AgentSTAR uses agents for articulated object tracking; Malik hails end of "grad student descent"
CSProfKGD · x · 2026-09-15
Jitendra Malik notes that the old "graduate student descent" — manually trying techniques and tweaking parameters for a desired output — can now be handed to AI agents, making the classic analysis-by-synthesis CV paradigm far more powerful.
The quoted post introduces AgentSTAR, an agentic method for joint reconstruction and tracking of articulated objects from monocular video, robust to rapid motion, heavy occlusion, and thin objects like spoons.
More from coding & agent
- SWE: pre-nerf Opus 4.6 was the goat, and smarter models won't make SWE easier — LouMM · 2026-09-15
- Elyx debuts with a new AI-friendly design file format for designers and agents — michalmalewicz · 2026-09-15
- Hour-long deep dive with an AI agents expert on workflows, skills, and making money — Rasmic · 2026-09-15
- Skill+CLI vs MCP: a developer asks which integration route wins on tokens and reliability — PrinceSauromates · 2026-09-15
- Open-source skill turns one sentence into a single-file web 3D documentary via Claude Code — xiaohu · 2026-09-15
- Hyper3D launches MCP service, letting Codex auto-build 3D models into explainer sites — xiaohu · 2026-09-15