Astra機器人空間推理躍升
Ad Skip to content GPT-6 Astra appears to show a "step change" in spatial reasoning based on early benchmarks Matthias Bastian View the LinkedIn Profile of Matthias Bastian Sep 12, 2026 GPT-6 Astra appears to be a big leap forward for spatial reasoning.
A new robotics benchmark called StationeryBench pits OpenAI's GPT-6 Astra against Ai2's MolmoAct2 across five desk-object tasks like uncapping a marker, pouring out paper clips, or passing a ruler between two robot arms.Both models controlled the same dual-arm YAM robots across 200 trials.
Astra fully completed 7 out of 100 tasks; MolmoAct2 completed zero.Astra's median progress score hit 46 out of 100, MolmoAct2 managed 12.All results, videos, and code are on GitHub.OpenAI has long-term plans to build its own consumer robots.
Yoav Artzi, an AI researcher at Cornell and Google DeepMind, calls Astra a "step change in spatial reasoning." On the still-unpublished REMAP benchmark, GPT-Astra reaches accuracy close to human level, though Artzi notes that "even ASTRA doesn't get to what humans do in other scenarios.
" He suspects OpenAI trained the model on large amounts of 3D data such as Blender scenes.That lines up with Astra's particular improvement on 3D tasks.
AdAd AI News Without the Hype – Curated by Humans Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe now Source: Robocurve BETA-TEST × wpDiscuzInsert BETA-TEST × wpDiscuzInsert
Related
相關文章
無問芯穹與華環電子簽署戰略合作，共同探索國產異構算力AI基礎設施新方向
無問芯穹與華環電子簽署戰略合作協議，雙方將結合各自在AI軟體平台、網路通信與硬體研發的優勢，共同探索國產異構算力基礎設施的協同方案。此次合作聚焦於智算中心解決方案及「Token工廠」新模式，目標是推動計算、網路與AI原生基礎設施深度融合，為AI規模化應用提供高效穩定的支撐。
Jina AI Releases jina-ocr-v1: A 3.4B MoE Document Parser With Built-In Speculative Decoding for Low-Budget GPUs
Jina AI, part of Elastic, has released jina-ocr-v1, an end-to-end visual document parser. It takes PDFs, scans, tables, charts or invoices and returns clean Markdown in 1 pass. The model has 3.
優步全球範圍裁員 10%，被裁員工稱 AI 已大舉滲透日常工作
作者：清源 責編：清源 評論： 9 月 18 日消息，據《商業內幕》今天（18 日）晚間報道，在優步（Uber），AI 已經滲透到員工工作的許多環節，從回答 Slack 裡的內部問題，到替乘客行程中聯繫客服時收到的消息撰寫回復。6 名近期遭裁員的員工透露，過去幾個月，AI 在工作中的使用範圍明顯擴大，其中一些人甚至會通過提示詞讓 AI 完成相當一部分任務。
智譜 ZCode 被質疑“偷傳代碼”：官方回應稱問題已修復，將開源代碼庫、引入第三方審查
作者：清源 責編：清源 評論： 感謝網友 咩咩洋 的線索投遞！9 月 18 日消息，針對社區中有關代碼庫數據上傳的討論，智譜旗下編程產品 ZCode 今天（18 日）通過智譜官方群組向受影響用戶致歉，併發布回應稱已第一時間完成自查，相關問題目前已經修復。
月之暗面遞表之後，Kimi 的成色要被驗算三遍
舒澤品牌手記2026.09.18 18:16 · 來自浙江全文4982字00:00 / 14:05Anthropic 的 30 萬次指控，會成為招股書的第幾頁？文 | 舒澤品牌手記9月17日，月之暗面發佈了一套金融行業解決方案。按官方披露，中信建投、中金公司、易方達等數十家金融機構已經在用 Kimi 處理投研建模、風險排查和盡調材料——研究人員把管理層報表、審計報告和盡調文件交給 Kimi，拿回一份可以繼續調整假設的 Excel 模型。同一天，深圳商報記者就港股上市進展、股東架構調整等事項向月之暗面發去採訪函。