Searcharxiv⌕ Search

arXiv subjects

Jianping Lin

Publications and source records attributed to Jianping Lin.

10 recordsLinked to original sources

Artifact Filtering versus Artifact-Compensated Training in JPEG to JPEG AI Recompression

In this paper, we consider the problem of recompression of images from JPEG to JPEG AI format. We show that direct recompression from JPEG to JPEG~AI trained on uncompressed images is accompanied by the preservation of the JPEG image artifacts in the resulting JPEG~AI image. In order to avoid it, we evaluate an approach where an artifacts removal neural network is first applied to the input JPEG image as an external pre-filter. However, in this case, the processing time is increased by 29 times. Therefore, we propose an artifact-compensated training for JPEG AI and show that it is able to combine pre-filtering against target distortions with efficient compression without increase in the processing time.

eess.IV↗

Omni-Flow: A Unified Workflow Orchestration and Distributed KV Cache Sharing Framework for Multimodal Inference

Multimodal models increasingly integrate heterogeneous components, from encoders and LLMs to diffusion models and media decoders. Serving these models efficiently requires flexible workflow orchestration, independent component scheduling, and cross-component state sharing. However, existing multimodal frameworks primarily organize execution as stage-level pipelines, while state ownership remains largely stage-local. We present Omni-Flow, a distributed serving framework built around three cooperating abstractions. Control Flow defines workflows through a Python DSL, organizing heterogeneous components and their dependencies into a unified dataflow graph. The runtime uses these dependencies to determine when each component can execute. Data Flow manages the placement, transfer, and lifetime of shared tensors and paged KV caches across roles, together with same-device weight sharing. Compute Flow matches multimodal conversation histories to reuse KV across turns and integrates framework-managed KV and model-specific sampling with SGLang's execution interfaces. Omni-Flow also enables cross-role prefix-KV reuse between compatible LLM and diffusion components. Together, these abstractions separate model-specific computation from workflow coordination and state management, allowing independently executing roles to share compatible resources through a common programming model. Experiments with Qwen3-Omni show that, across four benchmarks and multiple concurrency levels, Omni-Flow's aggregate job completion time (JCT) is 1.2\% and 4.9\% higher than vLLM-Omni's and SGLang-Omni's, respectively. In a 50-turn multimodal session, Omni-Flow avoids resubmitting accumulated inputs through server-side session state, reducing mean JCT by 7.5\% and 19.3\% relative to vLLM-Omni and SGLang-Omni, respectively.

cs.DC↗

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Autoregressive (DiNA), a unified framework that represents multimodal information within a shared discrete space, enabling a consistent and principled autoregressive modeling across modalities. A key innovation is the Discrete Native Any-resolution Visual Transformer (dNaViT), which performs tokenization and de-tokenization at arbitrary resolutions, transforming continuous visual signals into hierarchical discrete tokens. Building on this foundation, we develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal modality-specific design. As an industrial-strength foundation model, it excels at seeing, painting, and talking within a single framework, achieving strong performance across a wide range of multimodal benchmarks. In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks and provides a unified approach to effectively reconcile the conflict between understanding and generation. As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community. GitHub: https://github.com/meituan-longcat/LongCat-Next

cs.CV↗

Learned Image Compression with Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules

Recently deep learning-based image compression methods have achieved significant achievements and gradually outperformed traditional approaches including the latest standard Versatile Video Coding (VVC) in both PSNR and MS-SSIM metrics. Two key components of learned image compression are the entropy model of the latent representations and the encoding/decoding network architectures. Various models have been proposed, such as autoregressive, softmax, logistic mixture, Gaussian mixture, and Laplacian. Existing schemes only use one of these models. However, due to the vast diversity of images, it is not optimal to use one model for all images, even different regions within one image. In this paper, we propose a more flexible discretized Gaussian-Laplacian-Logistic mixture model (GLLMM) for the latent representations, which can adapt to different contents in different images and different regions of one image more accurately and efficiently, given the same complexity. Besides, in the encoding/decoding network design part, we propose a concatenated residual blocks (CRB), where multiple residual blocks are serially connected with additional shortcut connections. The CRB can improve the learning ability of the network, which can further improve the compression performance. Experimental results using the Kodak, Tecnick-100 and Tecnick-40 datasets show that the proposed scheme outperforms all the leading learning-based methods and existing compression standards including VVC intra coding (4:4:4 and 4:2:0) in terms of the PSNR and MS-SSIM. The source code is available at \url{https://github.com/fengyurenpingsheng}

eess.IV↗

Optimal Energy Shaping Control for a Backdrivable Hip Exoskeleton

Task-dependent controllers widely used in exoskeletons track predefined trajectories, which overly constrain the volitional motion of individuals with remnant voluntary mobility. Energy shaping, on the other hand, provides task-invariant assistance by altering the human body's dynamic characteristics in the closed loop. While human-exoskeleton systems are often modeled using Euler-Lagrange equations, in our previous work we modeled the system as a port-controlled-Hamiltonian system, and a task-invariant controller was designed for a knee-ankle exoskeleton using interconnection-damping assignment passivity-based control. In this paper, we extend this framework to design a controller for a backdrivable hip exoskeleton to assist multiple tasks. A set of basis functions that contains information of kinematics is selected and corresponding coefficients are optimized, which allows the controller to provide torque that fits normative human torque for different activities of daily life. Human-subject experiments with two able-bodied subjects demonstrated the controller's capability to reduce muscle effort across different tasks.

