arXiv subjects

Yang Jing

Publications and source records attributed to Yang Jing.

8 recordsLinked to original sources

arXiv2026

Diff-Symbo: Text-Controlled Long-Duration Symbolic Music Generation Using Autoregressive Latent Diffusion Model

Text-controlled symbolic music generation has recently gained research attention due to its versatile, flexible and straightforward approach to music composition. However, previous approaches tend to generate symbolic music with compromising quality, diversity, controllability and limited duration. In this paper, we present Diff-Symbo, an innovative method that uses latent diffusion model (LDM) to generate high-quality, diverse and long-duration symbolic music. To address the lack of text-symbolic music dataset, we develop a comprehensive dataset with 19,345 text templates by employing large language model. Furthermore, we design a music information encoder to reduce the training overhead while extracting more effective control representations. Given textual descriptions, our proposed method leverages LDM to improve the quality and diversity of music generation. Our method also improves the duration and the compositional consistency of music generation through an autoregressive approach. Experimental results show significant improvements of Diff-Symbo in text controllability, duration, and the quality of generated music compared to the baseline models such as GPT-4, MuseCoco and Multitrack Music Transformer (MMT). As one of the pioneer models in this field, Diff-Symbo paves the way towards controllable and high-quality symbolic music composition based on LDM, offering valuable contributions to both music amateurs and practitioners.

cs.SD↗

arXiv2025

Learning to Wait: Synchronizing Agents with the Physical World

Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental \textit{Temporal Gap} between action initiation and completion. Existing environment-side solutions, such as blocking wrappers or frequent polling, either limit scalability or dilute the agent's context window with redundant observations. In this work, we propose an \textbf{Agent-side Approach} that empowers Large Language Models (LLMs) to actively align their \textit{Cognitive Timeline} with the physical world. By extending the Code-as-Action paradigm to the temporal domain, agents utilize semantic priors and In-Context Learning (ICL) to predict precise waiting durations (\texttt{time.sleep(t)}), effectively synchronizing with asynchronous environment without exhaustive checking. Experiments in a simulated Kubernetes cluster demonstrate that agents can precisely calibrate their internal clocks to minimize both query overhead and execution latency, validating that temporal awareness is a learnable capability essential for autonomous evolution in open-ended environments.

cs.AI↗

arXiv2025

An Efficient, Reliable and Observable Collective Communication Library in Large-scale GPU Training Clusters

Large-scale LLM training requires collective communication libraries to exchange data among distributed GPUs. As a company dedicated to building and operating large-scale GPU training clusters, we encounter several practical limitations of NCCL in production, including 1) SM competition between computation and communication, 2) expensive restart costs under link failures, and 3) insufficient observability of transient collective communication anomalies. To address these challenges, we propose VCCL, an efficient, reliable, and observable collective communication library in large-scale GPU training clusters. VCCL removes SM-consuming P2P kernels by moving intra-node data movement and stream dependency enforcement to CPU threads and GPU copy engines. VCCL also introduces a primary-backup QP mechanism to tolerate frequent NIC port failures, and designs a window-based monitor to observe network anomalies at O({\mu}s) level. We opensource VCCL and deploy it in production training clusters for several months. Compared with NCCL, VCCL improves training throughput by up to 5.28% and reduces massive GPU resource wastage through runtime fault tolerance and finegrained monitor. We also share experience and lessons we learned during the deployment of VCCL in large-scale clusters.

cs.DC↗

arXiv2025

Digitization of Astronomical Photographic Plate of China: Photometric Calibration of Single-exposure Plates and Release of Photometric Catalogs

The Chinese Plate-Digitizing Project has digitized a total number of about 30,000 astronomical plates from 11 telescopes of five observatories (SHAO, NAOC, PMO, YNAO, and QDO) in China, spanning nearly 100 years of observations. In this work, we present a photometric calibration method to calibrate about 15,000 single-exposure plates to the JKC photometric system. Using standard stars constructed from the BEST database, we have identified and corrected various systematic effects (including the magnitude term, color term, and flat-field term) to a high precision. The final photometric precision is typically 0.15, 0.23, 0.17, 0.11, 0.19 mag for plates collected in SHAO, NAOC, PMO, YNAO, and QDO, respectively, with best cases reaching 0.07, 0.08, 0.06, 0.05, and 0.11 mag, respectively. Candidates of variable sources are also identified. The catalogs are publicly available at the China National Astronomical Data Center. Such a dataset will provide a valuable resource for conducting long-term, temporal-scale astronomical research. Our calibration method can also be applied to other digitized astronomical plates in general.

