623509 research outputs found
Sort by
NUSense: Robust Soft Optical Tactile Sensor
Get PDFWhile most tactile sensors rely on measuring pressure, insights from continuum mechanics suggest that measuring shear strain provides critical information for tactile sensing. In this work, we introduce an optical tactile sensing principle based on shear strain detection. A silicone rubber layer, dyed with color inks, is used to quantify the shear magnitude of the sensing layer. This principle was validated using the NUSense camera-based tactile sensor. The wide-angle camera captures the elongation of the soft pad under mechanical load, a phenomenon attributed to the Poisson effect. The physical and optical properties of the inked pad are essential and should ideally remain stable over time. We tested the robustness of the sensor by subjecting the outermost layer to multiple load cycles using a robot arm. Additionally, we discussed potential applications of this sensor in force sensing and contact localization.Madina Yergibay and Tleukhan Mussin contributed equally. 6 pages, 6 figure
Exploring Galactic open clusters with Gaia II. Mass Segregation and Mass Function in Fifteen Nearby Open Clusters
Get PDFContext. Mass is the most critical physical parameter in the evolution of a star. Since stars form in clusters their Initial Mass Function (IMF) is decisive in their evolution. Aims. Use Gaia DR3-based stellar masses_mass flame and the stellar members found for fifteen nearby open clusters from Paper I, to estimate their mass segregation and distribution. Methods. For each cluster, the single stars\u27 main sequence was fitted with a moving straight line weighted fit to the Color-Magnitude Diagram, stars brighter than the residuals dispersion were taken as binaries. Single stars masses were obtained from a cubic spline fit to the mass_flame vs. G magnitude data. For binary stars, the individual masses of each component were estimated using simulated-based inference. We used the minimum spanning tree concept to measure the mass segregation of each cluster. From the stellar mass distribution, an estimate of the power-law coefficient that best describes it was used to characterize the IMF. Results. Mass segregation is visible in all the clusters, the older ones have about 50% of their most massive stars segregated, while younger ones extend from about 30% to 55%. The IMF of the studied clusters is well described by a power-law of index 2.09. Conclusions. Significant mass segregation, from one-third to one-half of its most massive population is present in open clusters as young as > 10 Myr. Mass segregation may be strong for only a few of the most massive stars or less intense but extended to a larger fraction of those, it may start as early as 0.20 of the relaxation time of the cluster and progress over time by increasing both the number of the most massive stars affected and their amount of segregation. Older open clusters show evidence of binary disruption as time progresses.Submitted to A&A. 11 pages, 6 figure
Simulating User Agents for Embodied Conversational-AI
Get PDFEmbodied agents designed to assist users with tasks must engage in natural language interactions, interpret instructions, execute actions, and communicate effectively to resolve issues. However, collecting large-scale, diverse datasets of situated human-robot dialogues to train and evaluate such agents is expensive, labor-intensive, and time-consuming. To address this challenge, we propose building a large language model (LLM)-based user agent that can simulate user behavior during interactions with an embodied agent in a virtual environment. Given a user goal (e.g., make breakfast), at each time step, the user agent may observe the robot actions or speak to either intervene with the robot or answer questions. Such a user agent assists in improving the scalability and efficiency of embodied dialogues dataset generation and is critical for enhancing and evaluating the robot\u27s interaction and task completion ability, as well as for research in reinforcement learning using AI feedback. We evaluate our user agent\u27s ability to generate human-like behaviors by comparing its simulated dialogues with the TEACh dataset. We perform three experiments: zero-shot prompting to predict dialogue acts, few-shot prompting, and fine-tuning on the TEACh training subset. Results show the LLM-based user agent achieves an F-measure of 42% with zero-shot prompting and 43.4% with few-shot prompting in mimicking human speaking behavior. Through fine-tuning, performance in deciding when to speak remained stable, while deciding what to say improved from 51.1% to 62.5%. These findings showcase the feasibility of the proposed approach for assessing and enhancing the effectiveness of robot task completion through natural language communication.8 pages, 5 figures, 4 table
ALISE: Accelerating Large Language Model Serving with Speculative Scheduling
Get PDFLarge Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal throughput for inference serving. However, due to the unpredictability of LLM execution, the first-come-first-serve (FCFS) scheduling policy employed by current LLM serving systems suffers from head-of-line (HoL) blocking issues and long job response times.
In this paper, we propose a new efficient LLM inference serving framework, named ALISE. The key design paradigm of ALISE is to leverage a novel speculative scheduler by estimating the execution time for each job and exploiting such prior knowledge to assign appropriate job priority orders, thus minimizing potential queuing delays for heterogeneous workloads. Furthermore, to mitigate the memory overhead of the intermediate key-value (KV) cache, we employ a priority-based adaptive memory management protocol and quantization-based compression techniques. Evaluations demonstrate that in comparison to the state-of-the-art solution vLLM, ALISE improves the throughput of inference serving by up to 1.8x and 2.1x under the same latency constraint on the Alpaca and ShareGPT datasets, respectively.ICCAD 202
Sample-Efficient Agnostic Boosting
Get PDFThe theory of boosting provides a computational framework for aggregating approximate weak learning algorithms, which perform marginally better than a random predictor, into an accurate strong learner. In the realizable case, the success of the boosting approach is underscored by a remarkable fact that the resultant sample complexity matches that of a computationally demanding alternative, namely Empirical Risk Minimization (ERM). This in particular implies that the realizable boosting methodology has the potential to offer computational relief without compromising on sample efficiency.
