Search

Quantum machine learning (QML), which combines quantum computing with machine learning, is widely believed to hold the potential to outperform traditional machine learning in the era of noisy intermediate-scale quantum (NISQ). As one of the most important types of QML, quantum reinforcement learning (QRL) with parameterized quantum circuits as agents has received extensive attention in the past few years. Various algorithms and techniques have been introduced, demonstrating the effectiveness of QRL in solving some popular benchmark environments such as CartPole, FrozenLake, and MountainCar. However, tackling more complex environments with continuous action spaces and high-dimensional state spaces remains challenging within the existing QRL framework. Here we present PPO-Q, which, by integrating hybrid quantum-classical networks into the actor or critic part of the proximal policy optimization (PPO) algorithm, achieves state-of-the-art performance in a range of complex environments with significantly reduced training parameters. The hybrid quantum-classical networks in the PPO-Q incorporate two additional traditional neural networks to aid the parameterized quantum circuits in managing high-dimensional state encoding and action selection. When evaluated on 8 diverse environments, including four with continuous action space, the PPO-Q achieved comparable performance with the PPO algorithm but with significantly reduced training parameters. Especially, we accomplished the BipedalWalker environment, with a high-dimensional state and continuous action space simultaneously, which has not previously been reported in the QRL. More importantly, the PPO-Q is very friendly to the current NISQ hardware. We successfully trained two representative environments on the real superconducting quantum devices via the Quafu quantum cloud service.

We present QSteed, a quantum compilation system that can be deployed on real quantum computing devices and quantum computing clusters. It is designed to meet the challenges of effectively compiling quantum tasks and managing multiple quantum backends. The system integrates two core components: a quantum compiler and a quantum computing resource virtualization manager, both of which provide standardized interfaces. The resource manager models quantum chips into different abstract layers, including the real quantum processing unit (QPU), the standard QPU (StdQPU), the substructure QPU (SubQPU), and the virtual QPU (VQPU), and stores this information in a quantum computing resource virtualization database, thus realizing the unified management of quantum computing devices. The quantum compiler adopts a modular and extensible design, providing a flexible framework for customizing compilation optimization strategies. It provides hardware-aware compilation algorithms that account for quantum gate noise and qubit coupling structures. By selecting the most suitable computing resources from the VQPU library, the compiler maps quantum tasks to the optimal qubit regions of the target device. We validated the effectiveness of the QSteed on the superconducting devices of the Quafu quantum cloud computing cluster. The quantum computing resource virtualization management technology of QSteed and the flexible and extensible design of its compiler make it possible to achieve unified management and task compilation for backend devices of multiple physical systems such as neutral-atom and ion-trap., Comment: White paper for QSteed, with 7 figures and 18 pages

In this paper, we solve certain Fermat-type partial differential-difference equations for finite order entire functions of several complex variables. These results are significant generalizations of some earlier findings, especially those of Haldar and Ahamed (Entire solutions of several quadratic binomial and trinomial partial differential-difference equations in $\mathbb{C}^2$, Anal. Math. Phys., 12 (2022)). In addition, the results improve the previous results from the situation with two complex variables to the situation with several complex variables. To support our results, we have included several examples., Comment: Pages-24, Latex-V1

The objective of this study is to ascertain the existence and forms of the finite order meromorphic and entire functions of several complex variables satisfying some certain Fermat-type partial differential-difference equations by considering the more general forms of the PDDEs in an open problem on $\mathbb{C}^2$ due to Xu and Wang (Notes on the existence of entire solutions for several partial differential-difference equations, Bull. Iran. Math. Soc., 47, 1477-1489 (2020)). We provide examples to illustrate the results., Comment: 17 Pages, Latex-V1

Simulation offers unique values for both enumeration and extrapolation purposes, and is becoming increasingly important for managing the massive machine learning (ML) clusters and large-scale distributed training jobs. In this paper, we build Echo to tackle three key challenges in large-scale training simulation: (1) tracing the runtime training workloads at each device in an ex-situ fashion so we can use a single device to obtain the actual execution graphs of 1K-GPU training, (2) accurately estimating the collective communication without high overheads of discrete-event based network simulation, and (3) accounting for the interference-induced computation slowdown from overlapping communication and computation kernels on the same device. Echo delivers on average 8% error in training step -- roughly 3x lower than state-of-the-art simulators -- for GPT-175B on a 96-GPU H800 cluster with 3D parallelism on Megatron-LM under 2 minutes.

