arXiv subjects

Lianchen Jia

Publications and source records attributed to Lianchen Jia.

6 recordsLinked to original sources

arXiv2026

Decoupling Defense Strategies for Robust Image Watermarking

Deep learning-based image watermarking, while robust against conventional distortions, remains vulnerable to advanced adversarial and regeneration attacks. Conventional countermeasures, which jointly optimize the encoder and decoder via a noise layer, face 2 inevitable challenges: (1) decrease of clean accuracy due to decoder adversarial training and (2) limited robustness due to simultaneous training of all three advanced attacks. To overcome these issues, we propose AdvMark, a novel two-stage fine-tuning framework that decouples the defense strategies. In stage 1, we address adversarial vulnerability via a tailored adversarial training paradigm that primarily fine-tunes the encoder while only conditionally updating the decoder. This approach learns to move the image into a non-attackable region, rather than modifying the decision boundary, thus preserving clean accuracy. In stage 2, we tackle distortion and regeneration attacks via direct image optimization. To preserve the adversarial robustness gained in stage 1, we formulate a principled, constrained image loss with theoretical guarantees, which balances the deviation from cover and previous encoded images. We also propose a quality-aware early-stop to further guarantee the lower bound of visual quality. Extensive experiments demonstrate AdvMark outperforms with the highest image quality and comprehensive robustness, i.e. up to 29\%, 33\% and 46\% accuracy improvement for distortion, regeneration and adversarial attacks, respectively.

cs.CV↗

arXiv2026

HiVid: LLM-Guided Video Saliency For Content-Aware VOD And Live Streaming

Content-aware streaming requires dynamic, chunk-level importance weights to optimize subjective quality of experience (QoE). However, direct human annotation is prohibitively expensive while vision-saliency models generalize poorly. We introduce HiVid, the first framework to leverage Large Language Models (LLMs) as a scalable human proxy to generate high-fidelity weights for both Video-on-Demand (VOD) and live streaming. We address 3 non-trivial challenges: (1) To extend LLMs' limited modality and circumvent token limits, we propose a perception module to assess frames in a local context window, autoregressively building a coherent understanding of the video. (2) For VOD with rating inconsistency across local windows, we propose a ranking module to perform global re-ranking with a novel LLM-guided merge-sort algorithm. (3) For live streaming which requires low-latency, online inference without future knowledge, we propose a prediction module to predict future weights with a multi-modal time series model, which comprises a content-aware attention and adaptive horizon to accommodate asynchronous LLM inference. Extensive experiments show HiVid improves weight prediction accuracy by up to 11.5\% for VOD and 26\% for live streaming over SOTA baselines. Real-world user study validates HiVid boosts streaming QoE correlation by 14.7\%.

cs.CV↗

arXiv2025

Crucible: Quantifying the Potential of Control Algorithms through LLM Agents

Control algorithms in production environments typically require domain experts to tune their parameters and logic for specific scenarios. However, existing research predominantly focuses on algorithmic performance under ideal or default configurations, overlooking the critical aspect of Tuning Potential. To bridge this gap, we introduce Crucible, an agent that employs an LLM-driven, multi-level expert simulation to turn algorithms and defines a formalized metric to quantitatively evaluate their Tuning Potential. We demonstrate Crucible's effectiveness across a wide spectrum of case studies, from classic control tasks to complex computer systems, and validate its findings in a real-world deployment. Our experimental results reveal that Crucible systematically quantifies the tunable space across different algorithms. Furthermore, Crucible provides a new dimension for algorithm analysis and design, which ultimately leads to performance improvements. Our code is available at https://github.com/thu-media/Crucible.

cs.AI↗

arXiv2025

Towards User-level QoE: Large-scale Practice in Personalized Optimization of Adaptive Video Streaming

Traditional optimization methods based on system-wide Quality of Service (QoS) metrics have approached their performance limitations in modern large-scale streaming systems. However, aligning user-level Quality of Experience~(QoE) with algorithmic optimization objectives remains an unresolved challenge. Therefore, we propose \texttt{LingXi}, the first large-scale deployed system for personalized adaptive video streaming based on user-level experience. \texttt{LingXi} dynamically optimizes the objectives of adaptive video streaming algorithms by analyzing user engagement. Utilizing exit rate as a key metric, we investigate the correlation between QoS indicators and exit rates based on production environment logs, subsequently developing a personalized exit rate predictor. Through Monte Carlo sampling and online Bayesian optimization, we iteratively determine optimal parameters. Large-scale A/B testing utilizing 8\% of traffic on Kuaishou, one of the largest short video platforms, demonstrates \texttt{LingXi}'s superior performance. \texttt{LingXi} achieves a 0.15\% increase in total viewing time, a 0.1\% improvement in bitrate, and a 1.3\% reduction in stall time across all users, with particularly significant improvements for low-bandwidth users who experience a 15\% reduction in stall time.

cs.MM↗

arXiv2025

Beyond Interpretability: Exploring the Comprehensibility of Adaptive Video Streaming through Large Language Models

Over the past decade, adaptive video streaming technology has witnessed significant advancements, particularly driven by the rapid evolution of deep learning techniques. However, the black-box nature of deep learning algorithms presents challenges for developers in understanding decision-making processes and optimizing for specific application scenarios. Although existing research has enhanced algorithm interpretability through decision tree conversion, interpretability does not directly equate to developers' subjective comprehensibility. To address this challenge, we introduce \texttt{ComTree}, the first bitrate adaptation algorithm generation framework that considers comprehensibility. The framework initially generates the complete set of decision trees that meet performance requirements, then leverages large language models to evaluate these trees for developer comprehensibility, ultimately selecting solutions that best facilitate human understanding and enhancement. Experimental results demonstrate that \texttt{ComTree} significantly improves comprehensibility while maintaining competitive performance, showing potential for further advancement. The source code is available at https://github.com/thu-media/ComTree.

cs.MM↗

arXiv2025

EACO-RAG: Towards Distributed Tiered LLM Deployment using Edge-Assisted and Collaborative RAG with Adaptive Knowledge Update

Large language models (LLMs) have demonstrated impressive capabilities in language tasks, but they require high computing power and rely on static knowledge. To overcome these limitations, Retrieval-Augmented Generation (RAG) incorporates up-to-date external information into LLMs without extensive fine-tuning. Meanwhile, small language models (SLMs) deployed on edge devices offer efficiency and low latency but often struggle with complex reasoning tasks. Unfortunately, current RAG approaches are predominantly based on centralized databases and have not been adapted to address the distinct constraints associated with deploying SLMs in edge environments. To bridge this gap, we propose Edge-Assisted and Collaborative RAG (EACO-RAG), a lightweight framework that leverages distributed edge nodes for adaptive knowledge updates and retrieval. EACO-RAG also employs a hierarchical collaborative gating mechanism to dynamically select among local, edge-assisted, and cloud-based strategies, with a carefully designed algorithm based on Safe Online Bayesian Optimization to maximize the potential performance enhancements. Experimental results demonstrate that EACO-RAG matches the accuracy of cloud-based knowledge graph RAG systems while reducing total costs by up to 84.6% under relaxed delay constraints and by 65.3% under stricter delay requirements. This work represents our initial effort toward achieving a distributed and scalable tiered LLM deployments, with EACO-RAG serving as a promising first step in unlocking the full potential of hybrid edge-cloud intelligence.

cs.DC↗