Search

With the recent rise of Large Language Models (LLMs), Vision-Language Models (VLMs), and other general foundation models, there is growing potential for multimodal, multi-task embodied agents that can operate in diverse environments given only natural language as input. One such application area is indoor navigation using natural language instructions. However, despite recent progress, this problem remains challenging due to the spatial reasoning and semantic understanding required, particularly in arbitrary scenes that may contain many objects belonging to fine-grained classes. To address this challenge, we curate the largest real-world dataset for Vision and Language-guided Action in 3D Scenes (VLA-3D), consisting of over 11.5K scanned 3D indoor rooms from existing datasets, 23.5M heuristically generated semantic relations between objects, and 9.7M synthetically generated referential statements. Our dataset consists of processed 3D point clouds, semantic object and room annotations, scene graphs, navigable free space annotations, and referential language statements that specifically focus on view-independent spatial relations for disambiguating objects. The goal of these features is to aid the downstream task of navigation, especially on real-world systems where some level of robustness must be guaranteed in an open world of changing scenes and imperfect language. We benchmark our dataset with current state-of-the-art models to obtain a performance baseline. All code to generate and visualize the dataset is publicly released, see https://github.com/HaochenZ11/VLA-3D. With the release of this dataset, we hope to provide a resource for progress in semantic 3D scene understanding that is robust to changes and one which will aid the development of interactive indoor navigation systems., Comment: Accepted and presented at the 1st Workshop on Semantic Reasoning and Goal Understanding in Robotics (SemRob), Robotics Science and Systems Conference (RSS 2024)

Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the "life" of an RL agent is modeled as a stream of tasks drawn from a task distribution. We propose EPIC (\underline{E}mpirical \underline{P}AC-Bayes that \underline{I}mproves \underline{C}ontinuously), a novel algorithm designed for lifelong RL using PAC-Bayes theory. EPIC learns a shared policy distribution, referred to as the \textit{world policy}, which enables rapid adaptation to new tasks while retaining valuable knowledge from previous experiences. Our theoretical analysis establishes a relationship between the algorithm's generalization performance and the number of prior tasks preserved in memory. We also derive the sample complexity of EPIC in terms of RL regret. Extensive experiments on a variety of environments demonstrate that EPIC significantly outperforms existing methods in lifelong RL, offering both theoretical guarantees and practical efficacy through the use of the world policy.

We study the gap-dependent bounds of two important algorithms for on-policy Q-learning for finite-horizon episodic tabular Markov Decision Processes (MDPs): UCB-Advantage (Zhang et al. 2020) and Q-EarlySettled-Advantage (Li et al. 2021). UCB-Advantage and Q-EarlySettled-Advantage improve upon the results based on Hoeffding-type bonuses and achieve the almost optimal $\sqrt{T}$-type regret bound in the worst-case scenario, where $T$ is the total number of steps. However, the benign structures of the MDPs such as a strictly positive suboptimality gap can significantly improve the regret. While gap-dependent regret bounds have been obtained for Q-learning with Hoeffding-type bonuses, it remains an open question to establish gap-dependent regret bounds for Q-learning using variance estimators in their bonuses and reference-advantage decomposition for variance reduction. We develop a novel error decomposition framework to prove gap-dependent regret bounds of UCB-Advantage and Q-EarlySettled-Advantage that are logarithmic in $T$ and improve upon existing ones for Q-learning algorithms. Moreover, we establish the gap-dependent bound for the policy switching cost of UCB-Advantage and improve that under the worst-case MDPs. To our knowledge, this paper presents the first gap-dependent regret analysis for Q-learning using variance estimators and reference-advantage decomposition and also provides the first gap-dependent analysis on policy switching cost for Q-learning.

