DeepMind's SkillSmith Treats Model Weights as a Modality for Inference-Time Skill Composition
omarsar0 · x · 2026-08-03
Google DeepMind introduced SkillSmith, a novel approach that treats model weights as an additional modality natively read by LLMs.
The augmented model ingests text describing how a capability relates to a target and directly outputs new prefix weights manifesting that skill. This transforms skill composition from a training run into an inference-time operation, which the team calls "instruction-steered parametric synthesis."
Experiments show that combining text and weight adaptation yields gains exceeding what text-only or weight-only methods can achieve independently.
More from Research
- OpenAI Paper Explores 8 Agentic AI Applications in Scientific Computing — markjeffrey · 2026-08-03
- Developer Reproduces Reward Hacking in GRPO Training Without KL Penalty — malliktwts · 2026-08-03
- RL Training Failure: How Format Rewards Destroy Qwen's Reasoning — malliktwts · 2026-08-03
- Meta Open-Sources SAM 3D Body for Robust 3D Human Mesh Recovery from Single Images — tom_doerr · 2026-08-03
- Study: AI Systems Out-Persuade Expert Humans and World Debate Champions — geoffreyirving · 2026-08-03
- Top Information Retrieval Papers: Meta, YouTube, Tencent Explore RAG and Generative Recommendation — _reachsumit · 2026-08-03