Research map / Vision-language and multimodal / Robot action and navigation
PRISM: Primitive Routing via In-context Skill Mixing for Lifelong VLA
Jiachen Tao, Gengyu Zhang, Haoxuan Wang, Bing Liu, Yan Yan
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes PRISM, a lifelong VLA approach that routes among primitive skills via in-context skill mixing to retain skills and compose long-horizon tasks; only the abstract was available, so details are limited.
Problem
Vision-language-action policies must retain previously learned manipulation skills and reuse them within long-horizon composite tasks whose behavior changes across phases; the standard shared-update recipe absorbs every new task into one update, offering neither retention nor compositional reuse.
Approach
Routes among primitive skills using in-context skill mixing so that skills are kept separate and composed at inference rather than absorbed into one shared update (from abstract only; mechanism details not stated).
Closest papers by meaning
- ElegantVLA: Learning When to Think for Efficient Vision-Language-Action Models (NeurIPS 2026 · similarity 0.91)
- PriorVLA: Prior-Preserving Adaptation for Vision-Language-Action Models (NeurIPS 2026 · similarity 0.91)
- FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies (NeurIPS 2026 · similarity 0.91)
- VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models (NeurIPS 2026 · similarity 0.91)
- NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models (NeurIPS 2026 · similarity 0.90)
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching (NeurIPS 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
