arXiv subjects

Yi Zhang

Publications and source records attributed to Yi Zhang.

At least 595 records · Page 33Linked to original sources

arXiv2024

See Further When Clear: Curriculum Consistency Model

Significant advances have been made in the sampling efficiency of diffusion models and flow matching models, driven by Consistency Distillation (CD), which trains a student model to mimic the output of a teacher model at a later timestep. However, we found that the learning complexity of the student model varies significantly across different timesteps, leading to suboptimal performance in CD.To address this issue, we propose the Curriculum Consistency Model (CCM), which stabilizes and balances the learning complexity across timesteps. Specifically, we regard the distillation process at each timestep as a curriculum and introduce a metric based on Peak Signal-to-Noise Ratio (PSNR) to quantify the learning complexity of this curriculum, then ensure that the curriculum maintains consistent learning complexity across different timesteps by having the teacher model iterate more steps when the noise intensity is low. Our method achieves competitive single-step sampling Fréchet Inception Distance (FID) scores of 1.64 on CIFAR-10 and 2.18 on ImageNet 64x64.Moreover, we have extended our method to large-scale text-to-image models and confirmed that it generalizes well to both diffusion models (Stable Diffusion XL) and flow matching models (Stable Diffusion 3). The generated samples demonstrate improved image-text alignment and semantic structure, since CCM enlarges the distillation step at large timesteps and reduces the accumulated error.

cs.CV↗

arXiv2024

Towards Effective GenAI Multi-Agent Collaboration: Design and Evaluation for Enterprise Applications

AI agents powered by large language models (LLMs) have shown strong capabilities in problem solving. Through combining many intelligent agents, multi-agent collaboration has emerged as a promising approach to tackle complex, multi-faceted problems that exceed the capabilities of single AI agents. However, designing the collaboration protocols and evaluating the effectiveness of these systems remains a significant challenge, especially for enterprise applications. This report addresses these challenges by presenting a comprehensive evaluation of coordination and routing capabilities in a novel multi-agent collaboration framework. We evaluate two key operational modes: (1) a coordination mode enabling complex task completion through parallel communication and payload referencing, and (2) a routing mode for efficient message forwarding between agents. We benchmark on a set of handcrafted scenarios from three enterprise domains, which are publicly released with the report. For coordination capabilities, we demonstrate the effectiveness of inter-agent communication and payload referencing mechanisms, achieving end-to-end goal success rates of 90%. Our analysis yields several key findings: multi-agent collaboration enhances goal success rates by up to 70% compared to single-agent approaches in our benchmarks; payload referencing improves performance on code-intensive tasks by 23%; latency can be substantially reduced with a routing mechanism that selectively bypasses agent orchestration. These findings offer valuable guidance for enterprise deployments of multi-agent systems and advance the development of scalable, efficient multi-agent collaboration frameworks.

cs.CL↗

arXiv2024

Towards Fault Tolerance in Multi-Agent Reinforcement Learning

Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space created by unexpected faults. Second, transitions recorded before and after faults in the replay buffer affect training unevenly, leading to a sample imbalance problem. To overcome these challenges, this paper enhances the fault tolerance of MARL by combining optimized model architecture with a tailored training data sampling strategy. Specifically, an attention mechanism is incorporated into the actor and critic networks to automatically detect faults and dynamically regulate the attention given to faulty agents. Additionally, a prioritization mechanism is introduced to selectively sample transitions critical to current training needs. To further support research in this area, we design and open-source a highly decoupled code platform for fault-tolerant MARL, aimed at improving the efficiency of studying related problems. Experimental results demonstrate the effectiveness of our method in handling various types of faults, faults occurring in any agent, and faults arising at random times.

cs.LG↗

arXiv2024

Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries

Text-to-SQL systems (also known as NL-to-SQL systems) have become an increasingly popular solution for bridging the gap between user capabilities and SQL-based data access. These systems translate user requests in natural language to valid SQL statements for a specific database. Recent Text-to-SQL systems have benefited from the rapid improvement of transformer-based language models. However, while Text-to-SQL systems that incorporate such models continuously reach new high scores on -- often synthetic -- benchmark datasets, a systematic exploration of their robustness towards different data models in a real-world, realistic scenario is notably missing. This paper provides the first in-depth evaluation of the data model robustness of Text-to-SQL systems in practice based on a multi-year international project focused on Text-to-SQL interfaces. Our evaluation is based on a real-world deployment of FootballDB, a system that was deployed over a 9 month period in the context of the FIFA World Cup 2022, during which about 6K natural language questions were asked and executed. All of our data is based on real user questions that were asked live to the system. We manually labeled and translated a subset of these questions for three different data models. For each data model, we explore the performance of representative Text-to-SQL systems and language models. We further quantify the impact of training data size, pre-, and post-processing steps as well as language model inference time. Our comprehensive evaluation sheds light on the design choices of real-world Text-to-SQL systems and their impact on moving from research prototypes to real deployments. Last, we provide a new benchmark dataset to the community, which is the first to enable the evaluation of different data models for the same dataset and is substantially more challenging than most previous datasets in terms of query complexity.