In this paper, we consider model-free federated reinforcement learning for tabular episodic Markov decision processes. Under the coordination of a central server, multiple agents collaboratively explore the environment and learn an optimal policy without sharing their raw data. Despite recent advances in federated Q-learning algorithms achieving near-linear regret speedup with low communication cost, existing algorithms only attain suboptimal regrets compared to the information bound. We propose a novel model-free federated Q-learning algorithm, termed FedQ-Advantage. Our algorithm leverages reference-advantage decomposition for variance reduction and operates under two distinct mechanisms: synchronization between the agents and the server, and policy update, both triggered by events. We prove that our algorithm not only requires a lower logarithmic communication cost but also achieves an almost optimal regret, reaching the information bound up to a logarithmic factor and near-linear regret speedup compared to its single-agent counterpart when the time horizon is sufficiently large.

This paper presents a novel method for estimating the temperature of magnetic nanoparticles (MNPs) based on AC magnetization harmonics of MNPs dominated by Brownian relaxation. The difference in the AC magnetization response and magnetization harmonic between the Fokker-Planck equation and the Langevin function was analyzed, and we studied the relationship between the magnetization harmonic and the key factors, such as Brownian relaxation time, temperature, magnetic field strength, core size and hydrodynamic size of MNPs, excitation frequency, and so on. We proposed a compensation function for AC magnetization harmonic with consideration of the key factors and the difference between the Fokker-Planck equation and the Langevin function. Then a temperature estimation model based on the compensation function and the Langevin function was established. By employing the least squares algorithm, the temperature was successfully calculated. The experimental results show that the temperature error is less than 0.035 K in the temperature range from 310 K to 320 K. The temperature estimation model is expected to improve the performance of the magnetic nanoparticle thermometer and be applied to magnetic nanoparticle-mediated hyperthermia.

This paper explores the utilization of LLMs for data preprocessing (DP), a crucial step in the data mining pipeline that transforms raw data into a clean format conducive to easy processing. Whereas the use of LLMs has sparked interest in devising universal solutions to DP, recent initiatives in this domain typically rely on GPT APIs, raising inevitable data breach concerns. Unlike these approaches, we consider instruction-tuning local LLMs (7 -- 13B models) as universal DP task solvers that operate on a local, single, and low-priced GPU, ensuring data security and enabling further customization. We select a collection of datasets across four representative DP tasks and construct instruction tuning data using data configuration, knowledge injection, and reasoning data distillation techniques tailored to DP. By tuning Mistral-7B, Llama 3-8B, and OpenOrca-Platypus2-13B, our models, namely, Jellyfish-7B/8B/13B, deliver competitiveness compared to GPT-3.5/4 models and strong generalizability to unseen tasks while barely compromising the base models' abilities in NLP tasks. Meanwhile, Jellyfish offers enhanced reasoning capabilities compared to GPT-3.5. Our models are available at: https://huggingface.co/NECOUDBFM/Jellyfish . Our instruction dataset is available at: https://huggingface.co/datasets/NECOUDBFM/Jellyfish-Instruct ., Comment: Accepted by EMNLP 2024, a.k.a. "Jellyfish: Instruction-Tuning Local Large Language Models for Data Preprocessing''

Decentralized exchanges (DEXs) are a cornerstone of decentralized finance (DeFi), allowing users to trade cryptocurrencies without the need for third-party authorization. Investors are incentivized to deposit assets into liquidity pools, against which users can trade directly, while paying fees to liquidity providers (LPs). However, a number of unresolved issues related to capital efficiency and market risk hinder DeFi's further development. Uniswap V3, a leading and groundbreaking DEX project, addresses capital efficiency by enabling LPs to concentrate their liquidity within specific price ranges for deposited assets. Nevertheless, this approach exacerbates market risk, as LPs earn trading fees only when asset prices are within these predetermined brackets. To mitigate this issue, this paper introduces a deep reinforcement learning (DRL) solution designed to adaptively adjust these price ranges, maximizing profits and mitigating market risks. Our approach also neutralizes price-change risks by hedging the liquidity position through a rebalancing portfolio in a centralized futures exchange. The DRL policy aims to optimize trading fees earned by LPs against associated costs, such as gas fees and hedging expenses, which is referred to as loss-versus-rebalancing (LVR). Using simulations with a profit-and-loss (PnL) benchmark, our method demonstrates superior performance in ETH/USDC and ETH/USDT pools compared to existing baselines. We believe that this strategy not only offers investors a valuable asset management tool but also introduces a new incentive mechanism for DEX designers., Comment: 15 pages, 5 figures, 9 tables, submitted to Financial Cryptography and Data Security 2024

