arXiv subjects

Shan Liu

Publications and source records attributed to Shan Liu.

At least 19 recordsLinked to original sources

arXiv2026

Scalable Neural Video Representation Compression

Scalable video coding (SVC) encodes a video into a layered bitstream consisting of a base layer and one or multiple enhancement layers, enabling decoding at different bitrate/quality/resolution operating points to accommodate diverse device capabilities and network conditions. Due to its practical flexibility, SVC has been incorporated into major video coding standards and has recently attracted growing interest for both scene-agnostic and scene-adaptive neural video codecs. Among the latter, Implicit neural representation (INR) based codecs achieve compression by overfitting a compact neural network to an individual video, offering fast decoding and competitive coding efficiency compared to scene-agnostic neural codecs. However, research on scalable INR-based compression remains in its infancy: these methods support scalable coding by introducing additional network layers, which couple the bitrate with the decoding complexity and also cannot achieve comparable performance with strong scalable/non-scalable codecs. In this context, this paper proposes S-NVRC, a scalable INR-based video codec that jointly supports fine-grained bitrate and decoding complexity scalability from a single embedded bitstream. It adopts a coarse-to-fine prefix for feature grids and a nested prefix for network layers, which scale bitrate and decoding complexity, respectively. The proposed S-NVRC spans a wide range of bitrate and decoding-complexity using a single encoding (training) and outperforms SHM 12.4 and the multi-layer VTM-20.0, by 43.7% and 5.6% in BD-rate on the UVG dataset, while also providing flexible complexity scalability. Implemented code will be provided.

eess.IV↗

arXiv2026

Multi-scale Image Representation Compression

Overfitted codecs have demonstrated promising performance for image and video compression. In particular, for image compression, the Cool-chic family of models has shown competitive performance against scene-agnostic models, with orders of magnitude lower decoding complexity at the cost of a longer overfitting process. However, these overfitted image codecs are not fully optimized toward the rate-distortion objective: their network weights remain in full precision during training, and the associated quantization parameters are selected in a separate post-training stage. Furthermore, their synthesis operates at a single scale, which overlooks cross-scale redundancy. In this paper, we propose MIRC, an overfitted image codec in which every coded component, including the latents, the synthesis network, and the entropy models, is quantized and entropy coded under a single rate-distortion objective, adopting the end-to-end compression pipeline of the neural video representation codec NVRC. We further introduce a multi-scale representation with cross-stage parameter sharing, which improves coding efficiency at a small transmitted overhead. On the CLIC2020 professional validation set, MIRC achieves a 10.5% BD-rate saving against VVC (VTM 22.0). Moreover, MIRC offers a family of configurations spanning 1.2 to 2.9 kMAC per pixel, so the decoding budget can be selected to match the deployment target.

eess.IV↗

arXiv2026

Generation of high-fluence and high-intensity hard x-ray attosecond pulses at European XFEL

By combining hard x-ray attosecond pulses from the European XFEL with total-reflection focusing x-ray optics, we generated nanofocused hard x-ray attosecond pulses with intensities and fluences comparable to the highest values attained in the hard x-ray regime. A peak intensity on the order of 10$^{20}$ W/cm$^2$ is confirmed through the observation of saturation in amplified spontaneous emission from copper atoms. These x-ray pulses enable new scientific opportunities, including the exploration of higher-order nonlinear light--matter interactions, damage-free structure determination, and coherent control of atoms and molecules.

physics.optics↗

arXiv2026

A Necessary and Sufficient Condition for Exact Relaxation of Energy Storage Power Dispatch

Mixed-integer programming (MIP) precludes simultaneous charging and discharging in power dispatch of energy storage system (ESS), but is computationally intensive. Relaxation of this complementarity constraint improves computational efficiency, but may incur an impractical control SCD strategy. To bridge this gap, this letter proposes a necessary and sufficient condition for the exactness of such relaxation. We explicitly derive the relaxation gap and reveal that SCD does not necessarily imply a distinguished optimal value from the MIP model. In such cases, a feasible solution without SCD can be readily recovered without compromising the optimal value. Furthermore, a two-stage relaxation-and-recovery algorithm is proposed to improve the computational efficiency of ESS power dispatch optimization.

