The intrinsic nonlinearities of soft robots present significant control but simultaneously provide them with rich computational potential. Reservoir computing (RC) has shown effectiveness in online learning systems for controlling nonlinear systems such as soft actuators. Conventional RC can be extended into physical reservoir computing (PRC) by leveraging the nonlinear dynamics of soft actuators for computation. This paper introduces a PRC-based online learning framework to control the motion of a pneumatic soft bending actuator, utilizing another pneumatic soft actuator as the PRC model. Unlike conventional designs requiring two RC models, the proposed control system employs a more compact architecture with a single RC model. Additionally, the framework enables zero-shot online learning, addressing limitations of previous PRC-based control systems reliant on offline training. Simulations and experiments validated the performance of the proposed system. Experimental results indicate that the PRC model achieved superior control performance compared to a linear model, reducing the root-mean-square error (RMSE) by an average of over 37% in bending motion control tasks. The proposed PRC-based online learning control framework provides a novel approach for harnessing physical systems' inherent nonlinearities to enhance the control of soft actuators.

One of the most widely used tasks to evaluate Large Language Models (LLMs) is Multiple-Choice Question Answering (MCQA). While open-ended question answering tasks are more challenging to evaluate, MCQA tasks are, in principle, easier to assess, as the model's answer is thought to be simple to extract and is directly compared to a set of predefined choices. However, recent studies have started to question the reliability of MCQA evaluation, showing that multiple factors can significantly impact the reported performance of LLMs, especially when the model generates free-form text before selecting one of the answer choices. In this work, we shed light on the inconsistencies of MCQA evaluation strategies, which can lead to inaccurate and misleading model comparisons. We systematically analyze whether existing answer extraction methods are aligned with human judgment, and how they are influenced by answer constraints in the prompt across different domains. Our experiments demonstrate that traditional evaluation strategies often underestimate LLM capabilities, while LLM-based answer extractors are prone to systematic errors. Moreover, we reveal a fundamental trade-off between including format constraints in the prompt to simplify answer extraction and allowing models to generate free-form text to improve reasoning. Our findings call for standardized evaluation methodologies and highlight the need for more reliable and consistent MCQA evaluation practices.

Robotic manipulation of unfamiliar objects in new environments is challenging and requires extensive training or laborious pre-programming. We propose a new skill transfer framework, which enables a robot to transfer complex object manipulation skills and constraints from a single human demonstration. Our approach addresses the challenge of skill acquisition and task execution by deriving geometric representations from demonstrations focusing on object-centric interactions. By leveraging the Functional Maps (FM) framework, we efficiently map interaction functions between objects and their environments, allowing the robot to replicate task operations across objects of similar topologies or categories, even when they have significantly different shapes. Additionally, our method incorporates a Task-Space Imitation Algorithm (TSIA) which generates smooth, geometrically-aware robot paths to ensure the transferred skills adhere to the demonstrated task constraints. We validate the effectiveness and adaptability of our approach through extensive experiments, demonstrating successful skill transfer and task execution in diverse real-world environments without requiring additional training.

Multimodal Large Language Models (MLLMs) have shown remarkable capabilities in video content understanding but still struggle with fine-grained motion comprehension. To comprehensively assess the motion understanding ability of existing MLLMs, we introduce FAVOR-Bench, comprising 1,776 videos with structured manual annotations of various motions. Our benchmark includes both close-ended and open-ended tasks. For close-ended evaluation, we carefully design 8,184 multiple-choice question-answer pairs spanning six distinct sub-tasks. For open-ended evaluation, we develop both a novel cost-efficient LLM-free and a GPT-assisted caption assessment method, where the former can enhance benchmarking interpretability and reproducibility. Comprehensive experiments with 21 state-of-the-art MLLMs reveal significant limitations in their ability to comprehend and describe detailed temporal dynamics in video motions. To alleviate this limitation, we further build FAVOR-Train, a dataset consisting of 17,152 videos with fine-grained motion annotations. The results of finetuning Qwen2.5-VL on FAVOR-Train yield consistent improvements on motion-related tasks of TVBench, MotionBench and our FAVOR-Bench. Comprehensive assessment results demonstrate that the proposed FAVOR-Bench and FAVOR-Train provide valuable tools to the community for developing more powerful video understanding models. Project page: \href{https://favor-bench.github.io/}{https://favor-bench.github.io/}.

In the field of robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to get a clear understanding of their individual strengths and weaknesses and their applicability in real world robotic scenarios is it important to benchmark and compare their performances not only in a simulation but also on real hardware. The '2nd AI Olympics with RealAIGym' competition was held at the IROS 2024 conference to contribute to this cause and evaluate different controllers according to their ability to solve a dynamic control problem on an underactuated double pendulum system with chaotic dynamics. This paper describes the four different RL methods submitted by the participating teams, presents their performance in the swing-up task on a real double pendulum, measured against various criteria, and discusses their transferability from simulation to real hardware and their robustness to external disturbances.

