Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce actions often diminishes the VLM's foundational reasoning and multimodal understanding, hindering generalization to novel scenarios, instruction following, and semantic understanding. We argue that this catastrophic forgetting is due to a distribution mismatch between the VLM's internet-scale pretraining corpus and the robotics fine-tuning data. Inspired by this observation, we introduce VLM2VLA: a VLA training paradigm that first resolves this mismatch at the data level by representing low-level actions with natural language. This alignment makes it possible to train VLAs solely with Low-Rank Adaptation (LoRA), thereby minimally modifying the VLM backbone and averting catastrophic forgetting. As a result, the VLM can be fine-tuned on robot teleoperation data without fundamentally altering the underlying architecture and without expensive co-training on internet-scale VLM datasets. Through extensive Visual Question Answering (VQA) studies and over 800 real-world robotics experiments, we demonstrate that VLM2VLA preserves the VLM's core capabilities, enabling zero-shot generalization to novel tasks that require open-world semantic reasoning and multilingual instruction following.

Vision-language-action (VLA) models have recently emerged as a promising paradigm for robotic control, enabling end-to-end policies that ground natural language instructions into visuomotor actions. However, current VLAs often struggle to satisfy precise task constraints, such as stopping based on numeric thresholds, since their observation-to-action mappings are implicitly shaped by training data and lack explicit mechanisms for condition monitoring. In this work, we propose CLAW (CLIP-Language-Action for Weight), a framework that decouples condition evaluation from action generation. CLAW leverages a fine-tuned CLIP model as a lightweight prompt generator, which continuously monitors the digital readout of a scale and produces discrete directives based on task-specific weight thresholds. These prompts are then consumed by $π_0$, a flow-based VLA policy, which integrates the prompts with multi-view camera observations to produce continuous robot actions. This design enables CLAW to combine symbolic weight reasoning with high-frequency visuomotor control. We validate CLAW on three experimental setups: single-object grasping and mixed-object tasks requiring dual-arm manipulation. Across all conditions, CLAW reliably executes weight-aware behaviors and outperforms both raw-$π_0$ and fine-tuned $π_0$ models. We have uploaded the videos as supplementary materials.

In this paper, we present Optimized Prompt-based Unified System (OPUS), a framework that utilizes a Large Language Model (LLM) to control Pan-Tilt-Zoom (PTZ) cameras, providing contextual understanding of natural environments. To achieve this goal, the OPUS system improves cost-effectiveness by generating keywords from a high-level camera control API and transferring knowledge from larger closed-source language models to smaller ones through Supervised Fine-Tuning (SFT) on synthetic data. This enables efficient edge deployment while maintaining performance comparable to larger models like GPT-4. OPUS enhances environmental awareness by converting data from multiple cameras into textual descriptions for language models, eliminating the need for specialized sensory tokens. In benchmark testing, our approach significantly outperformed both traditional language model techniques and more complex prompting methods, achieving a 35% improvement over advanced techniques and a 20% higher task accuracy compared to closed-source models like Gemini Pro. The system demonstrates OPUS's capability to simplify PTZ camera operations through an intuitive natural language interface. This approach eliminates the need for explicit programming and provides a conversational method for interacting with camera systems, representing a significant advancement in how users can control and utilize PTZ camera technology.

The integration of robotics and augmented reality (AR) presents transformative opportunities for advancing human-robot interaction (HRI) by improving usability, intuitiveness, and accessibility. This work introduces a controller-free, LLM-driven voice-commanded AR puppeteering system, enabling users to teleoperate a robot by manipulating its virtual counterpart in real time. By leveraging natural language processing (NLP) and AR technologies, our system -- prototyped using Meta Quest 3 -- eliminates the need for physical controllers, enhancing ease of use while minimizing potential safety risks associated with direct robot operation. A preliminary user demonstration successfully validated the system's functionality, demonstrating its potential for safer, more intuitive, and immersive robotic control.

