Embodied Ai
PulseAugur coverage of Embodied Ai — every cluster mentioning Embodied Ai across labs, papers, and developer communities, ranked by signal.
11 day(s) with sentiment data
-
PhysX-CoT: New method generates 3D assets with explicit physical reasoning
Researchers have introduced PhysX-CoT, a novel approach to generating simulation-ready 3D assets from single images. Unlike previous methods that treat this as an implicit vision-language task, PhysX-CoT explicitly mode…
-
Deltoris framework enables real-time VLA inference for embodied AI
Researchers have developed Deltoris, a new framework designed to enable real-time inference for Vision-Language-Action (VLA) models in embodied AI systems. This framework addresses the high computational demands of diff…
-
New research integrates world modeling for efficient embodied AI control
Three new research papers introduce novel approaches to enhance embodied AI control by integrating world modeling more efficiently. WorldSimProbe focuses on diagnosing the faithfulness of action-conditioned world models…
-
New frameworks emerge for interactive video world models
Researchers have introduced two new frameworks for advancing video world models, which are crucial for embodied AI and interactive simulations. The first, HelloWorld, enables social interactions between users and charac…
-
Taku Komura's 2016 AI motion synthesis research wins SIGGRAPH Test-of-Time Award
Taku Komura and his team at the University of Hong Kong have been recognized with the SIGGRAPH Test-of-Time Award for their 2016 research on deep learning for character motion synthesis. This foundational work pioneered…
-
Security threats and defenses for embodied AI with world models surveyed
This paper surveys the security landscape of embodied AI systems that utilize world models. It details how these predictive cores, while enabling advanced planning, also introduce new vulnerabilities. The research trace…
-
Chinese tech giants invest heavily in physical AI and robotics
Major Chinese internet companies are expanding their AI investments beyond digital realms into physical applications. Meituan, JD.com, ByteDance, and Baidu are developing and deploying technologies such as robotaxis, de…
-
YaoLe Technology raises funding for tactile sensing data gloves for AI
YaoLe Technology, a company specializing in flexible tactile sensing, has secured a new round of Pre-A+ funding led by Dinghe Gaoda, with participation from Changshu Auto Trim and Zulong Entertainment. The company's tec…
-
RoboSense launches E2 perception platform for physical AI data
RoboSense has launched its second-generation all-solid-state perception platform, E2, designed to serve as a data input for physical AI. This new platform utilizes the company's proprietary "Peacock" SPAD-SoC chip and a…
-
Guangjian Technology unveils embodied AI visual perception solution
Guangjian Technology has launched a new embodied AI visual perception solution designed to provide robots with enhanced capabilities for understanding and interacting with the physical world. This solution utilizes AI-d…
-
RLinf v0.3 enhances embodied AI development with new models and real-robot capabilities
RLinf v0.3, a large-scale reinforcement learning infrastructure project for embodied AI, has been released by Wuwenxiong (Wuwenxiong) in collaboration with Tsinghua University. This new version enhances the platform's c…
-
Embodied AI takes center stage at RSS 2026, with Chinese firms gaining prominence
The 22nd Robotics: Science and Systems (RSS 2026) conference in Sydney will feature a significant focus on embodied AI, with independent sessions dedicated to VLA Models, Humanoids, and World Models, indicating a conver…
-
New black-box attack targets vision-language navigation systems
Researchers have developed AdvNav, a novel black-box adversarial attack framework designed to disrupt Vision-and-Language Navigation (VLN) systems. Unlike previous methods requiring white-box access, AdvNav operates sol…
-
MobileSAM2: Lightweight SAM2 for Spatial Intelligence on Mobile Devices
Researchers have developed MobileSAM2, a lightweight version of the SAM2 video foundation model designed for use on resource-constrained devices. This was achieved through a novel technique called Hypergraphical Knowled…
-
New AdvNav attack targets Vision-Language Navigation systems
Researchers have developed AdvNav, a novel black-box adversarial attack framework designed to disrupt Vision-Language Navigation (VLN) systems. Unlike previous methods requiring white-box access or focusing on single-st…
-
New AI Model GIRAF Enhances Human-Object Interaction Synthesis
Researchers have developed GIRAF, a text-conditioned diffusion model designed to generate realistic human interactions with articulated objects. This advancement addresses a key challenge in embodied AI and computer gra…
-
Embodied AI research advances grounded world models and agent collaboration · 8 sources tracked
Recent research explores advancements in embodied AI, focusing on how biological systems acquire grounded world models through environmental interaction. Papers discuss frameworks for integrating AI intelligence into ph…
-
Embodied AI Startup Simplexity Robotics Delivers First 100 Robots
Simplexity Robotics, a startup specializing in embodied AI, has successfully delivered its first 100 robots to production lines. The company, founded less than a year ago, announced the delivery of its i7 Pro model, whi…
-
New framework generates physically accurate mirror reflections for AI data
Researchers have developed PhysMirror, a new framework designed to generate physically accurate mirror reflections in images. This method addresses a key limitation in current text-to-image diffusion models, which often…
-
LLMs like ChatGPT lack physical bodies to perform real-world tasks
Large Language Models like ChatGPT excel at understanding and generating text, but they lack the physical embodiment necessary to perform real-world tasks such as washing dishes. This limitation stems from their inabili…