eess.SY↗

arXiv2026

Reduced-complexity Adaptive Loop Filtering via Input-dependent Graph Filters

Adaptive Loop Filtering is an important tool for suppressing compression artifacts in modern video codecs. In the enhanced compression model (ECM), a software test model used for experimenting with video coding tools beyond Versatile Video Coding, fixed filters are trained offline and achieve high signal adaptivity via a fine-grained gradient-based classifier, resulting in a large number of fixed filters that introduce redundancy and increased implementation complexity. Reducing this redundancy without compromising artifact suppression, therefore, remains a key challenge. This paper proposes an alternative graph-based fixed-filtering framework for adaptive loop filtering. By using a graph to encode pixel-intensity relationships, our approach captures local structural information more effectively than gradient-based classification alone. Fixed filters are learned as polynomial graph filters, enabling structurally similar local patterns to share common filtering behavior. Experimental results demonstrate that the proposed approach achieves a comparable performance to the ECM baseline while reducing the number of required filters by an order of magnitude.

eess.IV↗

arXiv2026

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control

Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet these gains largely rely on a forgiving region-tolerant paradigm, where many nearby pixels inside the same component remain valid. Precise geometric construction breaks this assumption: actions must land on points in continuous canvas space rather than tolerant regions. Because geometric primitives carry ontological dependencies, a local coordinate error can induce cascading topological failures that distort downstream objects and invalidate the final construction. We identify this regime as precision-sensitive GUI tasks, requiring point-level accuracy, geometry-aware verification, and robustness to dependency-driven error propagation. To benchmark it, we introduce PAGE Bench, with 4,906 problems and over 224K process-supervised, pixel-level GUI actions. We further propose PAGER, a topology-aware agent that decomposes construction into dependency-structured planning and pixel-level execution. Pixel-grounded supervised tuning establishes executable action grammar, while precision-aligned reinforcement learning mitigates rollout-induced exposure bias through state-conditioned geometric feedback. Experiments reveal a pronounced Semantic-Execution Gap: general multimodal models can exceed 88% action type accuracy yet remain below 6% task success. PAGER closes this gap, delivering 4.1x higher task success than the strongest evaluated general baseline and raising step success rate from below 9% for GUI-specialized agents to over 62%, establishing a new state of the art for point-precise GUI control.

cs.AI↗

arXiv2026

A Mamba-based Perceptual Loss Function for Learning-based UGC Transcoding

In user-generated content (UGC) transcoding, source videos typically suffer various degradations due to prior compression, editing, or suboptimal capture conditions. Consequently, existing video compression paradigms that solely optimize for fidelity relative to the reference become suboptimal, as they force the codec to replicate the inherent artifacts of the non-pristine source. To address this, we propose a novel perceptually inspired loss function for learning-based UGC video transcoding that redefines the role of the reference video, shifting it from a ground-truth pixel anchor to an informative contextual guide. Specifically, we train a lightweight neural quality model based on a Selective Structured State-Space Model (Mamba) optimized using a weakly-supervised Siamese ranking strategy. The proposed model is then integrated into the rate-distortion optimization (RDO) process of two neural video codecs (DCVC and HiNeRV) as a loss function, aiming to generate reconstructed content with improved perceptual quality. Our experiments demonstrate that this framework achieves substantial coding gains over both autoencoder and implicit neural representation-based baselines, with 8.46% and 12.89% BD-rate savings, respectively.