Large Language Models (LLMs), typified by OpenAI's GPT, have marked a significant advancement in artificial intelligence. Trained on vast amounts of text data, LLMs are capable of understanding and generating human-like text across a diverse range of topics. This study expands on the applications of LLMs, exploring their potential in data preprocessing, a critical stage in data mining and analytics applications. Aiming at tabular data, we delve into the applicability of state-of-the-art LLMs such as GPT-4 and GPT-4o for a series of preprocessing tasks, including error detection, data imputation, schema matching, and entity matching. Alongside showcasing the inherent capabilities of LLMs, we highlight their limitations, particularly in terms of computational expense and inefficiency. We propose an LLM-based framework for data preprocessing, which integrates cutting-edge prompt engineering techniques, coupled with traditional methods like contextualization and feature selection, to improve the performance and efficiency of these models. The effectiveness of LLMs in data preprocessing is evaluated through an experimental study spanning a variety of public datasets. GPT-4 emerged as a standout, achieving 100\% accuracy or F1 score on 4 of these datasets, suggesting LLMs' immense potential in these tasks. Despite certain limitations, our study underscores the promise of LLMs in this domain and anticipates future developments to overcome current hurdles., Comment: TaDA 2024 (workshop in conjunction with VLDB 2024)

Hybrid organic-inorganic metal halide perovskites are emerging materials in photovoltaics, whose bandgap is one of the most crucial parameters governing their light harvesting performance. Here we present the temperature and photocarrier density dependence of the bandgap in two phase-stabilized perovskite thin films (MA0.3FA0.7PbI3 and MA0.3FA0.7Pb0.5Sn0.5I3) using photoluminescence and absorption spectroscopy. Contrasting bandgap shifts with temperature are observed between the two perovskites. Using X-ray diffraction and in situ high-pressure photoluminescence spectroscopy, we show that thermal expansion plays only a minor role in the large bandgap blueshift, which is attributed to the enhanced structural stability of our samples. Our first-principles calculations further demonstrate the significant impact of thermally induced lattice distortions on the bandgap widening. We propose that the anomalous trends are caused by the competition between static and dynamic distortions. Additionally, both the bandgap renormalization and band filling effects are directly observed for the first time in fluence-dependent photoluminescence measurements and are employed to estimate the exciton effective mass. Our results provide new insights into the basic understanding of thermal and charge-accumulation effects on the band structure of hybrid perovskite thin films.

Metal halide perovskites make up a promising class of materials for semiconductor spintronics. Here we report a systematic investigation of coherent spin precession, spin dephasing and spin relaxation of electrons and holes in two hybrid organic-inorganic perovskites MA0.3FA0.7PbI3 and MA0.3FA0.7Pb0.5Sn0.5I3 using time-resolved Faraday rotation spectroscopy. With applied in-plane magnetic fields, we observe robust Larmor spin precession of electrons and holes that persists for hundreds of picoseconds. The spin dephasing and relaxation processes are likely to be sensitive to the defect levels. Temperature-dependent measurements give further insights into the spin relaxation channels. The extracted electron Land\'e g-factors (3.75 and 4.36) are the biggest among the reported values in inorganic or hybrid perovskites. Both the electron and hole g-factors shift dramatically with temperature, which we propose to originate from thermal lattice vibration effects on the band structure. These results lay the foundation for further design and use of lead- and tin-based perovskites for spintronic applications.

