aloha
PulseAugur coverage of aloha — every cluster mentioning aloha across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
逐际动力 FluxVLA Engine V2 streamlines embodied AI development
逐际动力 (LimX Dynamics) has released the second version of its open-source engineering foundation, FluxVLA Engine, designed to streamline the development and deployment of embodied AI. This update enhances capabilities by …
-
Study reveals VLA models' motor programs tied to absolute coordinates, ignoring scene changes
Researchers have conducted a mechanistic interpretability study on vision-language-action (VLA) models, revealing that motor programs are often tied to absolute coordinates and disregard changes in the visual scene. Thi…
-
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 VPP2 model enhances robot action prediction and generalization
Researchers have introduced Video Prediction Policy 2 (VPP2), an advancement in World Action Models (WAMs) designed for more accurate robot motion prediction and action generation in open-ended environments. VPP2 addres…
-
Reward AI unveils OM-1 robot policy trained solely on human demonstrations
Robotics startup Reward AI has introduced OM-1, a general-purpose manipulation policy trained exclusively on human demonstrations captured via a sensorized glove. Unlike typical approaches that use teleoperation or on-r…
-
New method fine-tunes robots for multi-task manipulation
Researchers have developed a novel self-supervised method to fine-tune vision-language-action (VLA) models for robotic manipulation tasks. This approach generates additional training data from the VLA's own zero-shot in…
-
New method fine-tunes VLA models for robots with self-supervised control
Researchers have developed a self-supervised method to fine-tune Vision-Language-Action (VLA) models, such as $π_{0.5}$, for improved performance on new robotic embodiments. This approach generates additional training d…
-
New framework ORPA enables real-time robot action correction with human feedback
Researchers have introduced ORPA (Online Residual Policy Adaptation), a new framework designed to improve robot manipulation control. ORPA allows for real-time adjustments to robot actions based on human feedback withou…
-
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…
-
Robot learning enhanced by human-like gaze and foveated vision transformers
Researchers have developed GIAVA (Gaze Integrated Active-Vision ALOHA), a novel robot vision system that mimics human gaze and foveation to improve efficiency and robustness in robot learning. By integrating eye-trackin…
-
GuidedVLA enhances robot action control with explicit task factor guidance
Researchers have introduced GuidedVLA, a novel approach to enhance the controllability and interpretability of vision-language-action (VLA) models for robot manipulation. This method explicitly guides the action generat…
-
Robots' false success detection relies on vision, study finds
Researchers have investigated the visibility of manipulation failures in robot learning, specifically focusing on "false successes" where a robot incorrectly logs a task as complete. Their study used simulated robotic t…
-
MSACT improves robot fine manipulation with stable, low-latency spatial alignment
Researchers have developed MSACT, a novel method for improving fine manipulation in robotics, particularly for bimanual tasks. This approach uses a multistage spatial attention module to extract stable 2D attention poin…