eess.IV↗

arXiv2026

Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning

Real-world reinforcement learning often faces environment drift, but most existing methods rely on static entropy coefficients/target entropy, causing over-exploration during stable periods and under-exploration after drift, and leaving unanswered the principled question of how exploration intensity should scale with drift magnitude. We show that, under standard assumptions, entropy scheduling in non-stationary maximum-entropy RL can be cast as the dynamic-regret trade-off between tracking a drifting comparator and stabilizing updates, yielding a square-root scaling rule for the entropy weight in terms of a online non-stationarity proxy. Building on this, we propose AES--Adaptive Entropy Scheduling--which adaptively adjusts the entropy coefficient/temperature online using observable drift proxies during training, requiring almost no structural changes and incurring minimal overhead. Across 4 algorithm variants, 12 tasks, and 4 drift modes, AES significantly reduces the fraction of performance degradation caused by drift and accelerates recovery after abrupt changes.

cs.LG↗

arXiv2026

DALD-PCAC: Density-Adaptive Learning Descriptor for Point Cloud Lossless Attribute Compression

Recently, deep learning has significantly advanced the performance of point cloud geometry compression. However, the learning-based lossless attribute compression of point clouds with varying densities is under-explored. In this paper, we develop a learning-based framework, namely DALD-PCAC that leverages Levels of Detail (LoD) to tailor for point cloud lossless attribute compression. We develop a point-wise attention model using a permutation-invariant Transformer to tackle the challenges of sparsity and irregularity of point clouds during context modeling. We also propose a Density-Adaptive Learning Descriptor (DALD) capable of capturing structure and correlations among points across a large range of neighbors. In addition, we develop a prior-guided block partitioning to reduce the attribute variance within blocks and enhance the performance. Experiments on LiDAR and object point clouds show that DALD-PCAC achieves the state-of-the-art performance on most data. Our method boosts the compression performance and is robust to the varying densities of point clouds. Moreover, it guarantees a good trade-off between performance and complexity, exhibiting great potential in real-world applications. The source code is available at https://github.com/zb12138/DALD_PCAC.

eess.IV↗

arXiv2025

Completely independent Steiner trees and corresponding tree connectivity

The $S$-Steiner tree packing problem provides mathematical foundations for optimizing multi-path information transmission, particularly in designing fault-tolerant parallelized routing architectures for massive-scale network infrastructures. In this article, we propose the definitions of completely independent $S$-Steiner trees (CISSTs for short) and generalized $k^*$-connectivity, which generalize the definitions of internally disjoint $S$-Steiner trees and generalized $k$-connectivity. Given a connected graph $G = (V,E)$ and a vertex subset $S\subseteq V, |S|\geq 2,$ an $S$-Steiner tree of $G$ is a subtree in $G$ that spans all nodes in $S.$ The $S$-Steiner trees $T_1,T_2,\cdots, T_k$ of $G$ are completely independent pairwise if for any $1\leq p<q\leq k,$ $E(T_p)\cap E(T_q)=\emptyset$ , $V(T_p)\cap V(T_q)=S,$ and for any two vertices $x_{1},x_{2}$ in $S$, the paths connecting $x_{1}$ and $x_{2}$ in $T_p,T_q$ are pairwise internally disjoint. The packing number of CISSTs, denoted by $\kappa^*_G(S),$ is the maximum number of CISSTs in $G.$ The generalized $k^*$-connectivity $\kappa_k^*(G)$ is the minimum $\kappa_G^*(S)$ for $S$ ranges over all $k$-subsets of $V(G).$ We provide a detailed characterization of CISSTs. Also, we investigate the CISSTs of complete graphs and complete bipartite graphs. Furthermore, we determine the generalized $k^*$-connectivity for complete graphs and give a tight lower bound of the generalized $k^*$-connectivity for complete bipartite graphs.

math.CO↗

arXiv2025

SOLID: a Framework of Synergizing Optimization and LLMs for Intelligent Decision-Making

This paper introduces SOLID (Synergizing Optimization and Large Language Models for Intelligent Decision-Making), a novel framework that integrates mathematical optimization with the contextual capabilities of large language models (LLMs). SOLID facilitates iterative collaboration between optimization and LLMs agents through dual prices and deviation penalties. This interaction improves the quality of the decisions while maintaining modularity and data privacy. The framework retains theoretical convergence guarantees under convexity assumptions, providing insight into the design of LLMs prompt. To evaluate SOLID, we applied it to a stock portfolio investment case with historical prices and financial news as inputs. Empirical results demonstrate convergence under various scenarios and indicate improved annualized returns compared to a baseline optimizer-only method, validating the synergy of the two agents. SOLID offers a promising framework for advancing automated and intelligent decision-making across diverse domains.