Despite recent progress, in agnostic boosting, where assumptions on the conditional distribution of labels given feature descriptions are absent, ERM outstrips the agnostic boosting methodology in being quadratically more sample efficient than all known agnostic boosting algorithms. In this paper, we make progress on closing this gap, and give a substantially more sample efficient agnostic boosting algorithm than those known, without compromising on the computational (or oracle) complexity. A key feature of our algorithm is that it leverages the ability to reuse samples across multiple rounds of boosting, while guaranteeing a generalization error strictly better than those obtained by blackbox applications of uniform convergence arguments. We also apply our approach to other previously studied learning problems, including boosting for reinforcement learning, and demonstrate improved results.NeurIPS 2024 camera ready versio
Performance of the MACE-MP-0 potential for calculating viscosity in LiF molten salt
Get PDFWe perform molecular dynamics simulations of molten Lithium Fluoride using the MACE-MP-0 (small) machine learnt interatomic potential and the classical Buckingham and Born-Huggins-Mayer potentials. We find that the MACE-MP-0, out-of-the-box, is able to accurately reproduce the experimental viscosity across the liquid state. Whilst the previous predicted viscosities from classical potentials are under-predicted, which has previously been attributed to a suppressed melting temperature. We find that the melting temperature simulated by MACE-MP-0, simply by heating a crystal structure, is significantly closer to the experimental melting temperature of LiF.7 pages, 5 figure
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
Get PDFMany imitation learning (IL) algorithms use inverse reinforcement learning (IRL) to infer a reward function that aligns with the demonstration. However, the inferred reward functions often fail to capture the underlying task objectives. In this paper, we propose a novel framework for IRL-based IL that prioritizes task alignment over conventional data alignment. Our framework is a semi-supervised approach that leverages expert demonstrations as weak supervision to derive a set of candidate reward functions that align with the task rather than only with the data. It then adopts an adversarial mechanism to train a policy with this set of reward functions to gain a collective validation of the policy\u27s ability to accomplish the task. We provide theoretical insights into this framework\u27s ability to mitigate task-reward misalignment and present a practical implementation. Our experimental results show that our framework outperforms conventional IL baselines in complex and transfer learning scenarios.arXiv admin note: substantial text overlap with arXiv:2306.0173
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
Get PDF3D Gaussian Splatting (3DGS) has become a crucial method for acquiring 3D assets. To protect the copyright of these assets, digital watermarking techniques can be applied to embed ownership information discreetly within 3DGS models. However, existing watermarking methods for meshes, point clouds, and implicit radiance fields cannot be directly applied to 3DGS models, as 3DGS models use explicit 3D Gaussians with distinct structures and do not rely on neural networks. Naively embedding the watermark on a pre-trained 3DGS can cause obvious distortion in rendered images. In our work, we propose an uncertainty-based method that constrains the perturbation of model parameters to achieve invisible watermarking for 3DGS. At the message decoding stage, the copyright messages can be reliably extracted from both 3D Gaussians and 2D rendered images even under various forms of 3D and 2D distortions. We conduct extensive experiments on the Blender, LLFF and MipNeRF-360 datasets to validate the effectiveness of our proposed method, demonstrating state-of-the-art performance on both message decoding accuracy and view synthesis quality
Artificial intelligence to improve clinical coding practice in Scandinavia: a crossover randomized controlled trial
Get PDF\textbf{Trial design} Crossover randomized controlled trial. \textbf{Methods} An AI tool, Easy-ICD, was developed to assist clinical coders and was tested for improving both accuracy and time in a user study in Norway and Sweden. Participants were randomly assigned to two groups, and crossed over between coding complex (longer) texts versus simple (shorter) texts, while using our tool versus not using our tool. \textbf{Results} Based on Mann-Whitney U test, the median coding time difference for complex clinical text sequences was 123 seconds (\emph{P}\textless.001, 95\% CI: 81 to 164), representing a 46\% reduction in median coding time when our tool is used. There was no significant time difference for simpler text sequences. For coding accuracy, the improvement we noted for both complex and simple texts was not significant. \textbf{Conclusions} This study demonstrates the potential of AI to transform common tasks in clinical workflows, with ostensible positive impacts on work efficiencies for complex clinical coding tasks. Further studies within hospital workflows are required before these presumed impacts can be more clearly understood.13 pages, 4 figures, 4 table
Identify Then Recommend: Towards Unsupervised Group Recommendation
Get PDFGroup Recommendation (GR), which aims to recommend items to groups of users, has become a promising and practical direction for recommendation systems. This paper points out two issues of the state-of-the-art GR models. (1) The pre-defined and fixed number of user groups is inadequate for real-time industrial recommendation systems, where the group distribution can shift dynamically. (2) The training schema of existing GR methods is supervised, necessitating expensive user-group and group-item labels, leading to significant annotation costs. To this end, we present a novel unsupervised group recommendation framework named \underline{I}dentify \underline{T}hen \underline{R}ecommend (\underline{ITR}), where it first identifies the user groups in an unsupervised manner even without the pre-defined number of groups, and then two pre-text tasks are designed to conduct self-supervised group recommendation. Concretely, at the group identification stage, we first estimate the adaptive density of each user point, where areas with higher densities are more likely to be recognized as group centers. Then, a heuristic merge-and-split strategy is designed to discover the user groups and decision boundaries. Subsequently, at the self-supervised learning stage, the pull-and-repulsion pre-text task is proposed to optimize the user-group distribution. Besides, the pseudo group recommendation pre-text task is designed to assist the recommendations. Extensive experiments demonstrate the superiority and effectiveness of ITR on both user recommendation (e.g., 22.22\% NDCG@5 ) and group recommendation (e.g., 22.95\% NDCG@5 ). Furthermore, we deploy ITR on the industrial recommender and achieve promising results.26 page