arXiv subjects

Yongsheng Liang

Publications and source records attributed to Yongsheng Liang.

At least 19 recordsLinked to original sources

arXiv2026

Variable-Length Finite-Rate CSI Feedback With Generative Priors

This letter studies scalable finite-rate CSI feedback for FDD massive MIMO. Existing scalable neural schemes usually obtain rate flexibility by ordering, masking, quantizing, vector-quantizing, or entropy-coding learned latents, which couples the finite-bit interface to a task-specific latent codec. We propose CsiCoGen, a generative feedback mechanism that moves the finite-bit decision to codebook-constrained Gaussian innovation selection along a reverse diffusion trajectory. A synchronized pseudo-random Gaussian codebook makes each index a generative update instruction; a length-$L$ prefix uses $R_L=L\log_2K$ bits and yields a valid CSI estimate. The codebook is training-free and not transmitted online, while the denoiser is pretrained as a shared CSI prior. On COST2100, CsiCoGen attains indoor/outdoor NMSE of $-28.58$/$-13.96$ dB at $792$ bits and $-30.72$/$-20.37$ dB at $1592$ bits, with corresponding $ρ$ values of $0.9964$/$0.9597$ and $0.9967$/$0.9748$. Accelerated-sampling throughput and MRT spectral-efficiency results further quantify the complexity and link-level effects.

eess.SP↗

arXiv2026

Locality-Aware Density Control for Efficient Gaussian-based Image Representation

2D Gaussian Splatting is an attractive direction for image representation due to its explicit formulation, fast rasterization, and favorable decoding efficiency. The representation quality of this paradigm depends on the proper allocation of Gaussian capacity to the demanding regions. However, existing methods fail to allocate Gaussian capacity efficiently during optimization: under-reconstructed content is often refined in a fragmented pixel-wise manner, while neighboring optimized Gaussians with similar attributes are redundantly retained. This inefficiency motivates the need for a density control framework that jointly addresses insufficient allocation in under-reconstructed regions and redundant allocation in over-reconstructed regions. Our key insight is that this framework should exploit two complementary forms of locality: the local continuity of reconstruction errors in image space for improved Gaussian allocation, and the local similarity of neighboring Gaussians in Gaussian space for redundant elimination. Based on this insight, we propose Locality-Aware Density Control (LocoADC), a plug-and-play framework that improves Gaussian capacity utilization through Region-wise Gaussian Densification (RGD) and Similarity-Driven Gaussian Merging (SDGM) strategies, together with a local color consistency constraint for more reliable merging. Extensive experiments on diverse datasets show that LocoADC consistently improves multiple baselines by enabling more effective local Gaussian allocation, including a 2.93 dB PSNR gain over GI on the CLIC dataset under the same 30k Gaussian budget. Code is available at: \textit{https://github.com/ChenJiaCong-1005/LocoADC}.

cs.CV↗

arXiv2026

Shift-MoE-Based DJSCC for CSI Feedback in Multi-User Pinching-Antenna Systems

In frequency-division duplexing systems, the performance gains of pinching-antenna systems (PASS) critically depend on accurate channel state information (CSI) at the base station. However, PASS CSI exhibits structured correlations over the waveguide-antenna grid and pronounced heterogeneity across users, making conventional fixed feedback mappings difficult to generalize. To address this challenge, this letter proposes an end-to-end CSI feedback scheme over a noisy uplink feedback link based on deep joint source-channel coding, termed Shift-based Mixture-of-Experts (Shift-MoE). Specifically, Shift-MoE leverages channel-grouped one-step shift operations to capture grid dependencies without global attention, and employs a gated multilayer perceptron mixture-of-experts module to adapt to heterogeneous CSI statistics across users. Numerical results demonstrate that the proposed Shift-MoE consistently outperforms representative learning-based CSI feedback baselines in normalized mean squared error and remains effective under different system parameter settings.

