Karl G. Jansky Very Large Array
PulseAugur coverage of Karl G. Jansky Very Large Array — every cluster mentioning Karl G. Jansky Very Large Array across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New robot autonomy benchmark and sovereign AI OS in use
A new benchmark, RobotAgentBench (RAB), has been introduced to evaluate robot agents in realistic, open-world household environments. This benchmark aims to capture the complexity of open-world robot autonomy by assessi…
-
New Echo framework improves robot task completion and failure recovery
Researchers have introduced Echo, a novel framework designed to enhance the capabilities of Vision-Language Action (VLA) models for robotic tasks. Echo integrates stop and failure signals directly into the action genera…
-
VLA-Rolling framework reuses discarded actions for faster, more accurate VLA models
Researchers have developed VLA-Rolling, a new framework that improves the efficiency and control of vision-language-action (VLA) models. This method reuses discarded action tails from previous planning cycles, rather th…
-
OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence
Researchers have introduced OrbiSim, a novel robotic simulation paradigm that treats world models as fully differentiable physics engines. This approach allows for end-to-end differentiability across the simulation loop…
-
Sichuan EIR Robotics secures 100M+ yuan for emotionally intelligent humanoid robots
Sichuan EIR Robotics has secured over 100 million yuan in Pre-A funding to advance its humanoid robot, "Ai Qiu," focusing on emotional companionship for household use. The company's "Emotion Native" approach integrates …
-
RoboHarness enables LLM agents to outperform specialized robotics models
A new open-source robotic harness called RoboHarness has been developed, enabling large language models (LLMs) to perform embodied manipulation tasks. This system provides LLM agents with a visual-geometric control inte…
-
Splat2Act pipeline personalizes robot manipulation policies using 3D scene reconstruction
Researchers have developed Splat2Act, a novel pipeline that personalizes generalist vision-language-action (VLA) manipulation policies for specific environments and objects. This system uses a handheld phone scan to cre…
-
New tuning method recovers generalization in quantized VLAs
Researchers have developed a new method called Policy-Induced Vulnerability-Oriented Tuning (PIVOT-Q) to improve the generalization capabilities of quantized Very Large Arrays (VLAs). Quantization, a process to reduce m…
-
New AI framework steers robot policies to novel behaviors using preferences
Researchers have introduced PrefPI, a novel framework for guiding pretrained generative robot policies toward out-of-distribution behaviors using only relative preferences. This method formulates preference learning as …
-
LLM vs. Agentic AI: Grad Student Weighs Career Paths
A graduate student is seeking advice on choosing between two distinct research paths for their future career: general large language model (LLM) work, encompassing areas like alignment, safety, and interpretability, ver…
-
Xieyue Intelligence raises hundreds of millions for embodied AI model
Xieyue Intelligence has secured several hundred million yuan in Series A+ funding, with participation from investors including Linear Capital and Junshan Capital. The company plans to use these funds to advance its Dupl…
-
Starlink signal leakage endangers radio astronomy frequencies
Starlink's satellite constellation is reportedly causing radio frequency interference that threatens sensitive radio astronomy observations. The leakage affects critical frequencies used for scientific research, particu…
-
HuRo pipeline robotizes human videos for scalable VLA pretraining
Researchers have developed a novel pipeline called HuRo to convert human videos into robot-aligned data for pretraining vision-language-action (VLA) policies. This method addresses the challenge of the embodiment gap be…
-
RoboTracer system enhances robot trajectory tracking with 3D spatial reasoning
Researchers have developed RoboTracer, a novel system that enhances robot trajectory tracking by leveraging 3D spatial perception and metric reasoning. Unlike previous methods that directly output joint torques or rely …
-
Mysterious Embodied AI 'MVP' Shows Human-Like Cognition and Self-Evolution
A mysterious team has released several impressive demonstration videos showcasing a new embodied AI model codenamed "MVP" (Make Veritable People), which aims to imbue robots with human-like cognitive abilities and conti…
-
New TwinDex system slashes robot training data needs, cuts teleoperation reliance
A new system called TwinDex has been developed, which significantly reduces the need for real-world robot teleoperation data in training. This system utilizes a novel approach where data collection and robot execution u…
-
XPeng's VLA system gains 4D spacetime understanding for L4 driving
XPeng has unveiled an upgraded version of its second-generation Very Large Array (VLA) system. This enhancement introduces a four-dimensional spacetime understanding, moving beyond three-dimensional spatial awareness. T…
-
Leju Robot launches KUAVO VLA, boosting industrial efficiency with specialized embodied AI
Leju Robot has launched KUAVO VLA, a specialized embodied intelligence model designed for industrial applications. This model undergoes "mid-training" using over 600 hours of real-world data from KUAVO robots, focusing …
-
New methods enhance VLA policy efficiency and robustness in robotics · 4 sources tracked
Researchers have developed new methods to improve the efficiency and robustness of vision-language-action (VLA) policies in robotics. One approach, EXIMO, uses a vision-language model (VLM) as a planner to break down co…
-
New Framework FabriMAE Enhances VLA Model Self-Evaluation
Researchers have developed FabriMAE, a novel self-evaluation framework for Vision-Language-Action (VLA) models. This framework, called Markov Attention Entropy (MAE), leverages internal visual modality entropy to assess…