AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersgpuai安全jake whartonit之家solidot港股

搜索：VLM

共命中 44 条（服务端检索）
In-Context Robot Learning with VLM Agents
Enabling robots to adapt to unfamiliar environments as readily as humans remains a moonshot goal of embodied AI. No fini…
智能体 HuggingFace Daily Papers · 9-16 阅读 23·访客 22
Show-Harness: Just a VLM Agent Can Play Robots
Foundation vision-language models (VLMs) exhibit broad intelligence about the world, yet translating this intelligence i…
智能体 HuggingFace Daily Papers · 9-9 阅读 27·访客 25
Robo-COP：机器人编排器与策略在部署中共进化
论文提出VLA策略在训练域外泛化能力有限、成为系统瓶颈，提出Robo-COP方法让VLM编排器与策略在部署中协同进化，以克服单独微调策略导致与编排器脱节的问题。
研究前沿 HuggingFace Daily Papers · 10-6 阅读 9·访客 9
一篇读懂视觉语言模型：图像是怎么变成「语言」的
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。
一叶一世界 精选 · 原创 · 10-6 阅读 63·访客 63
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model …
智能体 HuggingFace Daily Papers · 10-1 阅读 14·访客 14
AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors
When a VLM answers a visual query, current interpretability tools rely on text rationales, which use a mismatched modali…
行业动态 HuggingFace Daily Papers · 9-28 阅读 25·访客 24
清华具身模型登顶全球第一！突围GPT-6、英伟达，不靠外挂和额外数据
田, 晏林* 2026-10-09 11:52:21 来源：量子位 星动纪元选择将视频预测与动作学习分阶段训练，重点不是「视频、动作一锅炖」，而是把两者「解耦」，重新「排序」。 田晏林 发自 凹非寺 量子位 | 公众号 QbitAI 好家…
大模型 量子位 · 5天前 阅读 5·访客 5
Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as …
智能体 HuggingFace Daily Papers · 6天前 阅读 3·访客 3
AI breakthroughs in robotics won’t change your life any time soon
The story is a collaboration between MIT Technology Review and Aventine, a non-profit research foundation that creates a…
智能体 MIT Technology Review · 6天前 阅读 5·访客 5
BudgetPix: Compute-Adaptive Tokenization for Pixel-Space Image Diffusion
Most image generation models rely on uniform tokenization, allocating the exact same computational budget to equally-siz…
行业动态 HuggingFace Daily Papers · 6天前 阅读 1·访客 1
VLA（视觉-语言-动作）模型进化史：机器人如何「看懂再动手」
从 RT-2 把机器人动作当文本 token 输出，到 OpenVLA 开源 7B、π0 用流匹配跑到 50Hz、GR00T 与 Helix 转向双系统架构——本文梳理 VLA 模型三年的演进脉络：动作怎么表示、参数怎么变小、控制频率怎么上去，以及开源与闭源两条路线的分野。
研究前沿 精选 · 原创 · 10-7 阅读 76·访客 76
多模态 RAG：当文档里的关键信息藏在表格与图表里
真实企业文档的多数信息不在正文段落里，而在表格、图表与版式关系里——文本 RAG 的 OCR 管线在这里系统性失真。本文拆解两条补齐路线（解析增强 vs ColPali 式视觉检索）与生成端的图文编排，给出选型权衡。
后端技术 精选 · 原创 · 10-7 阅读 123·访客 123
When to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language Models
Vision-language models (VLMs) have achieved strong performance in multimodal reasoning, yet they remain prone to generat…
研究前沿 HuggingFace Daily Papers · 10-4 阅读 1·访客 1
VIEScore2：带空间定位解释的统一图像评估模型
VIEScore2 将图像表示为 N×N 网格，在单次前向中同时预测图像质量分数与缺陷位置，并在 38K 样本上结合监督微调与 GRPO 训练。
研究前沿 HuggingFace Daily Papers · 10-1 阅读 5·访客 5
刚刚，GPT-6 Astra接上宇树G1，把厨房收拾了！
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…
智能体 量子位 · 9-30 阅读 19·访客 19
工业创新进入“组队局”，拆解西门子Xcelerator开放生态的赋能链路
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？…
智能体 量子位 · 9-28 阅读 28·访客 28
Google Research Introduces an AI Video Co-Director: 4 Agentic Frameworks for Coherent, Minutes-Long Video Generation
Google Research has introduced an **AI video co-director** for long-form video generation. The suite of 4 agentic framew…
智能体 MarkTechPost · 9-28 阅读 25·访客 25
Researchers plug GPT-6 Astra directly into a robot and let it clean up an unfamiliar kitchen
Sep 27, 2026 Researchers from Stanford and Caltech have built HomeBody,** a system that lets a Unitree G1 robot autonomo…
智能体 The Decoder · 9-27 阅读 57·访客 55
Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding
Liquid AI has announced LFM2.5-VL-3B-DSpark, an experimental speculative-decoding draft model for its LFM2.5-VL-3B visio…
行业动态 MarkTechPost · 9-26 阅读 28·访客 28
AI开始研究Physical AI：FSD级团队亮出首版模型Simate-beta，空降RoboDojo
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…
研究前沿 量子位 · 9-26 阅读 26·访客 26
InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
World Action Models (WAMs) jointly model visual dynamics and action generation for generalist robot manipulation. A cent…
智能体 HuggingFace Daily Papers · 9-25 阅读 15·访客 15
早报｜GPT-6 Sol发布，价格腰斩/特努斯：Siri AI不应代替人际关系/4999起，OPPO Find X10系列发布
🧑‍💻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…
大模型 爱范儿 · 9-23 阅读 35·访客 35
HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis
Compositional 3D scene reconstruction has recently been explored from two directions: agentic reasoning that provides se…
智能体 HuggingFace Daily Papers · 9-22 阅读 14·访客 14
RoboFollow: Unveiling the Instruction Following Mirage in Embodied Agents
Modern embodied agents achieve impressive success rates, yet their actual instruction-following ability is far weaker th…