eess.SP↗

arXiv2026

STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation

2D Gaussian Splatting (2DGS) has recently become a promising paradigm for high-quality video representation. However, existing methods employ content-agnostic or spatio-temporal feature overlapping embeddings to predict canonical Gaussian primitive deformations, which entangles static and dynamic components in videos and prevents modeling their distinct properties effectively. These result in inaccurate predictions for spatio-temporal deformations and unsatisfactory representation quality. To address these problems, this paper proposes a Spatio-Temporal hash encoding framework for Gaussian-based Video representation (STGV). By decomposing video features into learnable 2D spatial and 3D temporal hash encodings, STGV effectively facilitates the learning of motion patterns for dynamic components while maintaining background details for static elements. In addition, we construct a more stable and consistent initial canonical Gaussian representation through a key frame canonical initialization strategy, preventing from feature overlapping and a structurally incoherent geometry representation. Experimental results demonstrate that our method attains better video representation quality (+0.98 PSNR) against other Gaussian-based methods and achieves competitive performance in downstream video tasks.

cs.CV↗

arXiv2026

Robust Deep Joint Source-Channel Coding for Video Transmission over Multipath Fading Channel

To address the challenges of wireless video transmission over multipath fading channels, we propose a robust deep joint source-channel coding (DeepJSCC) framework by effectively exploiting temporal redundancy and incorporating robust innovations at the modulation, coding, and decoding stages. At the modulation stage, tailored orthogonal frequency division multiplexing (OFDM) for robust video transmission is employed, decomposing wideband signals into orthogonal frequency-flat sub-channels to effectively mitigate frequency-selective fading. At the coding stage, conditional contextual coding with multi-scale Gaussian warped features is introduced to efficiently model temporal redundancy, significantly improving reconstruction quality under strict bandwidth constraints. At the decoding stage, a lightweight denoising module is integrated to robustly simplify signal restoration and accelerate convergence, addressing the suboptimality and slow convergence typically associated with simultaneously performing channel estimation, equalization, and semantic reconstruction. Experimental results demonstrate that the proposed robust framework significantly outperforms state-of-the-art video DeepJSCC methods, achieving an average reconstruction quality gain of 5.13 dB under challenging multipath fading channel conditions.

eess.IV↗

arXiv2025

Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction

3D Gaussian Splatting (3DGS) has emerged as a high-fidelity and efficient paradigm for online free-viewpoint video (FVV) reconstruction, offering viewers rapid responsiveness and immersive experiences. However, existing online methods face challenge in prohibitive storage requirements primarily due to point-wise modeling that fails to exploit the motion properties. To address this limitation, we propose a novel Compact Gaussian Streaming (ComGS) framework, leveraging the locality and consistency of motion in dynamic scene, that models object-consistent Gaussian point motion through keypoint-driven motion representation. By transmitting only the keypoint attributes, this framework provides a more storage-efficient solution. Specifically, we first identify a sparse set of motion-sensitive keypoints localized within motion regions using a viewspace gradient difference strategy. Equipped with these keypoints, we propose an adaptive motion-driven mechanism that predicts a spatial influence field for propagating keypoint motion to neighboring Gaussian points with similar motion. Moreover, ComGS adopts an error-aware correction strategy for key frame reconstruction that selectively refines erroneous regions and mitigates error accumulation without unnecessary overhead. Overall, ComGS achieves a remarkable storage reduction of over 159 X compared to 3DGStream and 14 X compared to the SOTA method QUEEN, while maintaining competitive visual fidelity and rendering speed.

cs.CV↗

arXiv2025

Boosting Neural Video Representation via Online Structural Reparameterization

Neural Video Representation~(NVR) is a promising paradigm for video compression, showing great potential in improving video storage and transmission efficiency. While recent advances have made efforts in architectural refinements to improve representational capability, these methods typically involve complex designs, which may incur increased computational overhead and lack the flexibility to integrate into other frameworks. Moreover, the inherent limitation in model capacity restricts the expressiveness of NVR networks, resulting in a performance bottleneck. To overcome these limitations, we propose Online-RepNeRV, a NVR framework based on online structural reparameterization. Specifically, we propose a universal reparameterization block named ERB, which incorporates multiple parallel convolutional paths to enhance the model capacity. To mitigate the overhead, an online reparameterization strategy is adopted to dynamically fuse the parameters during training, and the multi-branch structure is equivalently converted into a single-branch structure after training. As a result, the additional computational and parameter complexity is confined to the encoding stage, without affecting the decoding efficiency. Extensive experiments on mainstream video datasets demonstrate that our method achieves an average PSNR gain of 0.37-2.7 dB over baseline methods, while maintaining comparable training time and decoding speed.