cs.AI↗

arXiv2025

An Overview of the JPEG AI Learning-Based Image Coding Standard

JPEG AI is an emerging learning-based image coding standard developed by Joint Photographic Experts Group (JPEG). The scope of the JPEG AI is the creation of a practical learning-based image coding standard offering a single-stream, compact compressed domain representation, targeting both human visualization and machine consumption. Scheduled for completion in early 2025, the first version of JPEG AI focuses on human vision tasks, demonstrating significant BD-rate reductions compared to existing standards, in terms of MS-SSIM, FSIM, VIF, VMAF, PSNR-HVS, IW-SSIM and NLPD quality metrics. Designed to ensure broad interoperability, JPEG AI incorporates various design features to support deployment across diverse devices and applications. This paper provides an overview of the technical features and characteristics of the JPEG AI standard.

eess.IV↗

arXiv2025

Single-shot sorting of M\"ossbauer time-domain data at X-ray free-electron lasers

M\"ossbauer spectroscopy is widely used to study structure and dynamics of matter with remarkably high energy resolution, provided by the narrow nuclear resonance line widths. However, the narrow width implies low count rates, such that experiments commonly average over extended measurement times or many x-ray pulses (``shots''). This averaging impedes the study of non-equilibrium phenomena. It has been suggested that X-ray free-electron lasers (XFELs) could enable M\"ossbauer single-shot measurements without averaging, and a proof-of-principle demonstration has been reported. However, so far, only a tiny fraction of all shots resulted in signal-photon numbers which are sufficiently high for a single-shot analysis. Here, we demonstrate coherent nuclear-forward-scattering of self-seeded XFEL radiation, with up to 900 signal-photons per shot. We develop a sorting approach which allows us to include all data on a single-shot level, independent of the signal content of the individual shots. It utilizes the presence of different dynamics classes, i.e. different nuclear evolutions after each excitation. Each shot is assigned to one of the classes, which can then be analyzed separately. Our approach determines the classes from the data without requiring theory modeling nor prior knowledge on the dynamics, making it also applicable to unknown phenomena. We envision that our approach opens up new grounds for M\"ossbauer science, enabling the study of out-of-equilibrium transient dynamics of the nuclei or their environment.

quant-ph↗

arXiv2025

Probing the Linewidth of the 12.4-keV Solid-State $^{45}$Sc Isomeric Resonance

The $^{45}$Sc nuclear transition from the ground to the isomeric state at 12.389~keV, with a lifetime of 0.46~s, exhibits an extraordinarily narrow natural width of 1.4~feV and a quality factor $\simeq 10^{19}$ -- surpassing those of the most precise atomic clocks -- making $^{45}$Sc a compelling platform for advanced metrology and nuclear clocks. Here we investigate how closely the spectral width and quality factor of the solid-state $^{45}$Sc resonance can approach these natural limits. Using the European X-ray Free-Electron Laser, we confirm the isomer's lifetime via time-delayed incoherent $K_{\alpha,\beta}$ fluorescence and observe previously unreported elastic fluorescence, yielding a partial internal conversion coefficient of 390(60). The absence of a clear nuclear forward scattering signal beyond a 2-ms delay implies environmental broadening of at least $500~\Gamma_{0}$ under experimental conditions, placing bounds on solid-state decoherence mechanisms. These findings set new experimental benchmarks for solid-state nuclear clock development.