cs.DB↗

arXiv2024

The hot circumgalactic medium in the eROSITA All-Sky Survey III. Star-forming and quiescent galaxies

The circumgalactic medium (CGM), as the gas repository for star formation, might contain the answer to the mysterious galaxy quenching and bimodal galaxy population origin. We measured the X-ray emission of the hot CGM around star-forming and quiescent galaxies. We detect extended X-ray emission from the hot CGM around star-forming galaxies with $\log(M_*/M_\odot)>11.0$ and quiescent galaxies with $\log(M_*/M_\odot)>10.5$, extending out to $R_{\rm 500c}$. $L_{\rm X, CGM}$ of star-forming galaxies with median stellar masses $\log(M_{\rm *,med}/M_\odot) = 10.7, 11.1, 11.3$ are approximately $0.8\,, 2.3\,, 4.0 \times 10^{40}\,\rm erg/s$, while for quiescent galaxies with $\log(M_{\rm *,med}/M_\odot) = 10.8, 11.1, 11.4$, they are $1.1\,, 6.2\,, 30 \times 10^{40}\,\rm erg/s$. Notably, quiescent galaxies with $\log(M_{\rm *,med}/M_\odot) > 11.0$ exhibit brighter hot CGM than their star-forming counterparts. In halo mass bins, we detect similar X-ray emission around star-forming and quiescent galaxies with $\log(M_{\rm 200m}/M_\odot) > 12.5$, suggesting that galaxies in the same mass dark matter halos host equally bright hot CGM. We emphasize the observed $L_{\rm X, CGM} - M_{\rm 500c}$ relations of star-forming and quiescent galaxies are sensitive to the stellar-to-halo mass relation (SHMR). A comparison with cosmological hydrodynamical simulations (EAGLE, TNG100, and SIMBA) reveals varying degrees of agreement, contingent on the simulation and the specific stellar or halo mass ranges considered. Either selected in stellar mass or halo mass, the star-forming galaxies do not host brighter stacked X-ray emission from the hot CGM than their quiescent counterparts at the same mass range. The result provides useful constraints on the extent of feedback's impacts as a mechanism for quenching star formation as implemented in current cosmological simulations.

astro-ph.GA↗

arXiv2024

Look a Group at Once: Multi-Slide Modeling for Survival Prediction

Survival prediction is a critical task in pathology. In clinical practice, pathologists often examine multiple cases, leveraging a broader spectrum of cancer phenotypes to enhance pathological assessment. Despite significant advancements in deep learning, current solutions typically model each slide as a sample, struggling to effectively capture comparable and slide-agnostic pathological features. In this paper, we introduce GroupMIL, a novel framework inspired by the clinical practice of collective analysis, which models multiple slides as a single sample and organizes groups of patches and slides sequentially to capture cross-slide prognostic features. We also present GPAMamba, a model designed to facilitate intra- and inter-slide feature interactions, effectively capturing local micro-environmental characteristics within slide-level graphs while uncovering essential prognostic patterns across an extended patch sequence within the group framework. Furthermore, we develop a dual-head predictor that delivers comprehensive survival risk and probability assessments for each patient. Extensive empirical evaluations demonstrate that our model significantly outperforms state-of-the-art approaches across five datasets from The Cancer Genome Atlas.

cs.CV↗

arXiv2024

SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark

Electronic health records (EHRs) are stored in various database systems with different database models on heterogeneous storage architectures, such as relational databases, document stores, or graph databases. These different database models have a big impact on query complexity and performance. While this has been a known fact in database research, its implications for the growing number of Text-to-Query systems have surprisingly not been investigated so far. In this paper, we present SM3-Text-to-Query, the first multi-model medical Text-to-Query benchmark based on synthetic patient data from Synthea, following the SNOMED-CT taxonomy -- a widely used knowledge graph ontology covering medical terminology. SM3-Text-to-Query provides data representations for relational databases (PostgreSQL), document stores (MongoDB), and graph databases (Neo4j and GraphDB (RDF)), allowing the evaluation across four popular query languages, namely SQL, MQL, Cypher, and SPARQL. We systematically and manually develop 408 template questions, which we augment to construct a benchmark of 10K diverse natural language question/query pairs for these four query languages (40K pairs overall). On our dataset, we evaluate several common in-context-learning (ICL) approaches for a set of representative closed and open-source LLMs. Our evaluation sheds light on the trade-offs between database models and query languages for different ICL strategies and LLMs. Last, SM3-Text-to-Query is easily extendable to additional query languages or real, standard-based patient databases.

