contempt’ were adapted to the RTS — ‘It’s not the same mechanic, but it does kind of the same t
0TechRadar