{"version":1,"type":"story","url":"https://digestai.news/story/mit-google-and-northeastern-unveil-instructmesh-for-editing-aigenerate","json":"https://digestai.news/story/mit-google-and-northeastern-unveil-instructmesh-for-editing-aigenerate.json","markdown":"https://digestai.news/story/mit-google-and-northeastern-unveil-instructmesh-for-editing-aigenerate.md","slug":"mit-google-and-northeastern-unveil-instructmesh-for-editing-aigenerate","headline":"MIT, Google and Northeastern unveil InstructMesh for editing AI‑generated 3D models","summary":"InstructMesh is a new interface that lets users generate, edit, and 3D‑print objects with AI assistance. Developed by MIT’s CSAIL, Google, Microsoft’s TRELLIS system and Northeastern University, the tool pairs the text‑and‑image‑aware TRELLIS generator with the reasoning power of GPT‑4. Users can prompt a design—such as glasses or a mug—then highlight parts to refine, with sliders for precise tweaks.\n\nIn tests, the system recreated popular Thingiverse models, finding that nearly 80 percent of the AI‑generated shapes were structurally flawed. Novice participants were able to spot and fix those issues about 90 percent of the time, producing functional items like a dragon‑handle mug, a shell‑shaped whistle, and a “bristle bot” shrimp‑like robot. Researchers see the approach extending to AR‑guided on‑the‑fly printing and physics‑based simulations, though those capabilities are still speculative.\n\nThe work was presented at the ACM Symposium on User Interface Software and Technology and was supported in part by Google and the MIT‑HPI Collaborative Research Program.","keyPoints":["InstructMesh combines Microsoft TRELLIS 3D generator with GPT‑4 to enable natural‑language editing of AI‑created models","Nearly 80% of generated models were structurally flawed, but novices fixed them about 90% of the time","Researchers demonstrated functional items such as a dragon‑handle mug, a shell‑shaped whistle, and a shrimp‑like bristle bot"],"whyItMatters":"The tool lowers the expertise barrier for 3D design, letting creators and hobbyists correct AI‑generated flaws and reliably produce printable objects, accelerating adoption of generative AI in manufacturing and prototyping.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["MIT","Google","Microsoft","Northeastern University"],"models":["GPT-4","TRELLIS"],"people":["Faraz Faruqi","Stefanie Mueller","Ahmed Katary"]},"firstPublishedAt":"2026-10-01T22:00:00Z","updatedAt":"2026-10-01T22:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"MIT News on AI","title":"New tool lets users repair AI-generated 3D models, then fabricate them just the way they want","url":"https://news.mit.edu/2026/instructmesh-tool-lets-users-repair-ai-3d-models-then-fabricate-them-1001","publishedAt":"2026-10-01T22:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"MIT, Google and Northeastern unveil InstructMesh for editing AI‑generated 3D models\", 1 October 2026, https://digestai.news/story/mit-google-and-northeastern-unveil-instructmesh-for-editing-aigenerate","publisher":"Digest AI","title":"MIT, Google and Northeastern unveil InstructMesh for editing AI‑generated 3D models","datePublished":"2026-10-01T22:00:00Z","url":"https://digestai.news/story/mit-google-and-northeastern-unveil-instructmesh-for-editing-aigenerate"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}