Tuning effective step sizes is crucial for the stability and efficiency of optimization algorithms. While adaptive coordinate-wise step sizes tuning methods have been explored in first-order methods, second-order methods still lack efficient techniques. Current approaches, including hypergradient descent and cutting plane methods, offer limited improvements or encounter difficulties in second-order contexts. To address these challenges, we introduce a novel Learning-to-Optimize (L2O) model within the Broyden-Fletcher-Goldfarb-Shanno (BFGS) framework, which leverages neural networks to predict optimal coordinate-wise step sizes. Our model integrates a theoretical foundation that establishes conditions for the stability and convergence of these step sizes. Extensive experiments demonstrate that our approach achieves substantial improvements over traditional backtracking line search and hypergradient descent-based methods, offering up to 7$\times$ faster and stable performance across diverse optimization tasks.

Particle-based shape modeling (PSM) is a popular approach to automatically quantify shape variability in populations of anatomies. The PSM family of methods employs optimization to automatically populate a dense set of corresponding particles (as pseudo landmarks) on 3D surfaces to allow subsequent shape analysis. A recent deep learning approach leverages implicit radial basis function representations of shapes to better adapt to the underlying complex geometry of anatomies. Here, we propose an adaptation of this method using a traditional optimization approach that allows more precise control over the desired characteristics of models by leveraging both an eigenshape and a correspondence loss. Furthermore, the proposed approach avoids using a black-box model and allows more freedom for particles to navigate the underlying surfaces, yielding more informative statistical models. We demonstrate the efficacy of the proposed approach to state-of-the-art methods on two real datasets and justify our choice of losses empirically.

By applying some techniques of set-valued and variational analysis, we study solution stability of nonhomogeneous split equality problems and nonhomogeneous split feasibility problems, where the constraint sets need not be convex. Necessary and sufficient conditions for the Lipschitz-likeness of the solution maps of the problems are given and illustrated by concrete examples. The obtained results complement those given in [Huong VT, Xu HK, Yen ND. Stability analysis of split equality and split feasibility problems. arXiv:2410.16856.], where classical split equality problems and split feasibility problems have been considered.

Near-eye display plays an important role in emerging spatial computing systems, providing a distinctive visual effect of virtual-real fusion. However, its application for all-day wear is greatly limited by the bulky structure, energy expenditure, and continuous battery heating. Here, we propose a lightweight holographic near-eye display system that takes advantage of solar energy for self-charging. To achieve the collection of solar energy and near-eye display without crosstalk, holographic optical elements (HOE) are used to diffract sunlight and signal light into a common waveguide. Then, small-area solar cells convert the collected solar energy and power the system. Compact power supply components replace heavy batteries, contributing to the lightweight design. The simple acquisition of solar energy provides the system with sustainable self-charging capability. We believe that the lightweight design and continuous energy input solution will significantly promote the popularity of near-eye display in our daily lives.

In this paper, for the first time in the literature, we study the stability of solutions of two classes of feasibility (i.e., split equality and split feasibility) problems by set-valued and variational analysis techniques. Our idea is to equivalently reformulate the feasibility problems as parametric generalized equations to which set-valued and variational analysis techniques apply. Sufficient conditions, as well as necessary conditions, for the Lipschitz-likeness of the involved solution maps are proved by exploiting special structures of the problems and by using an advanced result of B.S. Mordukhovich [J. Global Optim. 28, 347--362 (2004)]. These conditions stand on a solid interaction among all the input data by means of their dual counterparts, which are transposes of matrices and regular/limiting normal cones to sets. Several examples are presented to illustrate how the obtained results work in practice and also show that the existence of nonzero solution assumption made in the necessity conditions cannot be lifted.

Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often requiring multiple iterations based on synthesis feedback. In contrast, existing compiler-based methods fall short in addressing complex designs. This paper introduces RTLRewriter, an innovative framework that leverages large models to optimize RTL code. A circuit partition pipeline is utilized for fast synthesis and efficient rewriting. A multi-modal program analysis is proposed to incorporate vital visual diagram information as optimization cues. A specialized search engine is designed to identify useful optimization guides, algorithms, and code snippets that enhance the model ability to generate optimized RTL. Additionally, we introduce a Cost-aware Monte Carlo Tree Search (C-MCTS) algorithm for efficient rewriting, managing diverse retrieved contents and steering the rewriting results. Furthermore, a fast verification pipeline is proposed to reduce verification cost. To cater to the needs of both industry and academia, we propose two benchmarking suites: the Large Rewriter Benchmark, targeting complex scenarios with extensive circuit partitioning, optimization trade-offs, and verification challenges, and the Small Rewriter Benchmark, designed for a wider range of scenarios and patterns. Our comparative analysis with established compilers such as Yosys and E-graph demonstrates significant improvements, highlighting the benefits of integrating large models into the early stages of circuit design. We provide our benchmarks at https://github.com/yaoxufeng/RTLRewriter-Bench., Comment: ICCAD2024

In this paper, we first introduce and study the notion of random Chebyshev centers. Further, based on the recently developed theory of stable sets, we introduce the notion of random complete normal structure so that we can prove the two deeper theorems: one of which states that random complete normal structure is equivalent to random normal structure for an $L^0$-convexly compact set in a complete random normed module; the other of which states that if $G$ is an $L^0$-convexly compact subset with random normal structure of a complete random normed module, then every commutative family of nonexpansive mappings from $G$ to $G$ has a common fixed point. We also consider the fixed point problems for isometric mappings in complete random normed modules. Finally, as applications of the fixed point theorems established in random normed modules, when the measurable selection theorems fail to work, we can still prove that a family of strong random nonexpansive operators from $(\Omega,\mathcal{F},P)\times C$ to $C$ has a common random fixed point, where $(\Omega,\mathcal{F},P)$ is a probability space and $C$ is a weakly compact convex subset with normal structure of a Banach space.

The global momentum towards establishing sustainable energy systems has become increasingly prominent. Hydrogen, as a remarkable carbon-free and renewable energy carrier, has been endorsed by 39 countries at COP28 in the UAE, recognizing its essential role in global energy transition and industry decarbonization. Both the European Union (EU) and China are at the forefront of this shift, developing hydrogen strategies to enhance regional energy security and racing for carbon neutrality commitments by 2050 for the EU and 2060 for China. The wide applications of hydrogen across hard-to-abate sectors and the flexibility of decentralized production and storage offer customized solutions utilizing local resources in a self-paced manner. To unveil the trajectory of hydrogen development in China and the EU, this paper proposes a comparative analysis framework employing key factors to investigate hydrogen developments in both economic powerhouses. Beyond country-wise statistics, it dives into representative hydrogen economic areas in China (Inner Mongolia, Capital Economic Circle, Yangtze River Delta) and Europe (Delta Rhine Corridor) for understanding supply and demand, industrial synergy, and policy incentives for local hydrogen industries. The derived implications offer stakeholders an evolving hydrogen landscape across the Eurasian continent and insights for future policy developments facilitating the global green transition., Comment: 19 pages, 18 figures, policy research working paper

