
Insta360最新全景综述:全景视觉的挑战、方法与未来 (opens in a new tab)
本文作者团队来自 Insta360 影石研究院及其合作高校。目前,Insta360 正在面向世界模型、多模态大模型、生成式模型等前沿方向招聘实习生与全职算法工程师,欢迎有志于前沿 AI 研究与落地的同
Total 388 articles

本文作者团队来自 Insta360 影石研究院及其合作高校。目前,Insta360 正在面向世界模型、多模态大模型、生成式模型等前沿方向招聘实习生与全职算法工程师,欢迎有志于前沿 AI 研究与落地的同

面向自动驾驶的多模态大模型在 “推理链” 上多以文字或符号为中介,易造成空间 - 时间关系模糊与细粒度信息丢失。FSDrive(FutureSightDrive)提出 “时空视觉 CoT”(Spatio-Temporal Chain-of-Thought),让模型直接 “以图思考”,用统一的未来图像帧作为中间推理步骤,联合未来场景与感知结果进行可视化推理。

AI Tech Review outlines Mei Tao's AWM concept, connecting language models, multimodal representations and embodied feedback. Team demos illustrate the idea; visual consistency does not establish physical accuracy or reliable real-world execution.

Huawei Cloud presents its Ascend-native embodied world model CloudRobo-WM1.2 and development platform, with two benchmark results and industrial demonstrations. Model weights, inference and post-training code, and pretraining practices are scheduled for November 30.

An Ant team and Westlake Xinchen present Duo v1, combining intent decisions with audiovisual generation for continuous interaction, and release models and code. The team reports 30 cases and 180 human checks; the work remains an early research demonstration.

Synced reports Mu Li is joining Aimotion as cofounder and CTO while remaining in the same roles at Boson AI. The teams plan to combine models and industry scenarios for commercial world models and sales/marketing agents.

方案以世界模型支持预演、通用模型生成技能、端侧执行动作。团队披露取衣实验中的迭代耗时和残留率,完整业务效果仍待验证。

Murea Labs的Murea-InWorld通过Murea-Mind协同Murea-Pro和Murea-Fast生成实时互动音视频,Murea-Pro以81.13分位列WBench Full-289第一,Murea-Fast以64.98分居OpenS2V-Eval参评开源模型第一。

普林斯顿大学、得克萨斯大学奥斯汀分校、多伦多大学、NVIDIA和智元研究人员提出WorldOracle,并于10月16日开放评测平台;七种模型的真实执行对照显示,其机械臂轨迹较准但物体运动易偏离,长序列预测表现也会明显退化。

英伟达联合MIT和牛津大学团队提出Physis-Lang,通过物理语言描述、自进化准则和能力导向的数据检索提升视频模型的物理理解与生成表现,其Cosmos3-Super和Cosmos3-Nano在Physics-IQ Verified分列第一、第二。