arXiv subjects

Hanchen Li

Publications and source records attributed to Hanchen Li.

24 records · Page 2Linked to original sources

arXiv2025

Loss-tolerant neural video codec aware congestion control for real time video communication

Because of reinforcement learning's (RL) ability to automatically create more adaptive controlling logics beyond the hand-crafted heuristics, numerous effort has been made to apply RL to congestion control (CC) design for real time video communication (RTC) applications and has successfully shown promising benefits over the rule-based RTC CCs. Online reinforcement learning is often adopted to train the RL models so the models can directly adapt to real network environments. However, its trail-and-error manner can also cause catastrophic degradation of the quality of experience (QoE) of RTC application at run time. Thus, safeguard strategies such as falling back to hand-crafted heuristics can be used to run along with RL models to guarantee the actions explored in the training sensible, despite that these safeguard strategies interrupt the learning process and make it more challenging to discover optimal RL policies. The recent emergence of loss-tolerant neural video codecs (NVC) naturally provides a layer of protection for the online learning of RL-based congestion control because of its resilience to packet losses, but such packet loss resilience have not been fully exploited in prior works yet. In this paper, we present a reinforcement learning (RL) based congestion control which can be aware of and takes advantage of packet loss tolerance characteristic of NVCs via reward in online RL learning. Through extensive evaluation on various videos and network traces in a simulated environment, we demonstrate that our NVC-aware CC running with the loss-tolerant NVC reduces the training time by 41\% compared to other prior RL-based CCs. It also boosts the mean video quality by 0.3 to 1.6dB, lower the tail frame delay by 3 to 200ms, and reduces the video stalls by 20\% to 77\% in comparison with other baseline RTC CCs.

cs.NI↗

arXiv2024

CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving

As large language models (LLMs) take on complex tasks, their inputs are supplemented with longer contexts that incorporate domain knowledge. Yet using long contexts is challenging, as nothing can be generated until the whole context is processed by the LLM. While the context-processing delay can be reduced by reusing the KV cache of a context across different inputs, fetching the KV cache, which contains large tensors, over the network can cause high extra network delays. CacheGen is a fast context-loading module for LLM systems. First, CacheGen uses a custom tensor encoder, leveraging KV cache's distributional properties to encode a KV cache into more compact bitstream representations with negligible decoding overhead, to save bandwidth usage. Second, CacheGen adapts the compression level of different parts of a KV cache to cope with changes in available bandwidth, in order to maintain low context-loading delay and high generation quality. % When available bandwidth drops, CacheGen may raise the compression level for a part of the context or recompute its KV cache on the fly. We test CacheGen on popular LLMs and datasets. Compared to the recent systems that reuse the KV cache, CacheGen reduces the KV cache size by 3.5-4.3x and the total delay in fetching and processing contexts by 3.2-3.7x with negligible impact on the LLM response quality. Our code is at: https://github.com/UChi-JCL/CacheGen.

cs.NI↗

arXiv2024

Eloquent: A More Robust Transmission Scheme for LLM Token Streaming

To render each generated token in real-time for users, the Large Language Model (LLM) server generates tokens one by one and streams each token (or group of a few tokens) through the network to the user right after generation, which we refer to as LLM token streaming. However, under unstable network conditions, the LLM token streaming experience could suffer greatly from stalls since one packet loss could block the rendering of later tokens even if the packets containing them arrive on time. With a measurement study, we show that current applications suffer from increased stalls under unstable networks. For this emerging token streaming problem in LLM Chatbots that differs from previous multimedia and text applications, we propose a novel transmission scheme, called Eloquent, which puts newly generated tokens as well as currently unacknowledged tokens in the next outgoing packet. This ensures that each packet contains some new tokens and, in the meantime, is independently rendered when received, avoiding the aforementioned stalls caused by missing packets. Through simulation under various networks, we show Eloquent reduces stall ratio (proportion of token rendering wait time) by 71.0% compared to the retransmission method commonly used by real chatbot applications and by 31.6% compared to the baseline packet duplication scheme. By tailoring Eloquent to fit the token-by-token generation of LLM, we enable the Chatbots to respond like an eloquent speaker for users to better enjoy pervasive AI.

