Research
New research from Google DeepMind. (bookmark it) SkillSmith treats model weights as an additional modality the LLM reads natively. The augme…
New research from Google DeepMind. (bookmark it) SkillSmith treats model weights as an additional modality the LLM reads natively. The augmented model ingests existing prefix weights alongside rich te
New research from Google DeepMind. (bookmark it) SkillSmith treats model weights as an additional modality the LLM reads natively. The augmented model ingests existing prefix weights alongside rich text describing how a capability relates to a target, then directly outputs new prefix weights that manifest that skill. Skill composition becomes an inference-time operation instead of a training run. The team calls this instruction-steered parametric synthesis. The gains exceed what text-only and weight-only adaptation reach on their own. Paper: https://arxiv.org/abs/2607.27497 Track more trending AI papers in our academy: https://academy.dair.ai/
Related
- What if a model became the computer itself?
- A nice paper worth checking out. (bookmark it) For a long time, we have had machines that work astonishingly well before we had a real theor…
- Understanding Layer Patching in Model Size Interpolation
Source: DAIR.AI (X) | 2026-08-02