AI Applications

FAST: A novel action tokenization method using discrete cosine transform drastically improves autoregressive vision-language-action models’ training and performance, enabling dexterous and high-freque…

EnerVerse: A novel framework seamlessly integrates convolutional and attention mechanisms to generate embodied future spaces for enhanced robotic manipulation, mitigating data scarcity with a generati…

Android Agent Arena (A3): A novel evaluation platform for mobile GUI agents offering diverse tasks, flexible action space, and automated LLM-based evaluation, advancing real-world AI agent research.

SWE-Gym, a novel environment for training real-world software engineering agents using 2,438 real-world Python task instances, achieves new state-of-the-art performance and is publicly available.

LearnLM enhances Gemini for education by training it to follow pedagogical instructions, leading to significant preference improvements over GPT-40, Claude 3.5, and Gemini 1.5 Pro in diverse learning …

MoDE makes AI for robot control faster and more efficient.

From language models to action models: building AI that does things.

TidyBot++: Low-cost, open-source holonomic mobile base makes robot learning easier.

CARP: A novel visuomotor policy learning paradigm achieves high accuracy and 10x faster inference than state-of-the-art by combining autoregressive efficiency and diffusion model precision through a c…

Moto: Bridging language for robot manipulation using latent motion tokens, achieving superior performance with limited data.

Code-as-Monitor (CaM) uses vision-language models and constraint-aware visual programming to achieve both reactive and proactive robotic failure detection in real-time, improving success rates and red…

WildLMa enables robots to perform complex, long-horizon manipulation tasks in unstructured environments by combining language-conditioned imitation learning, a whole-body controller for efficient tele…

DiffusionDrive: a novel truncated diffusion model achieves real-time, high-quality end-to-end autonomous driving by leveraging multi-mode action distributions and significantly reducing computational …

SWIFT, a new system, enables a soft robotic hand to learn dynamic pen spinning via real-world trial-and-error, achieving 100% success across diverse pen properties without explicit object modeling.

Claude 3.5 Computer Use: A groundbreaking AI model offering public beta graphical user interface (GUI) agent for computer use is comprehensively analyzed in this research. This study provides an out-o…

Hermes, a novel LLM-based framework, automates cellular network modeling by generating explainable ‘blueprints’ for constructing Network Digital Twins (NDTs), paving the way for fully autonomous netwo…

DynaMem empowers robots with online dynamic spatio-semantic memory, achieving a 2x improvement in pick-and-drop success rate on non-stationary objects compared to static systems.

DeeR-VLA dynamically adjusts the size of a multimodal large language model based on task difficulty, significantly reducing computational cost and memory usage in robotic control without compromising …

Collaborative Assistant for Personalized Exploration (CARE) enhances LLM chatbots for exploratory tasks by combining a multi-agent framework with a structured interface, delivering tailored solutions …