COLM 2026 poster: Weightless Fine-tuning personalizes LLMs for millions of users without SFT
TuhinChakr · x · 2026-10-09
A COLM 2026 poster, Weightless Fine-tuning for Personalizing LLMs without actual Fine-tuning, tackles SFT's scaling problem: per-user optimization, separate LoRA weights, and retraining become prohibitively expensive at millions of users.
The team previously showed per-author SFT can emulate award-winning authors' styles; this work aims to personalize without any weight updates. Details live in the poster.
More from Research
- Exa launches ATLAS benchmark: even priciest search agents miss ~1/3 of results — yoimnotkesku · 2026-10-09
- PPTBench: a new benchmark testing if coding agents can rebuild visuals into editable slides — jiqizhixin · 2026-10-09
- TIDE attributes diffusion outputs to training images in milliseconds — serrjoa · 2026-10-09
- DeepScholar-Bench at COLM 2026: benchmarking AI-generated research synthesis — mrdrozdov · 2026-10-09
- Frontier AI models beat human experts at earnings predictions for the first time — maithra_raghu · 2026-10-09
- Cell paper reconstructs cell fate map of the mouse embryo — anshulkundaje · 2026-10-09