CoLLAs 2026 Keynote: Continual Model Merging via Subspace Modeling and Low-Rank Experts
apsarathchandar · x · 2026-09-16
In the first Day 3 keynote at CoLLAs 2026, Li Shen presented work on lifelong foundation models: merging sequentially arriving models for scalable knowledge reuse.
Techniques covered include subspace modeling, low-rank experts, and Pareto frontiers for merging trade-offs. A notable update from the continual learning research community.
More from Research
- CARLA veteran Ros shares synthetic data workflows to accelerate AV development — abursuc · 2026-09-16
- Grade AI like coworkers: open-source FrontierAgent framework ships with CLI TUI and fully local execution — aakashgupta · 2026-09-16
- CoLLAs 2026 talk: memorization may be unavoidable — curation, unlearning, pruning as strategies — gkdziugaite · 2026-09-16
- ETH Zürich robotic hand walks on its own fingers, no legs or wheels needed — lukas_m_ziegler · 2026-09-16
- Genome Biology opens collection on tumor microenvironment, welcomes AI and multi-omic methods — arjunrajlab · 2026-09-16
- Google Engineers' WikiSkill Turns Agent Execution History Into Validated, Reusable Skills — blaizedsouza · 2026-09-16