cs.DB↗

arXiv2024

Asymptotics of Sum of Heavy-tailed Risks with Copulas

We study the tail asymptotics of the sum of two heavy-tailed random variables. The dependence structure is modeled by copulas with the so-called tail order property. Examples are presented to illustrate the approach. Further for each example we apply the main results to obtain the asymptotic expansions for Value-at-Risk of aggregate risk.

q-fin.RM↗

arXiv2024

Piecewise Linearity of Min-Norm Solution Map of a Nonconvexly Regularized Convex Sparse Model

It is well known that the minimum $\ell_2$-norm solution of the convex LASSO model, say $\mathbf{x}_{\star}$, is a continuous piecewise linear function of the regularization parameter $λ$, and its signed sparsity pattern is constant within each linear piece. The current study is an extension of this classic result, proving that the aforementioned properties extend to the min-norm solution map $\mathbf{x}_{\star}(\mathbf{y},λ)$, where $\mathbf{y}$ is the observed signal, for a generalization of LASSO termed the scaled generalized minimax concave (sGMC) model. The sGMC model adopts a nonconvex debiased variant of the $\ell_1$-norm as sparse regularizer, but its objective function is overall-convex. Based on the geometric properties of $\mathbf{x}_{\star}(\mathbf{y},λ)$, we propose an extension of the least angle regression (LARS) algorithm, which iteratively computes the closed-form expression of $\mathbf{x}_{\star}(\mathbf{y},λ)$ in each linear zone. Under suitable conditions, the proposed algorithm provably obtains the whole solution map $\mathbf{x}_{\star}(\mathbf{y},λ)$ within finite iterations. Notably, our proof techniques for establishing continuity and piecewise linearity of $\mathbf{x}_{\star}(\mathbf{y},λ)$ are novel, and they lead to two side contributions: (a) our proofs establish continuity of the sGMC solution set as a set-valued mapping of $(\mathbf{y},λ)$; (b) to prove piecewise linearity and piecewise constant sparsity pattern of $\mathbf{x}_{\star}(\mathbf{y},λ)$, we do not require any assumption that previous work relies on (whereas to prove some additional properties of $\mathbf{x}_{\star}(\mathbf{y},λ)$, we use a different set of assumptions from previous work).

math.OC↗

arXiv2024

Understanding Fermionic Generalized Symmetries

We explore new aspects of internal fermionic shifting symmetries, present in physical systems such as free Dirac spinors and p-form tensor-spinor fields. We propose a novel procedure to gauge these global symmetries, which also introduces a new Stückelberg mechanism to give a mass to free fermionic fields. Furthermore, we find new magnetic fermionic symmetries in these physical systems whose charged objects are disorder operators. For the case of a Dirac spinor, we discuss an dual description, where the magnetic symmetry acts on the holonomies of a dual 2-form tensor-spinor. Further generalizations such as higher-group-like structures are also discussed.

hep-th↗

arXiv2024

Detector integration at HEPS: a systematic, efficient and high-performance approach

At least 25 kinds of detector-like devices need to be integrated in Phase I of the High Energy Photon Source (HEPS), and the work needs to be carefully planned to maximise productivity with highly limited human resources. After a systematic analysis on the actual work involved in detector integration, a separation of concerns between collaborating groups of personnel is established to minimise the duplication of efforts. To facilitate software development for detector integration, the ADGenICam library, which abstracts repeated code in EPICS modules for cameras, is extended to support a much wider range of detectors. An increasingly considerable fraction of detectors, both inside and outside HEPS, offer performance that exceed capabilities of the areaDetector framework in EPICS. Given this background, areaDetector's limitations in performance and architecture are analysed, and a QueueIOC -based framework that overcomes these limitations is introduced. A simple, flexible ZeroMQ-based protocol is used for data transport in this framework, while RDMA transport and multi-node readout will be explored for higher data throughputs. By calling C/C++ libraries from within Python, the performance of the former and the expressiveness of the latter can coexist nicely; the expressiveness allows for much higher efficiency in the implementation and use of integration modules functionally comparable to their EPICS counterparts.

