Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No fini…

Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence i…

大语言模型只认 token 序列，图片如何进入对话？本文拆解视觉语言模型的三块积木：把图像切块编码的 ViT、对齐两种向量空间的投影层，以及图文对三阶段训练配方，并解释视觉幻觉与计数失准这些特有失败的架构根源。

Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model …

When a VLM answers a visual query, current interpretability tools rely on text rationales, which use a mismatched modali…

henry* 2026-09-30 15:54:54 来源：量子位 让GPT把机器人技能当工具调用 henry 发自 凹非寺 量子位 | 公众号 QbitAI 机器人的GPT时刻，还真得靠GPT（doge）！ 刚刚，GPT-6 Astra…

田, 晏林* 2026-09-28 20:43:53 来源：量子位 工业平台已经卷到帮伙伴拿线索、做Agent、出海了 田晏林 发自 凹非寺 量子位 | 公众号 QbitAI 一家技术公司想把一个工业创新方案卖进工厂，中间大概要过多少关？…

Google Research has introduced an **AI video co-director** for long-form video generation. The suite of 4 agentic framew…

Sep 27, 2026 Researchers from Stanford and Caltech have built HomeBody,** a system that lets a Unitree G1 robot autonomo…

Liquid AI has announced LFM2.5-VL-3B-DSpark, an experimental speculative-decoding draft model for its LFM2.5-VL-3B visio…

田, 晏林* 2026-09-26 17:07:41 来源：量子位 Simate将训练、推理与评测全流程接入自研Infra，通过极致的任务编排与资源调度，同时并行推进数十条相互独立的研究路线。 Jay 发自 凹非寺 量子位 | 公众号 Q…

World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation. A cent…

🧑‍💻GPT-6 Sol 与 Luna 发布，API 价格降低 50% 🧠Claude Opus 5.5 发布，典型任务运行成本降低 40% 🍎特努斯：Siri AI 不应代替人际关系 📱OPPO Find X10 系列发布：49…

Compositional 3D scene reconstruction has recently been explored from two directions: agentic reasoning that provides se…

Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker th…

Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-La…

Generating Scalable Vector Graphics (SVG) code from natural-language instructions is an open-ended task without absolute…

Multilingual scene text recognition (STR) remains challenging due to the scarcity of training data for most languages an…

Robotic bin packing requires long-horizon sequential decision-making, as each object placement affects the available spa…

Humans can seamlessly adapt to both physical and digital worlds, suggesting that while a digital-to-real gap exists in e…

Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex valu…

Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded.…

Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundan…

卡位具身智能规模化落地“最后一公里”！]

We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting fu…

这家中国公司，刚跑完了物理闭环里最难的一段路]

Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucina…

Open-vocabulary detection accepts any class list at inference, and promptable segmentation returns regions without class…

3D point-cloud observations are inherently ambiguous in complex, cluttered manipulation scenes, where target objects may…

Objects in post-fire environments often undergo irreversible physical transformations that change their geometry, materi…

Iterative reference-conditioned image editing can introduce grid-like and granular textures, commonly described as digit…

Visual generation is evolving from generative models used through a single invocation into agentic control processes tha…

Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existi…

Long-horizon manipulation is partially observable: the information needed to choose the next action may appear only in o…

Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and …