This work presents the design and construction of a test-stand for the Split and Delay Line (SDL) at the European X-ray Free Electron Laser (XFEL) in Hamburg, Germany. The advancements in Free Electron Laser technology have now made it possible to investigate ultra-fast dynamics in materials science, biology, chemistry, etc. In the SDL, an incident free electron laser pulse is split into two parts by a beam splitter: one half travels along the upper branch, and the other half travels along the lower branch. These two pulses can either merge again in the collinear mode or travel along different optical paths toward the sample in the inclined mode. This setup achieves a temporal separation of a few femtoseconds between the X-ray pulse pairs, which is crucial for ultra-fast X-ray pump-probe experiments investigating rapid dynamics. This report provides detailed documentation of the mechanical and electronic configuration of the test-stand, vacuum testing, the manufacturing of supporting cables, and the challenges encountered during the project. Finally, the SDL was successfully assembled and initially validated under ultra-high vacuum (UHV) operating conditions., Comment: 45 pages, 26 figures, Internship Report

Large language model (LLM)-based applications consist of both LLM and non-LLM components, each contributing to the end-to-end latency. Despite great efforts to optimize LLM inference, end-to-end workflow optimization has been overlooked. Existing frameworks employ coarse-grained orchestration with task modules, which confines optimizations to within each module and yields suboptimal scheduling decisions. We propose fine-grained end-to-end orchestration, which utilizes task primitives as the basic units and represents each query's workflow as a primitive-level dataflow graph. This explicitly exposes a much larger design space, enables optimizations in parallelization and pipelining across primitives of different modules, and enhances scheduling to improve application-level performance. We build Teola, a novel orchestration framework for LLM-based applications that implements this scheme. Comprehensive experiments show that Teola can achieve up to 2.09x speedup over existing systems across various popular LLM applications.

The capacity of Large Language Models (LLMs) to comprehend and reason over long contexts is pivotal for advancements in diverse fields. Yet, they still stuggle with capturing long-distance dependencies within sequences to deeply understand semantics. To address this issue, we introduce Query-aware Inference for LLMs (Q-LLM), a system designed to process extensive sequences akin to human cognition. By focusing on memory data relevant to a given query, Q-LLM can accurately capture pertinent information within a fixed window size and provide precise answers to queries. It doesn't require extra training and can be seamlessly integrated with any LLMs. Q-LLM using LLaMA3 (QuickLLaMA) can read Harry Potter within 30s and accurately answer the questions. On widely recognized benchmarks, Q-LLM improved by 7.17% compared to the current state-of-the-art on LLaMA3, and by 3.26% on Mistral on the $\infty$-bench. In the Needle-in-a-Haystack and BABILong task, Q-LLM improved upon the current SOTA by 7.0% and 6.1%. Our code can be found in https://github.com/dvlab-research/Q-LLM.

The emergence of Large Language Models (LLMs) has improved the prospects for robotic tasks. However, existing benchmarks are still limited to single tasks with limited generalization capabilities. In this work, we introduce a comprehensive benchmark and an autonomous learning framework, RoboCoder aimed at enhancing the generalization capabilities of robots in complex environments. Unlike traditional methods that focus on single-task learning, our research emphasizes the development of a general-purpose robotic coding algorithm that enables robots to leverage basic skills to tackle increasingly complex tasks. The newly proposed benchmark consists of 80 manually designed tasks across 7 distinct entities, testing the models' ability to learn from minimal initial mastery. Initial testing revealed that even advanced models like GPT-4 could only achieve a 47% pass rate in three-shot scenarios with humanoid entities. To address these limitations, the RoboCoder framework integrates Large Language Models (LLMs) with a dynamic learning system that uses real-time environmental feedback to continuously update and refine action codes. This adaptive method showed a remarkable improvement, achieving a 36% relative improvement. Our codes will be released.