Building generalist robotic systems involves effectively endowing robots with the capabilities to handle novel objects in an open-world setting. Inspired by the advances of large pre-trained models, we propose Keypoint Affordance Learning from Imagined Environments (KALIE), which adapts pre-trained Vision Language Models (VLMs) for robotic control in a scalable manner. Instead of directly producing motor commands, KALIE controls the robot by predicting point-based affordance representations based on natural language instructions and visual observations of the scene. The VLM is trained on 2D images with affordances labeled by humans, bypassing the need for training data collected on robotic systems. Through an affordance-aware data synthesis pipeline, KALIE automatically creates massive high-quality training data based on limited example data manually collected by humans. We demonstrate that KALIE can learn to robustly solve new manipulation tasks with unseen objects given only 50 example data points. Compared to baselines using pre-trained VLMs, our approach consistently achieves superior performance.

Supporting real-time interactions between human controllers and remote devices remains a challenging goal in the Metaverse due to the stringent requirements on computing workload, communication throughput, and round-trip latency. In this paper, we establish a novel framework for real-time interactions through the virtual models in the Metaverse. Specifically, we jointly predict the motion of the human controller for 1) proactive rendering in the Metaverse and 2) generating control commands to the real-world remote device in advance. The virtual model is decoupled into two components for rendering and control, respectively. To dynamically adjust the prediction horizons for rendering and control, we develop a two-step human-in-the-loop continuous reinforcement learning approach and use an expert policy to improve the training efficiency. An experimental prototype is built to verify our algorithm with different communication latencies. Compared with the baseline policy without prediction, our proposed method can reduce 1) the Motion-To-Photon (MTP) latency between human motion and rendering feedback and 2) the root mean squared error (RMSE) between human motion and real-world remote devices significantly.

Models with fewer parameters are necessary for the neural control of memory-limited, performant robots. Finding these smaller neural network architectures can be time-consuming. We propose HyperPPO, an on-policy reinforcement learning algorithm that utilizes graph hypernetworks to estimate the weights of multiple neural architectures simultaneously. Our method estimates weights for networks that are much smaller than those in common-use networks yet encode highly performant policies. We obtain multiple trained policies at the same time while maintaining sample efficiency and provide the user the choice of picking a network architecture that satisfies their computational constraints. We show that our method scales well - more training resources produce faster convergence to higher-performing architectures. We demonstrate that the neural policies estimated by HyperPPO are capable of decentralized control of a Crazyflie2.1 quadrotor. Website: https://sites.google.com/usc.edu/hyperppo

On Monday, a group of AI researchers from Google and the Technical University of Berlin unveiled PaLM-E, a multimodal embodied visual-language model (VLM) with 562 billion parameters that integrates vision and language for robotic control. They claim it is the largest VLM ever developed and that it can perform a variety of tasks without the need for retraining. According to Google, when given a high-level command, such as "bring me the rice chips from the drawer," PaLM-E can generate a plan of action for a mobile robot platform with an arm (developed by Google Robotics) and execute the actions by itself. PaLM-E does this by analyzing data from the robot's camera without needing a pre-processed scene representation. This eliminates the need for a human to pre-process or annotate the data and allows for more autonomous robotic control.

In machine learning, meta-learning methods aim for fast adaptability to unknown tasks using prior knowledge. Model-based meta-reinforcement learning combines reinforcement learning via world models with Meta Reinforcement Learning (MRL) for increased sample efficiency. However, adaption to unknown tasks does not always result in preferable agent behavior. This paper introduces a new Meta Adaptation Controller (MAC) that employs MRL to apply a preferred robot behavior from one task to many similar tasks. To do this, MAC aims to find actions an agent has to take in a new task to reach a similar outcome as in a learned task. As a result, the agent will adapt quickly to the change in the dynamic and behave appropriately without the need to construct a reward function that enforces the preferred behavior.

Edge computing provides groundbreaking innovations to enterprise cloud organizations, including nearly instant code transfer, reduced latency, and enhanced performance. The lightning speed of edge compute is due to the placement of the platform. Unlike public cloud, edge compute is placed as close as possible to the point of interaction with humans, electronics, and various connected devices. Edge compute becomes more and more relevant to companies as applications evolve, including virtual reality, augmented reality, and video analytics, which rely on artificial intelligence. With real-time code transfer that AI needs to be extremely precise, and as AI evolves, every millisecond counts, according to Paul Savill (pictured), senior vice president of core network and technology solutions at CenturyLink Inc.