Machine learning interatomic potentials (MLIPs) are a promising tool to accelerate atomistic simulations and molecular property prediction. The quality of MLIPs strongly depends on the quantity of available training data as well as the quantum chemistry (QC) level of theory used to generate that data. Datasets generated with high-fidelity QC methods, such as coupled cluster, are typically restricted to small molecules and may be missing energy gradients. With this limited quantity of data, it is often difficult to train good MLIP models. We present an ensemble knowledge distillation (EKD) method to improve MLIP accuracy when trained to energy-only datasets. In our EKD approach, first, multiple teacher models are trained to QC energies and then used to generate atomic forces for all configurations in the dataset. Next, a student MLIP is trained to both QC energies and to ensemble-averaged forces generated by the teacher models. We apply this workflow on the ANI-1ccx dataset which consists of organic molecules with configuration energies computed at the coupled cluster level of theory. The resulting student MLIPs achieve new state-of-the-art accuracy on the out-of-sample COMP6 benchmark and improved stability for molecular dynamics simulations. The EKD approach for MLIP is broadly applicable for chemical, biomolecular and materials science simulations.

Teaching and instruction in undergraduate physics courses has largely relied on problem-solving as the standard method to measure student performance [1-6]. Common practice is for "real-time" performance to be measured via multiple-choice or single-solution problems, where canonically correct answers determine the student's knowledge of the core material. Accuracy scores across assignments and examinations, typically coupled with letter grades, act as signals of progress throughout the course as well as final verdicts of student success. While engaging in problem-solving is a useful experience for students in a physics classroom, using the problem solution as a measure of student learning assumes a direct correlation that may not always hold. Problem-solving accuracy as a measurand assumes that students will engage in a learning process involving the core material to obtain the problem solution. Often times, there are alternative strategies for obtaining a problem solution such as rote-memorization of the rules or procedures required for solving similar problem types [7]. In this scenario, students would score very high on exams that contain these problem types; however given a previously unseen problem structure where the same core material is to be applied, the students would struggle. Here, a risk of using problem-solving accuracy as the predominant metric is an inflated sense of confidence in both the instructor and the student that the core material has been learned. It could also pose a risk for confounding variables in research studies that aim to investigate how instructional techniques influence student learning [8-12].

The objective of this study is to design and implement a reinforcement learning (RL) environment using D\&D 5E combat scenarios to challenge smaller RL agents through interaction with a robust adversarial agent controlled by advanced Large Language Models (LLMs) like GPT-4o and LLaMA 3 8B. This research employs Deep Q-Networks (DQN) for the smaller agents, creating a testbed for strategic AI development that also serves as an educational tool by simulating dynamic and unpredictable combat scenarios. We successfully integrated sophisticated language models into the RL framework, enhancing strategic decision-making processes. Our results indicate that while RL agents generally outperform LLM-controlled adversaries in standard metrics, the strategic depth provided by LLMs significantly enhances the overall AI capabilities in this complex, rule-based setting. The novelty of our approach and its implications for mastering intricate environments and developing adaptive strategies are discussed, alongside potential innovations in AI-driven interactive simulations. This paper aims to demonstrate how integrating LLMs can create more robust and adaptable AI systems, providing valuable insights for further research and educational applications.

ChatGPT, powered by a large language model (LLM), has revolutionized everyday human-computer interaction (HCI) since its 2022 release. While now used by millions around the world, a coherent pathway for evaluating the user experience (UX) ChatGPT offers remains missing. In this rapid review (N = 58), I explored how ChatGPT UX has been approached quantitatively so far. I focused on the independent variables (IVs) manipulated, the dependent variables (DVs) measured, and the methods used for measurement. Findings reveal trends, gaps, and emerging consensus in UX assessments. This work offers a first step towards synthesizing existing approaches to measuring ChatGPT UX, urgent trajectories to advance standardization and breadth, and two preliminary frameworks aimed at guiding future research and tool development. I seek to elevate the field of ChatGPT UX by empowering researchers and practitioners in optimizing user interactions with ChatGPT and similar LLM-based systems.

Large Language Models (LLMs) have been widely adopted in commercial code completion engines, significantly enhancing coding efficiency and productivity. However, LLMs may generate code with quality issues that violate coding standards and best practices, such as poor code style and maintainability, even when the code is functionally correct. This necessitates additional effort from developers to improve the code, potentially negating the efficiency gains provided by LLMs. To address this problem, we propose a novel comparative prefix-tuning method for controllable high-quality code generation. Our method introduces a single, property-specific prefix that is prepended to the activations of the LLM, serving as a lightweight alternative to fine-tuning. Unlike existing methods that require training multiple prefixes, our approach trains only one prefix and leverages pairs of high-quality and low-quality code samples, introducing a sequence-level ranking loss to guide the model's training. This comparative approach enables the model to better understand the differences between high-quality and low-quality code, focusing on aspects that impact code quality. Additionally, we design a data construction pipeline to collect and annotate pairs of high-quality and low-quality code, facilitating effective training. Extensive experiments on the Code Llama 7B model demonstrate that our method improves code quality by over 100% in certain task categories, while maintaining functional correctness. We also conduct ablation studies and generalization experiments, confirming the effectiveness of our method's components and its strong generalization capability.