physics.ins-det↗

arXiv2024

A versatile framework for attitude tuning of beamlines at advanced light sources

Aside from regular beamline experiments at light sources, the preparation steps before these experiments are also worth systematic consideration in terms of automation; a representative category in these steps is attitude tuning, which typically appears in names like beam focusing, sample alignment etc. With the goal of saving time and manpower in both writing and using in mind, a Mamba-based attitude-tuning framework is created. It supports flexible input/output ports, easy integration of diverse evaluation functions, and free selection of optimisation algorithms; with the help from Mamba's infrastructure, machine learning (ML) and artificial intelligence (AI) technologies can also be readily integrated. The tuning of a polycapillary lens and of an X-ray emission spectrometer are given as examples for the general use of this framework, featuring powerful command-line interfaces (CLIs) and friendly graphical user interfaces (GUIs) that allow comfortable human-in-the-loop control. The tuning of a Raman spectrometer demonstrates more specialised use of the framework with customised optimisation algorithms. With similar applications in mind, our framework is estimated to be capable of fulfilling a majority of attitude-tuning needs. Also reported is a virtual-beamline mechanism based on easily customisable simulated detectors and motors, which facilitates both testing for developers and training for users.

physics.ins-det↗

arXiv2024

Symplectic Discretization Approach for Developing New Proximal Point Algorithm

The rapid advancements in high-dimensional statistics and machine learning have increased the use of first-order methods. Many of these methods can be regarded as instances of the proximal point algorithm. Given the importance of the proximal point algorithm, there has been growing interest in developing its accelerated variants. However, some existing accelerated proximal point algorithms exhibit oscillatory behavior, which can impede their numerical convergence rate. In this paper, we first introduce an ODE system and demonstrate its $ o(1/t^2) $ convergence rate and weak convergence property. Next, we apply the Symplectic Euler Method to discretize the ODE and obtain a new accelerated proximal point algorithm, which we call the Symplectic Proximal Point Algorithm. The reason for using the Symplectic Euler Method is its ability to preserve the geometric structure of the ODEs. Theoretically, we demonstrate that the Symplectic Proximal Point Algorithm achieves an $ o(1/k^2) $ convergence rate and that the sequences generated by our method converge weakly to the solution set. Practically, our numerical experiments illustrate that the Symplectic Proximal Point Algorithm significantly reduces oscillatory behavior, leading to improved long-time behavior and faster numerical convergence rate.

math.OC↗

arXiv2024

CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models

Large language models (LLMs) have obtained promising results in mathematical reasoning, which is a foundational skill for human intelligence. Most previous studies focus on improving and measuring the performance of LLMs based on textual math reasoning datasets (e.g., MATH, GSM8K). Recently, a few researchers have released English multimodal math datasets (e.g., MATHVISTA and MATH-V) to evaluate the effectiveness of large multimodal models (LMMs). In this paper, we release a Chinese multimodal math (CMM-Math) dataset, including benchmark and training parts, to evaluate and enhance the mathematical reasoning of LMMs. CMM-Math contains over 28,000 high-quality samples, featuring a variety of problem types (e.g., multiple-choice, fill-in-the-blank, and so on) with detailed solutions across 12 grade levels from elementary to high school in China. Specifically, the visual context may be present in the questions or opinions, which makes this dataset more challenging. Through comprehensive analysis, we discover that state-of-the-art LMMs on the CMM-Math dataset face challenges, emphasizing the necessity for further improvements in LMM development. We also propose a Multimodal Mathematical LMM (Math-LMM) to handle the problems with mixed input of multiple images and text segments. We train our model using three stages, including foundational pre-training, foundational fine-tuning, and mathematical fine-tuning. The extensive experiments indicate that our model effectively improves math reasoning performance by comparing it with the SOTA LMMs over three multimodal mathematical datasets.

cs.CL↗

arXiv2024

Right this way: Can VLMs Guide Us to See More to Answer Questions?