Computational Pathology CPath is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main objective for CPath is to develop infrastructure and workflows of digital diagnostics as an assistive CAD system for clinical pathology, facilitating transformational changes in the diagnosis and treatment of cancer that are mainly address by CPath tools. With evergrowing developments in deep learning and computer vision algorithms, and the ease of the data flow from digital pathology, currently CPath is witnessing a paradigm shift. Despite the sheer volume of engineering and scientific works being introduced for cancer image analysis, there is still a considerable gap of adopting and integrating these algorithms in clinical practice. This raises a significant question regarding the direction and trends that are undertaken in CPath. In this article we provide a comprehensive review of more than 800 papers to address the challenges faced in problem design all-the-way to the application and implementation viewpoints. We have catalogued each paper into a model-card by examining the key works and challenges faced to layout the current landscape in CPath. We hope this helps the community to locate relevant works and facilitate understanding of the field's future directions. In a nutshell, we oversee the CPath developments in cycle of stages which are required to be cohesively linked together to address the challenges associated with such multidisciplinary science. We overview this cycle from different perspectives of data-centric, model-centric, and application-centric problems. We finally sketch remaining challenges and provide directions for future technical developments and clinical integration of CPath (https://github.com/AtlasAnalyticsLab/CPath_Survey)., Comment: Accepted in Elsevier Journal of Pathology Informatics (JPI) 2024

We show that the path-integral of conformal field theories in $D$ dimensions (CFT$_D$) can be constructed by solving for eigenstates of an RG operator following from the Turaev-Viro formulation of a topological field theory in $D+1$ dimensions (TQFT$_{D+1}$), explicitly realising the holographic sandwich relation between a symmetric theory and a TQFT. Generically, exact eigenstates corresponding to symmetric-TQFT$_D$ follow from Frobenius algebra in the TQFT$_{D+1}$. For $D=2$, we constructed eigenstates that produce 2D rational CFT path-integral exactly, which, curiously connects a continuous field theoretic path-integral with the Turaev-Viro state sum. We also devise and illustrate numerical methods for $D=2,3$ to search for CFT$_D$ as phase transition points between symmetric TQFT$_D$. Finally since the RG operator is in fact an exact analytic holographic tensor network, we compute ``bulk-boundary'' correlator and compare with the AdS/CFT dictionary at $D=2$. Promisingly, they are numerically compatible given our accuracy, although further works will be needed to explore the precise connection to the AdS/CFT correspondence., Comment: 27 pages, 46 figures

The cryogenic performance of GaN-based HEMTs (high-electron-mobility transistors) is systematically investigated by the direct current (DC) and low-frequency noise (LFN) characteristics within the temperature (T) range from 300 K to 4.2 K. The important electrical merits of the device, including drain saturation current (IDsat), on-resistance (RON), transductance, subthreshold swing (SS), gate leakage current, and Schottky barrier height, are comprehensively characterized and their temperature-dependent behavior was statistically analyzed. In addition, the LFN of the device shows an evident behavior of 1/f noise from 10 Hz to 10 kHz in the measured temperature range and can be significantly reduced at cryogenic temperature. These results are of great importance to motivate further studies into the GaN-based cryo-devices and systems., Comment: This paper was submitted without all the corresponding authors' agreements

Distribution system (DS) restoration after natural disasters often faces the challenge of communication failures to feeder automation (FA) facilities, resulting in prolonged load pick-up process. This letter discusses the utilization of drone small cells for wireless communication recovery of FA, and proposes an integrated DS restoration strategy with communication recovery. Demonstrative case studies are conducted to validate the proposed model, and its advantages are illustrated by comparing to benchmark strategies.

Learning through tests is a broadly used methodology in human learning and shows great effectiveness in improving learning outcome: a sequence of tests are made with increasing levels of difficulty; the learner takes these tests to identify his/her weak points in learning and continuously addresses these weak points to successfully pass these tests. We are interested in investigating whether this powerful learning technique can be borrowed from humans to improve the learning abilities of machines. We propose a novel learning approach called learning by passing tests (LPT). In our approach, a tester model creates increasingly more-difficult tests to evaluate a learner model. The learner tries to continuously improve its learning ability so that it can successfully pass however difficult tests created by the tester. We propose a multi-level optimization framework to formulate LPT, where the tester learns to create difficult and meaningful tests and the learner learns to pass these tests. We develop an efficient algorithm to solve the LPT problem. Our method is applied for neural architecture search and achieves significant improvement over state-of-the-art baselines on CIFAR-100, CIFAR-10, and ImageNet., Comment: arXiv admin note: substantial text overlap with arXiv:2012.04863, arXiv:2012.12502, arXiv:2012.12899