arXiv subjects

Haoran Wan

Publications and source records attributed to Haoran Wan.

6 recordsLinked to original sources

arXiv2026

NeuralEmu: in situ Measurement-Driven, ML-based, High-Fidelity 5G Network Emulation

Current and future applications demand ultra-low latency and consistent throughput, yet frequently traverse 5G cellular networks, so cope with volatile packet dynamics, as 5G base station schedulers dynamically react to user workloads and wireless channel conditions. The task of evaluating network algorithms in these environments is hamstrung by current tools: record-and-replay emulators sever the feedback interaction that exists between application end points and a commercial operator's proprietary 5G scheduler, while full-stack simulators rely on overly simplistic scheduling logic. To bridge this reality gap, we present NeuralEmu, a high-fidelity, machine learning-based emulation framework that learns complex 5G scheduler resource allocation behaviors directly from extremely high-resolution network telemetry tools. The first emulator to handle multiple clients, NeuralEmu utilizes machine learning to dynamically predict resource block allocations and modulation schemes based on instantaneous user buffer occupancy and channel states. To capture realistic cross-user contention, a traffic reconstruction model inverts cellular network scheduling results to recover the underlying traffic patterns of uncontrolled background users. Implemented as an high-performance Linux middlebox emulator, NeuralEmu reduces emulation error relative to the state of the art for various network applications including but not limited to 55% for web-page load time, 57% for WebRTC encoder bit rate, and 51% for cloud gaming packet one-way delay, providing an accurate, standardized testing ground for tomorrow's real-time interactive network protocols and applications.

cs.NI↗

arXiv2026

HeartMuLa: A Family of Open Sourced Music Foundation Models

We present a family of open-source Music Foundation Models designed to advance large-scale music understanding and generation across diverse tasks and modalities. Our framework consists of four major components: (1) HeartCLAP, an audio-text alignment model; (2) HeartTranscriptor, a robust lyric recognition model optimized for real-world music scenarios; and (3) HeartCodec, a low-frame-rate (12.5 Hz) yet high-fidelity music codec tokenizer that captures long-range musical structure while preserving fine-grained acoustic details and enabling efficient autoregressive modeling; (4) HeartMuLa, an LLM-based song generation model capable of synthesizing high-fidelity music under rich, user-controllable conditions (e.g., textual style descriptions, lyrics, and reference audio). In addition, it provides two specialized modes: (i) fine-grained musical attribute control, which allows users to specify the style of different song sections (e.g., intro, verse, chorus) using natural language prompts; and (ii) short, engaging music generation, which is suitable as background music for short videos. Lastly, HeartMuLa improves significantly when scaled to 7B parameters. For the first time, we show that a Suno-level, commercial-grade system can be reproduced using academic-scale data and GPU resources. We expect these foundation models to serve as strong baselines for future research and to facilitate practical applications in multimodal content production.

cs.SD↗

arXiv2025

L4Span: Spanning Congestion Signaling over NextG Networks for Interactive Applications

Design for low latency networking is essential for tomorrow's interactive applications, but it is essential to deploy incrementally and universally at the network's last mile. While wired broadband ISPs are rolling out the leading queue occupancy signaling mechanisms, the cellular Radio Access Network (RAN), another important last mile to many users, lags behind these efforts. This paper proposes a new RAN design, L4Span, that abstracts the complexities of RAN queueing in a simple interface, thus tying the queue state of the RAN to end-to-end low-latency signaling all the way back to the content server. At millisecond-level timescales, L4Span predicts the RAN's queuing occupancy and performs ECN marking for both low-latency and classic flows. L4Span is lightweight, requiring minimal RAN modifications, and remains 3GPP and O-RAN compliant for maximum ease of deployment. We implement a prototype on the srsRAN open-source software in C++. Our evaluation compares the performance of low-latency as well as classic flows with or without the deployment of L4Span in various wireless channel conditions. Results show that L4Span reduces the one-way delay of both low-latency and classic flows by up to 98 %, while simultaneously maintaining near line-rate throughput. The code is available at https://github.com/PrincetonUniversity/L4Span.

cs.NI↗

arXiv2025

Automated, Cross-Layer Root Cause Analysis of 5G Video-Conferencing Quality Degradation

5G wireless networks are complex, leveraging layers of scheduling, retransmission, and adaptation mechanisms to maximize their efficiency. But these mechanisms interact to produce significant fluctuations in uplink and downlink capacity and latency. This markedly impacts the performance of real-time applications, such as video-conferencing, which are particularly sensitive to such fluctuations, resulting in lag, stuttering, distorted audio, and low video quality. This paper presents a cross-layer view of 5G networks and their impact on and interaction with video-conferencing applications. We conduct novel, detailed measurements of both Private CBRS and commercial carrier cellular network dynamics, capturing physical- and link-layer events and correlating them with their effects at the network and transport layers, and the video-conferencing application itself. Our two datasets comprise days of low-rate campus-wide Zoom telemetry data, and hours of high-rate, correlated WebRTC-network-5G telemetry data. Based on these data, we trace performance anomalies back to root causes, identifying 24 previously unknown causal event chains that degrade 5G video conferencing. Armed with this knowledge, we build Domino, a tool that automates this process and is user-extensible to future wireless networks and interactive applications.

cs.NI↗

arXiv2024

Evolving Mobile Cloud Gaming with 5G Standalone Network Telemetry

Mobile cloud gaming places the simultaneous demands of high capacity and low latency on the wireless network, demands that Private and Metropolitan-Area Standalone 5G networks are poised to meet. However, lacking introspection into the 5G Radio Access Network (RAN), cloud gaming servers are ill-poised to cope with the vagaries of the wireless last hop to a mobile client, while 5G network operators run mostly closed networks, limiting their potential for co-design with the wider internet and user applications. This paper presents Telesa, a passive, incrementally-deployable, and independently-deployable Standalone 5G network telemetry system that streams fine-grained RAN capacity, latency, and retransmission information to application servers to enable better millisecond scale, application-level decisions on offered load and bit rate adaptation than end-to-end latency measurements or end-to-end packet losses currently permit. We design, implement, and evaluate a Telesa telemetry-enhanced game streaming platform, demonstrating exact congestion-control that can better adapt game video bitrate while simultaneously controlling end-to-end latency, thus maximizing game quality of experience. Our experimental evaluation on a production 5G Standalone network demonstrates a 178-249% Quality of Experience improvement versus two state-of-the-art cloud gaming applications.

cs.NI↗

arXiv2022

ALT: Boosting Deep Learning Performance by Breaking the Wall between Graph and Operator Level Optimizations

Deep learning models rely on highly optimized tensor libraries for efficient inference on heterogeneous hardware. Current deep compilers typically predetermine layouts of tensors and then optimize loops of operators. However, such unidirectional and one-off workflow strictly separates graph-level optimization and operator-level optimization into different system layers, missing opportunities for unified tuning. This paper proposes ALT, a compiler that performs joint graph- and operator-level optimizations for deep models. ALT provides a generic transformation module to manipulate layouts and loops with easy-to-use primitive functions. ALT further integrates an auto-tuning module that jointly optimizes graph-level data layouts and operator-level loops while guaranteeing efficiency. Experimental results show that ALT significantly outperforms state-of-the-art compilers (e.g., Ansor) in terms of both single operator performance (e.g., 1.5x speedup on average) and end-to-end inference performance (e.g., 1.4x speedup on average).

cs.LG↗