cs.RO↗

Learned Variable-Rate Multi-Frequency Image Compression using Modulated Generalized Octave Convolution

In this proposal, we design a learned multi-frequency image compression approach that uses generalized octave convolutions to factorize the latent representations into high-frequency (HF) and low-frequency (LF) components, and the LF components have lower resolution than HF components, which can improve the rate-distortion performance, similar to wavelet transform. Moreover, compared to the original octave convolution, the proposed generalized octave convolution (GoConv) and octave transposed-convolution (GoTConv) with internal activation layers preserve more spatial structure of the information, and enable more effective filtering between the HF and LF components, which further improve the performance. In addition, we develop a variable-rate scheme using the Lagrangian parameter to modulate all the internal feature maps in the auto-encoder, which allows the scheme to achieve the large bitrate range of the JPEG AI with only three models. Experiments show that the proposed scheme achieves much better Y MS-SSIM than VVC. In terms of YUV PSNR, our scheme is very similar to HEVC.

eess.IV↗

M-LVC: Multiple Frames Prediction for Learned Video Compression

We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduces the usage of the previous multiple frames as references. In our scheme, the motion vector (MV) field is calculated between the current frame and the previous one. With multiple reference frames and associated multiple MV fields, our designed network can generate more accurate prediction of the current frame, yielding less residual. Multiple reference frames also help generate MV prediction, which reduces the coding cost of MV field. We use two deep auto-encoders to compress the residual and the MV, respectively. To compensate for the compression error of the auto-encoders, we further design a MV refinement network and a residual refinement network, taking use of the multiple reference frames as well. All the modules in our scheme are jointly optimized through a single rate-distortion loss function. We use a step-by-step training strategy to optimize the entire scheme. Experimental results show that the proposed method outperforms the existing learned video compression methods for low-latency mode. Our method also performs better than H.265 in both PSNR and MS-SSIM. Our code and models are publicly available.

eess.IV↗

LabelECG: A Web-based Tool for Distributed Electrocardiogram Annotation

Electrocardiography plays an essential role in diagnosing and screening cardiovascular diseases in daily healthcare. Deep neural networks have shown the potentials to improve the accuracies of arrhythmia detection based on electrocardiograms (ECGs). However, more ECG records with ground truth are needed to promote the development and progression of deep learning techniques in automatic ECG analysis. Here we propose a web-based tool for ECG viewing and annotating, LabelECG. With the facilitation of unified data management, LabelECG is able to distribute large cohorts of ECGs to dozens of technicians and physicians, who can simultaneously make annotations through web-browsers on PCs, tablets and cell phones. Along with the doctors from four hospitals in China, we applied LabelECG to support the annotations of about 15,000 12-lead resting ECG records in three months. These annotated ECGs have successfully supported the First China ECG intelligent Competition. La-belECG will be freely accessible on the Internet to support similar researches, and will also be upgraded through future works.

cs.DB↗

Deep Learning-Based Video Coding: A Review and A Case Study

The past decade has witnessed great success of deep learning technology in many disciplines, especially in computer vision and image processing. However, deep learning-based video coding remains in its infancy. This paper reviews the representative works about using deep learning for image/video coding, which has been an actively developing research area since the year of 2015. We divide the related works into two categories: new coding schemes that are built primarily upon deep networks (deep schemes), and deep network-based coding tools (deep tools) that shall be used within traditional coding schemes or together with traditional coding tools. For deep schemes, pixel probability modeling and auto-encoder are the two approaches, that can be viewed as predictive coding scheme and transform coding scheme, respectively. For deep tools, there have been several proposed techniques using deep learning to perform intra-picture prediction, inter-picture prediction, cross-channel prediction, probability distribution prediction, transform, post- or in-loop filtering, down- and up-sampling, as well as encoding optimizations. In the hope of advocating the research of deep learning-based video coding, we present a case study of our developed prototype video codec, namely Deep Learning Video Coding (DLVC). DLVC features two deep tools that are both based on convolutional neural network (CNN), namely CNN-based in-loop filter (CNN-ILF) and CNN-based block adaptive resolution coding (CNN-BARC). Both tools help improve the compression efficiency by a significant margin. With the two deep tools as well as other non-deep coding tools, DLVC is able to achieve on average 39.6\% and 33.0\% bits saving than HEVC, under random-access and low-delay configurations, respectively. The source code of DLVC has been released for future researches.

cs.MM↗

Atomistic mechanisms governing structural stability change of zinc antimony thermoelectrics

The structural stability of thermoelectric materials is a subject of growing importance for their energy harvesting applications. Here, we study the microscopic mechanisms governing the structural stability change of zinc antimony at its working temperature, using molecular dynamics combined with experimental measurements of the electrical and thermal conductivity. Our results show that the temperature-dependence of the thermal and electrical transport coefficients is strongly correlated with a structural transition. This is found to be associated with a relaxation process, in which a group of Zn atoms migrates between interstitial sites. This atom migration gradually leads to a stabilizing structural transition of the entire crystal framework, and then results in a more stable crystal structure of $β-$ Zn4Sb3 at high temperature.

cond-mat.mtrl-sci↗