Network function (NF) offloading on SmartNICs has been widely used in modern data centers, offering benefits in host resource saving and programmability. Co-running NFs on the same SmartNICs can cause performance interference due to contention of onboard resources. To meet performance SLAs while ensuring efficient resource management, operators need mechanisms to predict NF performance under such contention. However, existing solutions lack SmartNIC-specific knowledge and exhibit limited traffic awareness, leading to poor accuracy for on-NIC NFs. This paper proposes Yala, a novel performance predictive system for on-NIC NFs. Yala builds upon the key observation that co-located NFs contend for multiple resources, including onboard accelerators and the memory subsystem. It also facilitates traffic awareness according to the behaviors of individual resources to maintain accuracy as the external traffic attributes vary. Evaluation using BlueField-2 SmartNICs shows that Yala improves the prediction accuracy by 78.8% and reduces SLA violations by 92.2% compared to state-of-the-art approaches, and enables new practical usecases., Comment: New version

Nowadays, Information spreads at an unprecedented pace in social media and discerning truth from misinformation and fake news has become an acute societal challenge. Machine learning (ML) models have been employed to identify fake news but are far from perfect with challenging problems like limited accuracy, interpretability, and generalizability. In this paper, we enhance ML-based solutions with linguistics input and we propose LingML, linguistic-informed ML, for fake news detection. We conducted an experimental study with a popular dataset on fake news during the pandemic. The experiment results show that our proposed solution is highly effective. There are fewer than two errors out of every ten attempts with only linguistic input used in ML and the knowledge is highly explainable. When linguistics input is integrated with advanced large-scale ML models for natural language processing, our solution outperforms existing ones with 1.8% average error rate. LingML creates a new path with linguistics to push the frontier of effective and efficient fake news detection. It also sheds light on real-world multi-disciplinary applications requiring both ML and domain expertise to achieve optimal performance., Comment: 7 pages

The increasing demand for Large Language Models (LLMs) across various applications has led to a significant shift in the design of deep learning serving systems. Deploying LLMs, particularly in multi-tenant environments, poses substantial challenges due to their high computational and memory demands. We introduce BlockLLM, a serving system that leverages component sharing among fine-tuned LLM models to provide an efficient and flexible solution for LLM workloads. BlockLLM partitions models into finer-grained blocks, enabling the reuse of model components and independent provisioning to improve computation efficiency. BlockLLM comprises an offline block zoo for storing blocks and an online system to serve requests through chains of blocks. It offers multi-fold flexibilities: (1) Adaptive assembly of blocks on-the-fly through equivalence evaluation among blocks in the zoo; (2) Per-block batch size configuration and best-effort KV cache coordination at the individual block level; (3) Speculative execution and locality-aware block placement to reduce communication costs from dynamic block resource allocation. Our evaluation shows that BlockLLM reduces memory and storage footprints and improves computational efficiency, outperforming existing serving approach in 95%ile latency and GPU utilization by 33.5% and 20.1%, respectively, with minimal impact on accuracy

We present the first experimental observation of quantized Klein tunneling in a bounded Dirac system, implemented by a dimer chain of dielectric microwave resonators. Both the unusual quantized levels and corresponding spinor states hybridized from distinct particle and hole wavefunctions are measured. All observations are in quantitative agreement with the hitherto-untested prediction of Dirac equation. Our results make an important step to realize and understand the particle-hole physics of Klein tunneling in bounded Dirac systems, and also shed light on potential applications for manipulating particle-hole hybridized spinor waves.

Thanks to advances in deep learning techniques, Human Pose Estimation (HPE) has achieved significant progress in natural scenarios. However, these models perform poorly in artificial scenarios such as painting and sculpture due to the domain gap, constraining the development of virtual reality and augmented reality. With the growth of model size, retraining the whole model on both natural and artificial data is computationally expensive and inefficient. Our research aims to bridge the domain gap between natural and artificial scenarios with efficient tuning strategies. Leveraging the potential of language models, we enhance the adaptability of traditional pose estimation models across diverse scenarios with a novel framework called VLPose. VLPose leverages the synergy between language and vision to extend the generalization and robustness of pose estimation models beyond the traditional domains. Our approach has demonstrated improvements of 2.26% and 3.74% on HumanArt and MSCOCO, respectively, compared to state-of-the-art tuning strategies.