智能体 HuggingFace Daily Papers · 9-22 阅读 12·访客 12
X-Planner: Event-Structured Task Planning for Embodied Intelligence
Task planning bridges high-level instructions and executable behavior in long-horizon manipulation, yet modern Vision-La…
行业动态 HuggingFace Daily Papers · 9-21 阅读 5·访客 5
RULER: Instance-aware Rubric Rewards for SVG Generation
Generating Scalable Vector Graphics (SVG) code from natural-language instructions is an open-ended task without absolute…
智能体 HuggingFace Daily Papers · 9-21 阅读 14·访客 14
All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts
Multilingual scene text recognition (STR) remains challenging due to the scarcity of training data for most languages an…
行业动态 HuggingFace Daily Papers · 9-21 阅读 15·访客 15
PackLab: A Comprehensive Framework for Developing, Training, and Evaluating MLLMs in Robotic Bin Packing
Robotic bin packing requires long-horizon sequential decision-making, as each object placement affects the available spa…
智能体 HuggingFace Daily Papers · 9-20 阅读 17·访客 16
Transferring the Intelligence of VLMs to Robotic Control
Humans can seamlessly adapt to both physical and digital worlds, suggesting that while a digital-to-real gap exists in e…
智能体 HuggingFace Daily Papers · 9-19 阅读 13·访客 13
Paint-Anything: Unified Any-Color Control for Image Generation and Editing
Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex valu…
行业动态 HuggingFace Daily Papers · 9-17 阅读 18·访客 18
PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
Intelligent systems that act in the world require image understanding that is both comprehensive and spatially grounded.…
智能体 HuggingFace Daily Papers · 9-16 阅读 14·访客 14
RiskChainBench: A Benchmark for Obfuscated Platform Message Restoration and Evidence-Grounded Web Investigation
Platform abuse campaigns conceal redirection instructions with emojis, homophones, character decomposition, and redundan…
研究前沿 HuggingFace Daily Papers · 9-15 阅读 20·访客 18
无问芯穹联合清华、上交正式开源具身端侧推理引擎APXInf，Pi 0.5性能SOTA
卡位具身智能规模化落地“最后一公里”！]
开源项目 量子位 · 9-15 阅读 27·访客 26
PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models
We present PhysBrain 1.5, a unified model for understanding physical environments, generating actions, and predicting fu…
行业动态 HuggingFace Daily Papers · 9-14 阅读 15·访客 15
中国物理AI大突破：PhysBrain 1.5登顶全球开源榜一，空间智能与GPT-6 Astra并驾齐驱
这家中国公司，刚跑完了物理闭环里最难的一段路]
开源项目 量子位 · 9-14 阅读 25·访客 23
E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
Can financial vision-language models (VLMs) turn chart evidence into reliable action recommendations? Existing hallucina…
研究前沿 HuggingFace Daily Papers · 9-13 阅读 15·访客 15
RelateAnything: Real-Time Open-Vocabulary Relation Prediction From Any Inputs
Open-vocabulary detection accepts any class list at inference, and promptable segmentation returns regions without class…
行业动态 HuggingFace Daily Papers · 9-11 阅读 18·访客 18
Attention-DP3: Spatially Object-aware 3D Diffusion Policy via Geometry-aligned Attentional Conditioning
3D point-cloud observations are inherently ambiguous in complex, cluttered manipulation scenes, where target objects may…
行业动态 HuggingFace Daily Papers · 9-10 阅读 13·访客 12
Feature Recovery for Object Understanding After Irreversible Fire Damage
Objects in post-fire environments often undergo irreversible physical transformations that change their geometry, materi…
行业动态 HuggingFace Daily Papers · 9-10 阅读 12·访客 12
Mi-Ripple: Restoring Images Degraded by Iterative AI Editing
Iterative reference-conditioned image editing can introduce grid-like and granular textures, commonly described as digit…
行业动态 HuggingFace Daily Papers · 9-10 阅读 13·访客 9
Agentic Visual Generation: From Generative Models to Agentic Control
Visual generation is evolving from generative models used through a single invocation into agentic control processes tha…
智能体 HuggingFace Daily Papers · 9-6 阅读 14·访客 12
ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models
Vision-Language-Action (VLA) models demonstrate strong generalization in robotic manipulation and navigation, but existi…
智能体 HuggingFace Daily Papers · 9-2 阅读 4·访客 4
SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models
Long-horizon manipulation is partially observable: the information needed to choose the next action may appear only in o…
行业动态 HuggingFace Daily Papers · 9-2 阅读 16·访客 15
Training-Free Speech-Centric Omni Understanding with Frozen VLMs
Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and …
行业动态 HuggingFace Daily Papers · 8-7 阅读 8·访客 7