In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically generate direct, one-shot responses without evaluating the sufficiency of the information. To investigate this gap, we identify a critical and challenging task in the Visual Question Answering (VQA) scenario: can VLMs indicate how to adjust an image when the visual information is insufficient to answer a question? This capability is especially valuable for assisting visually impaired individuals who often need guidance to capture images correctly. To evaluate this capability of current VLMs, we introduce a human-labeled dataset as a benchmark for this task. Additionally, we present an automated framework that generates synthetic training data by simulating ``where to know'' scenarios. Our empirical results show significant performance improvements in mainstream VLMs when fine-tuned with this synthetic data. This study demonstrates the potential to narrow the gap between information assessment and acquisition in VLMs, bringing their performance closer to humans.

cs.CV↗

arXiv2024

The SRG/eROSITA diffuse soft X-ray background. I. The local hot bubble in the western Galactic hemisphere

The SRG/eROSITA All-Sky Surveys (eRASSs) combine the advantages of complete sky coverage and the energy resolution provided by the charge couple device and offer the most holistic and detailed view of the diffuse soft X-ray background (SXRB) to date. The first eRASS (eRASS1) was completed at solar minimum, when solar wind charge exchange emission was minimal, providing the clearest view of the SXRB. We aim to extract spatial and spectral information from each constituent of the SXRB in the western Galactic hemisphere, focusing on the local hot bubble (LHB). We extracted and analysed eRASS1 spectra from almost all directions in the western Galactic hemisphere by dividing the sky into equal signal-to-noise bins. We fitted all bins with fixed spectral templates of known background constituents. We find the temperature of the LHB exhibits a north-south dichotomy at high latitudes ($|b|>30^{\circ}$), with the south being hotter, with a mean temperature at $kT=121.8\pm0.6\,$eV and the north at $kT=100.8\pm0.5\,$eV. At low latitudes, the LHB temperature increases towards the Galactic plane, especially towards the inner Galaxy. The LHB emission measure (${\rm EM_{LHB}}$) enhances approximately towards the Galactic poles. The ${\rm EM_{LHB}}$ map shows clear anti-correlation with the local dust column density. In particular, we found tunnels of dust cavities filled with hot plasma, potentially forming a wider network of hot interstellar medium. We also constructed a three-dimensional LHB model from ${\rm EM_{LHB}}$, assuming constant density. The average thermal pressure of the LHB is $P_{\rm thermal}/k=10100^{+1200}_{-1500}\,{\rm cm^{-3}\,K}$, a lower value than typical supernova remnants and wind-blown bubbles. This could be an indication of the LHB being open towards high Galactic latitudes.

astro-ph.GA↗

arXiv2024

MARCO: Multi-Agent Real-time Chat Orchestration

Large language model advancements have enabled the development of multi-agent frameworks to tackle complex, real-world problems such as to automate tasks that require interactions with diverse tools, reasoning, and human collaboration. We present MARCO, a Multi-Agent Real-time Chat Orchestration framework for automating tasks using LLMs. MARCO addresses key challenges in utilizing LLMs for complex, multi-step task execution. It incorporates robust guardrails to steer LLM behavior, validate outputs, and recover from errors that stem from inconsistent output formatting, function and parameter hallucination, and lack of domain knowledge. Through extensive experiments we demonstrate MARCO's superior performance with 94.48% and 92.74% accuracy on task execution for Digital Restaurant Service Platform conversations and Retail conversations datasets respectively along with 44.91% improved latency and 33.71% cost reduction. We also report effects of guardrails in performance gain along with comparisons of various LLM models, both open-source and proprietary. The modular and generic design of MARCO allows it to be adapted for automating tasks across domains and to execute complex usecases through multi-turn interactions.

cs.AI↗

arXiv2024

P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics

When solving partial differential equations (PDEs), classical numerical methods often require fine mesh grids and small time stepping to meet stability, consistency, and convergence conditions, leading to high computational cost. Recently, machine learning has been increasingly utilized to solve PDE problems, but they often encounter challenges related to interpretability, generalizability, and strong dependency on rich labeled data. Hence, we introduce a new PDE-Preserved Coarse Correction Network (P$^2$C$^2$Net) to efficiently solve spatiotemporal PDE problems on coarse mesh grids in small data regimes. The model consists of two synergistic modules: (1) a trainable PDE block that learns to update the coarse solution (i.e., the system state), based on a high-order numerical scheme with boundary condition encoding, and (2) a neural network block that consistently corrects the solution on the fly. In particular, we propose a learnable symmetric Conv filter, with weights shared over the entire model, to accurately estimate the spatial derivatives of PDE based on the neural-corrected system state. The resulting physics-encoded model is capable of handling limited training data (e.g., 3--5 trajectories) and accelerates the prediction of PDE solutions on coarse spatiotemporal grids while maintaining a high accuracy. P$^2$C$^2$Net achieves consistent state-of-the-art performance with over 50\% gain (e.g., in terms of relative prediction error) across four datasets covering complex reaction-diffusion processes and turbulent flows.

math.NA↗