quant-ph↗

arXiv2025

Cross-architecture universal feature coding via distribution alignment

Feature coding has become increasingly important in scenarios where semantic representations rather than raw pixels are transmitted and stored. However, most existing methods are architecture-specific, targeting either CNNs or Transformers. This design limits their applicability in real-world scenarios where features from both architectures coexist. To address this gap, we introduce a new research problem: cross-architecture universal feature coding (CAUFC), which seeks to build a unified codec that can effectively compress features from heterogeneous architectures. To tackle this challenge, we propose a two-step distribution alignment method. First, we design the format alignment method that unifies CNN and Transformer features into a consistent 2D token format. Second, we propose the feature value alignment method that harmonizes statistical distributions via truncation and normalization. As a first attempt to study CAUFC, we evaluate our method on the image classification task. Experimental results demonstrate that our method achieves superior rate-accuracy trade-offs compared to the architecture-specific baseline. This work marks an initial step toward universal feature compression across heterogeneous model architectures.

cs.CV↗

arXiv2025

Instance Data Condensation for Image Super-Resolution

Deep learning based Image Super-Resolution (ISR) relies on large training datasets to optimize model generalization; this requires substantial computational and storage resources during training. While dataset condensation (DC) has shown potential in improving data efficiency for high-level computer vision tasks, adopting these methods for ISR is not straightforward due to the different requirements of ISR training, including the use of unlabeled datasets and high resolution images with fine details. In this paper, we propose a novel Instance Data Condensation (IDC) framework specifically for ISR, which achieves data condensation in a per-image manner, aiming to address the limitations when directly applying existing DC methods to the ISR task. Furthermore, the IDC framework is based on a novel Random Local Fourier Feature Extraction and Multi-level Feature Distribution Matching methods, which are designed to generate high-quality synthesized content by aligning its feature distributions with those of the original high-resolution training samples at both global and local levels. This framework has been utilized to condense the most commonly used training dataset for ISR, DIV2K, with a 10% condensation rate. The resulting synthetic dataset offers comparable performance to the original full dataset and excellent training stability when used to train various popular ISR models. To the best of our knowledge, this is the first time that a condensed/synthetic dataset (with a 10% data volume) has demonstrated such performance.

cs.CV↗

arXiv2025

NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results

This paper presents a review for the NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement. The challenge comprises two tracks: (i) Efficient Video Quality Assessment (KVQ), and (ii) Diffusion-based Image Super-Resolution (KwaiSR). Track 1 aims to advance the development of lightweight and efficient video quality assessment (VQA) models, with an emphasis on eliminating reliance on model ensembles, redundant weights, and other computationally expensive components in the previous IQA/VQA competitions. Track 2 introduces a new short-form UGC dataset tailored for single image super-resolution, i.e., the KwaiSR dataset. It consists of 1,800 synthetically generated S-UGC image pairs and 1,900 real-world S-UGC images, which are split into training, validation, and test sets using a ratio of 8:1:1. The primary objective of the challenge is to drive research that benefits the user experience of short-form UGC platforms such as Kwai and TikTok. This challenge attracted 266 participants and received 18 valid final submissions with corresponding fact sheets, significantly contributing to the progress of short-form UGC VQA and image superresolution. The project is publicly available at https://github.com/lixinustc/KVQE- ChallengeCVPR-NTIRE2025.

eess.IV↗

arXiv2024

Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation

Despite alleviating the dependence on dense annotations inherent to fully supervised methods, weakly supervised point cloud semantic segmentation suffers from inadequate supervision signals. In response to this challenge, we introduce a novel perspective that imparts auxiliary constraints by regulating the feature space under weak supervision. Our initial investigation identifies which distributions accurately characterize the feature space, subsequently leveraging this priori to guide the alignment of the weakly supervised embeddings. Specifically, we analyze the superiority of the mixture of von Mises-Fisher distributions (moVMF) among several common distribution candidates. Accordingly, we develop a Distribution Guidance Network (DGNet), which comprises a weakly supervised learning branch and a distribution alignment branch. Leveraging reliable clustering initialization derived from the weakly supervised learning branch, the distribution alignment branch alternately updates the parameters of the moVMF and the network, ensuring alignment with the moVMF-defined latent space. Extensive experiments validate the rationality and effectiveness of our distribution choice and network design. Consequently, DGNet achieves state-of-the-art performance under multiple datasets and various weakly supervised settings.

cs.CV↗