cs.NI↗

arXiv2024

GRACE: Loss-Resilient Real-Time Video through Neural Codecs

In real-time video communication, retransmitting lost packets over high-latency networks is not viable due to strict latency requirements. To counter packet losses without retransmission, two primary strategies are employed -- encoder-based forward error correction (FEC) and decoder-based error concealment. The former encodes data with redundancy before transmission, yet determining the optimal redundancy level in advance proves challenging. The latter reconstructs video from partially received frames, but dividing a frame into independently coded partitions inherently compromises compression efficiency, and the lost information cannot be effectively recovered by the decoder without adapting the encoder. We present a loss-resilient real-time video system called GRACE, which preserves the user's quality of experience (QoE) across a wide range of packet losses through a new neural video codec. Central to GRACE's enhanced loss resilience is its joint training of the neural encoder and decoder under a spectrum of simulated packet losses. In lossless scenarios, GRACE achieves video quality on par with conventional codecs (e.g., H.265). As the loss rate escalates, GRACE exhibits a more graceful, less pronounced decline in quality, consistently outperforming other loss-resilient schemes. Through extensive evaluation on various videos and real network traces, we demonstrate that GRACE reduces undecodable frames by 95% and stall duration by 90% compared with FEC, while markedly boosting video quality over error concealment methods. In a user study with 240 crowdsourced participants and 960 subjective ratings, GRACE registers a 38% higher mean opinion score (MOS) than other baselines.

cs.MM↗

arXiv2023

VidPlat: A Tool for Fast Crowdsourcing of Quality-of-Experience Measurements

For video or web services, it is crucial to measure user-perceived quality of experience (QoE) at scale under various video quality or page loading delays. However, fast QoE measurements remain challenging as they must elicit subjective assessment from human users. Previous work either (1) automates QoE measurements by letting crowdsourcing raters watch and rate QoE test videos or (2) dynamically prunes redundant QoE tests based on previously collected QoE measurements. Unfortunately, it is hard to combine both ideas because traditional crowdsourcing requires QoE test videos to be pre-determined before a crowdsourcing campaign begins. Thus, if researchers want to dynamically prune redundant test videos based on other test videos' QoE, they are forced to launch multiple crowdsourcing campaigns, causing extra overheads to re-calibrate or train raters every time. This paper presents VidPlat, the first open-source tool for fast and automated QoE measurements, by allowing dynamic pruning of QoE test videos within a single crowdsourcing task. VidPlat creates an indirect shim layer between researchers and the crowdsourcing platforms. It allows researchers to define a logic that dynamically determines which new test videos need more QoE ratings based on the latest QoE measurements, and it then redirects crowdsourcing raters to watch QoE test videos dynamically selected by this logic. Other than having fewer crowdsourcing campaigns, VidPlat also reduces the total number of QoE ratings by dynamically deciding when enough ratings are gathered for each test video. It is an open-source platform that future researchers can reuse and customize. We have used VidPlat in three projects (web loading, on-demand video, and online gaming). We show that VidPlat can reduce crowdsourcing cost by 31.8% - 46.0% and latency by 50.9% - 68.8%.

cs.HC↗

arXiv2022

GRACE: Loss-Resilient Real-Time Video Communication Using Data-Scalable Autoencoder

Across many real-time video applications, we see a growing need (especially in long delays and dynamic bandwidth) to allow clients to decode each frame once any (non-empty) subset of its packets is received and improve quality with each new packet. We call it data-scalable delivery. Unfortunately, existing techniques (e.g., FEC, RS and Fountain Codes) fall short: they require either delivery of a minimum number of packets to decode frames, and/or pad video data with redundancy in anticipation of packet losses, which hurts video quality if no packets get lost. This work explores a new approach, inspired by recent advances of neural-network autoencoders, which make data-scalable delivery possible. We present Grace, a concrete data-scalable real-time video system. With the same video encoding, Grace's quality is slightly lower than traditional codec without redundancy when no packet is lost, but with each missed packet, its quality degrades much more gracefully than existing solutions, allowing clients to flexibly trade between frame delay and video quality. Grace makes two contributions: (1) it trains new custom autoencoders to balance compression efficiency and resilience against a wide range of packet losses; and (2) it uses a new transmission scheme to deliver autoencoder-coded frames as individually decodable packets. We test Grace (and traditional loss-resilient schemes and codecs) on real network traces and videos, and show that while Grace's compression efficiency is slightly worse than heavily engineered video codecs, it significantly reduces tail video frame delay (by 2$\times$ at the 95th percentile) with the marginally lowered video quality

cs.MM↗