eess.IV↗

arXiv2025

DynaQuant: Dynamic Mixed-Precision Quantization for Learned Image Compression

Prevailing quantization techniques in Learned Image Compression (LIC) typically employ a static, uniform bit-width across all layers, failing to adapt to the highly diverse data distributions and sensitivity characteristics inherent in LIC models. This leads to a suboptimal trade-off between performance and efficiency. In this paper, we introduce DynaQuant, a novel framework for dynamic mixed-precision quantization that operates on two complementary levels. First, we propose content-aware quantization, where learnable scaling and offset parameters dynamically adapt to the statistical variations of latent features. This fine-grained adaptation is trained end-to-end using a novel Distance-aware Gradient Modulator (DGM), which provides a more informative learning signal than the standard Straight-Through Estimator. Second, we introduce a data-driven, dynamic bit-width selector that learns to assign an optimal bit precision to each layer, dynamically reconfiguring the network's precision profile based on the input data. Our fully dynamic approach offers substantial flexibility in balancing rate-distortion (R-D) performance and computational cost. Experiments demonstrate that DynaQuant achieves rd performance comparable to full-precision models while significantly reducing computational and storage requirements, thereby enabling the practical deployment of advanced LIC on diverse hardware platforms.

eess.IV↗

arXiv2025

Strain-Induced Boundary States and Phase Transitions in Graphene Flakes

Strain has been extensively employed to tailor graphene's properties and has emerged as a powerful tool for engineering gauge fields and exploring fundamental phenomena in artificial platforms like photonic graphene. Here we discover that, in graphene flakes with custom boundaries, one can create or destroy edge states depending on the direction of the applied uniaxial strain. This is experimentally demonstrated in a photonic platform with two specific examples: one flake structure with pairs of twig and zigzag edges, and the other with pairs of armchair and bearded edges. We find that the existence of the edge states and their positions in momentum space are accurately predicted with appropriate winding numbers, unveiling the underlying topology of such edge states. Furthermore, when a graphene flake supports the maximum number of edge states along boundaries after a semimetal-to-insulator transition, both compact localized edge and corner states emerge, indicating the realization of a photonic minimal-model higher-order topological insulator based on such strained graphene flakes.

physics.optics↗

arXiv2025

Dataset Distillation as Data Compression: A Rate-Utility Perspective

Driven by the ``scale-is-everything'' paradigm, modern machine learning increasingly demands ever-larger datasets and models, yielding prohibitive computational and storage requirements. Dataset distillation mitigates this by compressing an original dataset into a small set of synthetic samples, while preserving its full utility. Yet, existing methods either maximize performance under fixed storage budgets or pursue suitable synthetic data representations for redundancy removal, without jointly optimizing both objectives. In this work, we propose a joint rate-utility optimization method for dataset distillation. We parameterize synthetic samples as optimizable latent codes decoded by extremely lightweight networks. We estimate the Shannon entropy of quantized latents as the rate measure and plug any existing distillation loss as the utility measure, trading them off via a Lagrange multiplier. To enable fair, cross-method comparisons, we introduce bits per class (bpc), a precise storage metric that accounts for sample, label, and decoder parameter costs. On CIFAR-10, CIFAR-100, and ImageNet-128, our method achieves up to $170\times$ greater compression than standard distillation at comparable accuracy. Across diverse bpc budgets, distillation losses, and backbone architectures, our approach consistently establishes better rate-utility trade-offs.

