stanford-iris-lab
0 Apps · 1 Tool · 1 Intel
The Intelligence through Robotic Interaction at Scale (IRIS) Lab is a Stanford University research group directed by Professor Chelsea Finn, investigating how robots and AI agents can develop broadly intelligent behavior through learning and interaction. The lab draws on deep reinforcement learning, meta-learning, and self-supervised techniques to build scalable robotic intelligence, and is affiliated with SAIL, the Stanford Robotics Center, and CRFM.
Tools
Stanford IRIS Lab's agent scaffolding that hit 76.4% on Terminal-Bench 2.0 with Claude Opus 4.6.
Intel
A research paper and framework demonstrating automated optimization of model harnesses - the scaffolding code that determines what AI models store, retrieve, and present during task execution. Shows significant improvements over hand-designed systems across text classification, math reasoning, and coding tasks.