Square root of pi
PulseAugur coverage of π0.5 — every cluster mentioning π0.5 across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
逐际动力发布FluxVLA Engine，统一具身智能研发流程
逐际动力 (Interlink Dynamics) has released the FluxVLA Engine, an open-source engineering framework designed to streamline the development of embodied AI. This engine aims to unify data, training, evaluation, and deployment…
-
New TOPS method enhances multi-task robot manipulation with adaptive priors
Researchers have developed TOPS (Task-Oriented Priors and Schedules), a novel method for language-conditioned multi-task robot manipulation. TOPS adapts the flow source prior and interpolation schedule to individual tas…
-
New research explores context inference in randomized dynamics and dynamic view routing for robots
A new research paper explores how dynamics randomization in simulated environments can affect a model's ability to infer context. The study introduces the concept of "predictive headroom" to quantify the remaining infor…
-
New Orchestra system enables robots to follow complex multimodal instructions
Researchers have developed Orchestra, a new agent harness designed to improve robotic manipulation by enabling robots to follow complex, multi-step multimodal instructions. Orchestra separates task planning and executio…
-
GreenWAM: A Unified Foundation Model for Robotics Control and Prediction
Researchers have introduced GreenWAM, a novel world foundation model designed for robotics. This single model functions as both an action-conditioned world model and a policy, capable of operating across 20 diverse robo…
-
Robot policy learning advances with new methods for memory and time integration · 6 sources tracked
Recent research in robotics is exploring how to improve policy learning by explicitly incorporating physical time into memory dynamics. Papers propose methods like RSSM-RLPD for learning from real-robot interaction with…
-
Chinese robotics firm Star-Epoch's VPP2 model tops global rankings, outperforming GPT-6 and Nvidia
A Chinese robotics company, Star-Epoch, has developed a world action model (WAM) called VPP2 that has achieved the top ranking on the RoboDojo benchmark, surpassing leading models like GPT-6-ASTRA and Nvidia's GR00T-N1.…
-
New RoboSPA benchmark tests VLA models on complex robotic reasoning
Researchers have introduced RoboSPA, a new dataset and benchmark designed to evaluate the embodied reasoning capabilities of Vision-Language-Action (VLA) models in robotics. RoboSPA focuses on fine-grained spatial reaso…
-
Li, Wu introduce TrAct to unify robot control and visual prediction
Researchers, including Fei-Fei Li and Jiajun Wu, have introduced TrAct, a novel approach to bridge the gap between robot control and visual prediction. TrAct utilizes "visual tracks" as an intermediary language, transla…
-
Former Huawei "Genius Youth" Li Bojie Discusses AI Career and Entrepreneurship
Li Bojie, a former "Genius Youth" at Huawei, has publicly discussed his experiences, including a viral interview incident and his entrepreneurial journey. He co-founded Metagent, an AI agent company, which faced challen…
-
StreamPI framework gives VLA models temporal understanding of physical world
Researchers from Da Xiao Robotics and the University of Hong Kong have introduced StreamPI, a novel framework designed to imbue Vision-Language-Action (VLA) models with a temporal understanding of the physical world. Un…
-
New SoftVTBench dataset evaluates physical interaction in deformable object manipulation
Researchers have introduced SoftVTBench, a new dataset and benchmark designed to evaluate the quality of physical interaction in deformable object manipulation. This dataset pairs visual observations with tactile data, …
-
GigaBrain-0.7 advances embodied AI with new architecture and massive pretraining
Researchers have introduced GigaBrain-0.7, an embodied foundation model designed to enhance generalization across various robot embodiments. This model utilizes a novel three-system architecture, extensive heterogeneous…
-
Robotic embodiment's critical role in AI development is underestimated · 1 source tracked
The importance of robotic embodiment, or the physical hardware of robots, is being underestimated in the pursuit of more intelligent AI models. While AI development often focuses on model capabilities and data availabil…
-
Fei-Fei Li's World Labs launches R2S2R for robot training
Fei-Fei Li's World Labs has launched a new robot training and evaluation engine called Real-to-sim-to-real (R2S2R). This engine bridges the gap between simulated environments and real-world robot deployment by first rec…
-
Humanoid robots gain LLM-powered 'hands' with new VLA models
Recent advancements in Vision-Language-Action (VLA) models aim to bridge the gap between LLMs' reasoning capabilities and the real-time demands of robotic control. NVIDIA's GR00T N1.7, Google DeepMind's Gemini Robotics …
-
Embodied AI firms race to develop tactile sensing for robots at WAIC
At the World Artificial Intelligence Conference (WAIC), companies in the embodied AI sector are increasingly focusing on tactile sensing for robots. This shift is driven by the limitations of purely visual perception in…
-
OpenBMB releases MiniCPM-Robot models for on-device robotics
OpenBMB has released two new models, MiniCPM-RobotTrack and MiniCPM-RobotManip, designed for on-device AI in robotics. MiniCPM-RobotTrack focuses on language-conditioned target tracking, utilizing fused visual features …
-
New models and frameworks advance embodied AI capabilities
Researchers are developing advanced models and frameworks to enable more capable embodied artificial intelligence. One approach, Athena-Brain-8B, is an 8B LLM designed for on-device robot brains, showing strong general …
-
RoboDojo benchmark reveals huge gap between AI robots and human performance
A new benchmark called RoboDojo has been released to evaluate embodied AI, featuring 42 simulation tasks and 18 real-world robot tasks. The benchmark highlights a significant gap between current AI models and human perf…