cs.LG↗

arXiv2025

Content-Distortion High-Order Interaction for Blind Image Quality Assessment

The content and distortion are widely recognized as the two primary factors affecting the visual quality of an image. While existing No-Reference Image Quality Assessment (NR-IQA) methods have modeled these factors, they fail to capture the complex interactions between content and distortions. This shortfall impairs their ability to accurately perceive quality. To confront this, we analyze the key properties required for interaction modeling and propose a robust NR-IQA approach termed CoDI-IQA (Content-Distortion high-order Interaction for NR-IQA), which aggregates local distortion and global content features within a hierarchical interaction framework. Specifically, a Progressive Perception Interaction Module (PPIM) is proposed to explicitly simulate how content and distortions independently and jointly influence image quality. By integrating internal interaction, coarse interaction, and fine interaction, it achieves high-order interaction modeling that allows the model to properly represent the underlying interaction patterns. To ensure sufficient interaction, multiple PPIMs are employed to hierarchically fuse multi-level content and distortion features at different granularities. We also tailor a training strategy suited for CoDI-IQA to maintain interaction stability. Extensive experiments demonstrate that the proposed method notably outperforms the state-of-the-art methods in terms of prediction accuracy, data efficiency, and generalization ability.

cs.CV↗

arXiv2025

Observation of doubly-degenerate topological flatbands of edge states in strained graphene

Flat bands are of significant interest due to their potential for energy confinement and their ability to enable strongly correlated physics. Incorporating topology into flatband systems further enhances flatband mode robustness against perturbations. Here, we present the first realization of doubly degenerate topological flatbands of edge states in chiral-symmetric strained graphene. The flatband degeneracy stems from Dirac point merging, achieved by tuning the coupling ratios in a honeycomb lattice with twig boundary conditions. The nontrivial topology of these modes is characterized by the winding of the Berry connection, which ensures their robustness against disorder. Experimentally, two types of topological edge states are observed in a strained photonic graphene lattice, consistent with numerical simulations. Moreover, the degeneracy of the topological flatbands doubles the density of states for zero-energy modes, facilitating the formation of compact edge states and enhancing control over edge states and light confinement. Our findings underscore the interplay among lattice geometry, symmetry, and topology in shaping doubly degenerate topological flatbands. This opens new possibilities for advancements in correlated effects, nonlinear optical phenomena, and efficient energy transfer in materials science, photonic crystals, and quantum devices.

physics.optics↗

arXiv2025

ShiftLIC: Lightweight Learned Image Compression with Spatial-Channel Shift Operations

Learned Image Compression (LIC) has attracted considerable attention due to their outstanding rate-distortion (R-D) performance and flexibility. However, the substantial computational cost poses challenges for practical deployment. The issue of feature redundancy in LIC is rarely addressed. Our findings indicate that many features within the LIC backbone network exhibit similarities. This paper introduces ShiftLIC, a novel and efficient LIC framework that employs parameter-free shift operations to replace large-kernel convolutions, significantly reducing the model's computational burden and parameter count. Specifically, we propose the Spatial Shift Block (SSB), which combines shift operations with small-kernel convolutions to replace large-kernel. This approach maintains feature extraction efficiency while reducing both computational complexity and model size. To further enhance the representation capability in the channel dimension, we propose a channel attention module based on recursive feature fusion. This module enhances feature interaction while minimizing computational overhead. Additionally, we introduce an improved entropy model integrated with the SSB module, making the entropy estimation process more lightweight and thereby comprehensively reducing computational costs. Experimental results demonstrate that ShiftLIC outperforms leading compression methods, such as VVC Intra and GMM, in terms of computational cost, parameter count, and decoding latency. Additionally, ShiftLIC sets a new SOTA benchmark with a BD-rate gain per MACs/pixel of -102.6\%, showcasing its potential for practical deployment in resource-constrained environments. The code is released at https://github.com/baoyu2020/ShiftLIC.

eess.IV↗

arXiv2025

Observation of Topological Armchair Edge States in Photonic Biphenylene Network

Edge states in 2D materials are vital for advancements in spintronics, quantum computing, and logic transistors. For graphene nanoribbons, it is well known that the zigzag edges can host edge states, but realization of armchair edge states has been challenging without breaking the time-reversal symmetry. Here, by using a photonic analog of recently synthesized graphene-like biphenylene network (BPN), we demonstrate topological in-gap edge states particularly at the armchair edges. Interestingly, several bulk states preserve the characteristics of edge states along the armchair boundaries, manifesting an unusual hybridization between the edge and bulk states. Experimentally, we observe both zigzag and armchair edge states in photonic BPN lattices written in a nonlinear crystal. Furthermore, we clarify the different features of the armchair boundary between the BPN and graphene lattices. Our results demonstrated here may be applicable to carbon-based BPNs and other artificial platforms beyond photonics, holding promise for expanding the application scope of 2D materials.