astro-ph.IM↗

arXiv2025

Solving Schr\"{o}dinger bridge problem via continuous normalizing flow

The Schr\"{o}dinger Bridge Problem (SBP), which can be understood as an entropy-regularized optimal transport, seeks to compute stochastic dynamic mappings connecting two given distributions. SBP has shown significant theoretical importance and broad practical potential, with applications spanning a wide range of interdisciplinary fields. While theoretical aspects of the SBP are well-understood, practical computational solutions for general cases have remained challenging. This work introduces a computational framework that leverages continuous normalizing flows and score matching methods to approximate the drift in the dynamic formulation of the SBP. The learned drift term can be used for building generative models, opening new possibilities for applications in probability flow-based methods. We also provide a rigorous $\Gamma-$convergence analysis for our algorithm, demonstrating that the neuron network solutions converge to the theoretical ones as the regularization parameter tends to infinity. Lastly, we validate our algorithm through numerical experiments on fundamental cases.

math.OC↗

arXiv2024

Convergence analysis of OT-Flow for sample generation

Deep generative models aim to learn the underlying distribution of data and generate new ones. Despite the diversity of generative models and their high-quality generation performance in practice, most of them lack rigorous theoretical convergence proofs. In this work, we aim to establish some convergence results for OT-Flow, one of the deep generative models. First, by reformulating the framework of OT-Flow model, we establish the $\Gamma$-convergence of the formulation of OT-flow to the corresponding optimal transport (OT) problem as the regularization term parameter $\alpha$ goes to infinity. Second, since the loss function will be approximated by Monte Carlo method in training, we established the convergence between the discrete loss function and the continuous one when the sample number $N$ goes to infinity as well. Meanwhile, the approximation capability of the neural network provides an upper bound for the discrete loss function of the minimizers. The proofs in both aspects provide convincing assurances for OT-Flow.

math.NA↗

arXiv2022

A deep learning framework for geodesics under spherical Wasserstein-Fisher-Rao metric and its application for weighted sample generation

Wasserstein-Fisher-Rao (WFR) distance is a family of metrics to gauge the discrepancy of two Radon measures, which takes into account both transportation and weight change. Spherical WFR distance is a projected version of WFR distance for probability measures so that the space of Radon measures equipped with WFR can be viewed as metric cone over the space of probability measures with spherical WFR. Compared to the case for Wasserstein distance, the understanding of geodesics under the spherical WFR is less clear and still an ongoing research focus. In this paper, we develop a deep learning framework to compute the geodesics under the spherical WFR metric, and the learned geodesics can be adopted to generate weighted samples. Our approach is based on a Benamou-Brenier type dynamic formulation for spherical WFR. To overcome the difficulty in enforcing the boundary constraint brought by the weight change, a Kullback-Leibler (KL) divergence term based on the inverse map is introduced into the cost function. Moreover, a new regularization term using the particle velocity is introduced as a substitute for the Hamilton-Jacobi equation for the potential in dynamic formula. When used for sample generation, our framework can be beneficial for applications with given weighted samples, especially in the Bayesian inference, compared to sample generation with previous flow models.

cs.LG↗

arXiv2019

Accelerated Symmetric ADMM and Its Applications in Signal Processing

The alternating direction method of multipliers (ADMM) were extensively investigated in the past decades for solving separable convex optimization problems. Fewer researchers focused on exploring its convergence properties for the nonconvex case although it performed surprisingly efficient. In this paper, we propose a symmetric ADMM based on different acceleration techniques for a family of potentially nonsmooth nonconvex programing problems with equality constraints, where the dual variables are updated twice with different stepsizes. Under proper assumptions instead of using the so-called Kurdyka-Lojasiewicz inequality, convergence of the proposed algorithm as well as its pointwise iteration-complexity are analyzed in terms of the corresponding augmented Lagrangian function and the primal-dual residuals, respectively. Performance of our algorithm is verified by some preliminary numerical examples on applications in sparse nonconvex/convex regularized minimization signal processing problems.

math.NA↗