physics.optics↗

arXiv2024

Bulk-hole correspondence and inner robust boundary modes in singular flatband lattices

Topological entities based on bulk-boundary correspondence are ubiquitous, from conventional to higher-order topological insulators, where the protected states are typically localized at the outer boundaries (edges or corners). A less explored scenario involves protected states that are localized at the inner boundaries, sharing the same energy as the bulk states. Here, we propose and demonstrate what we refer to as the bulk-hole correspondence - a relation between the inner robust boundary modes (RBMs) and the existence of multiple "holes" in singular flatband lattices, mediated by the immovable discontinuity of the bulk Bloch wavefunctions. We find that the number of independent flatband states always equals the sum of the number of independent compact localized states and the number of nontrivial inner RBMs, as captured by the Betti number that also counts the hole number from topological data analysis. This correspondence is universal for singular flatband lattices, regardless of the lattice shape and the hole shape. Using laser-written Kagome lattices as a platform, we experimentally observe such inner RBMs, demonstrating their real-space topological nature and robustness. Our results may extend to other singular flatband systems beyond photonics, including non-Euclidean lattices, providing a new approach for understanding nontrivial flatband states and topology in hole-bearing lattice systems.

physics.optics↗

arXiv2024

Enhancing Adversarial Training with Prior Knowledge Distillation for Robust Image Compression

Deep neural network-based image compression (NIC) has achieved excellent performance, but NIC method models have been shown to be susceptible to backdoor attacks. Adversarial training has been validated in image compression models as a common method to enhance model robustness. However, the improvement effect of adversarial training on model robustness is limited. In this paper, we propose a prior knowledge-guided adversarial training framework for image compression models. Specifically, first, we propose a gradient regularization constraint for training robust teacher models. Subsequently, we design a knowledge distillation based strategy to generate a priori knowledge from the teacher model to the student model for guiding adversarial training. Experimental results show that our method improves the reconstruction quality by about 9dB when the Kodak dataset is elected as the backdoor attack object for psnr attack. Compared with Ma2023, our method has a 5dB higher PSNR output at high bitrate points.

eess.IV↗

arXiv2024

Transformations in Learned Image Compression from a Modulation Perspective

In this paper, a unified transformation method in learned image compression(LIC) is proposed from the perspective of modulation. Firstly, the quantization in LIC is considered as a generalized channel with additive uniform noise. Moreover, the LIC is interpreted as a particular communication system according to the consistency in structures and optimization objectives. Thus, the technology of communication systems can be applied to guide the design of modules in LIC. Furthermore, a unified transform method based on signal modulation (TSM) is defined. In the view of TSM, the existing transformation methods are mathematically reduced to a linear modulation. A series of transformation methods, e.g. TPM and TJM, are obtained by extending to nonlinear modulation. The experimental results on various datasets and backbone architectures verify that the effectiveness and robustness of the proposed method. More importantly, it further confirms the feasibility of guiding LIC design from a communication perspective. For example, when backbone architecture is hyperprior combining context model, our method achieves 3.52$\%$ BD-rate reduction over GDN on Kodak dataset without increasing complexity.

eess.IV↗

arXiv2023

Bandwidth-efficient Inference for Neural Image Compression

With neural networks growing deeper and feature maps growing larger, limited communication bandwidth with external memory (or DRAM) and power constraints become a bottleneck in implementing network inference on mobile and edge devices. In this paper, we propose an end-to-end differentiable bandwidth efficient neural inference method with the activation compressed by neural data compression method. Specifically, we propose a transform-quantization-entropy coding pipeline for activation compression with symmetric exponential Golomb coding and a data-dependent Gaussian entropy model for arithmetic coding. Optimized with existing model quantization methods, low-level task of image compression can achieve up to 19x bandwidth reduction with 6.21x energy saving.

cs.CV↗