Ying Chen

Ren Yang, Radu Timofte, Meisong Zheng et al. · tencent-ai

This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video. In this challenge, we proposed the LDV 2.0 dataset, which includes the LDV dataset (240 videos) and 95 additional videos. This challenge includes three tracks. Track 1 aims at enhancing the videos compressed by HEVC at a fixed QP. Track 2 and Track 3 target both the super-resolution and quality enhancement of HEVC compressed video. They require x2 and x4 super-resolution, respectively. The three tracks totally attract more than 600 registrations. In the test phase, 8 teams, 8 teams and 12 teams submitted the final results to Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of super-resolution and quality enhancement of compressed video. The proposed LDV 2.0 dataset is available at https://github.com/RenYang-home/LDV_dataset. The homepage of this challenge (including open-sourced codes) is at https://github.com/RenYang-home/NTIRE22_VEnh_SR.

Yifu Qiu, Hongyu Li, Yingqi Qu et al. · baidu, cambridge

In this paper, we present DuReader_retrieval, a large-scale Chinese dataset for passage retrieval. DuReader_retrieval contains more than 90K queries and over 8M unique passages from a commercial search engine. To alleviate the shortcomings of other datasets and ensure the quality of our benchmark, we (1) reduce the false negatives in development and test sets by manually annotating results pooled from multiple retrievers, and (2) remove the training queries that are semantically similar to the development and testing queries. Additionally, we provide two out-of-domain testing sets for cross-domain evaluation, as well as a set of human translated queries for for cross-lingual retrieval evaluation. The experiments demonstrate that DuReader_retrieval is challenging and a number of problems remain unsolved, such as the salient phrase mismatch and the syntactic mismatch between queries and paragraphs. These experiments also show that dense retrievers do not generalize well across domains, and cross-lingual retrieval is essentially challenging. DuReader_retrieval is publicly available at https://github.com/baidu/DuReader/tree/master/DuReader-Retrieval.

Zicheng Zhang, Wei Sun, Yucheng Zhu et al.

Point cloud is one of the most widely used digital representation formats for three-dimensional (3D) contents, the visual quality of which may suffer from noise and geometric shift distortions during the production procedure as well as compression and downsampling distortions during the transmission process. To tackle the challenge of point cloud quality assessment (PCQA), many PCQA methods have been proposed to evaluate the visual quality levels of point clouds by assessing the rendered static 2D projections. Although such projection-based PCQA methods achieve competitive performance with the assistance of mature image quality assessment (IQA) methods, they neglect that the 3D model is also perceived in a dynamic viewing manner, where the viewpoint is continually changed according to the feedback of the rendering device. Therefore, in this paper, we evaluate the point clouds from moving camera videos and explore the way of dealing with PCQA tasks via using video quality assessment (VQA) methods. First, we generate the captured videos by rotating the camera around the point clouds through several circular pathways. Then we extract both spatial and temporal quality-aware features from the selected key frames and the video clips through using trainable 2D-CNN and pre-trained 3D-CNN models respectively. Finally, the visual quality of point clouds is represented by the video quality values. The experimental results reveal that the proposed method is effective for predicting the visual quality levels of the point clouds and even competitive with full-reference (FR) PCQA methods. The ablation studies further verify the rationality of the proposed framework and confirm the contributions made by the quality-aware features extracted via the dynamic viewing manner. The code is available at https://github.com/zzc-1998/VQA_PC.

Dihe Huang, Ying Chen, Shang Xu et al.

The detector-free feature matching approaches are currently attracting great attention thanks to their excellent performance. However, these methods still struggle at large-scale and viewpoint variations, due to the geometric inconsistency resulting from the application of the mutual nearest neighbour criterion (\ie, one-to-one assignment) in patch-level matching.Accordingly, we introduce AdaMatcher, which first accomplishes the feature correlation and co-visible area estimation through an elaborate feature interaction module, then performs adaptive assignment on patch-level matching while estimating the scales between images, and finally refines the co-visible matches through scale alignment and sub-pixel regression module.Extensive experiments show that AdaMatcher outperforms solid baselines and achieves state-of-the-art results on many downstream tasks. Additionally, the adaptive assignment and sub-pixel refinement module can be used as a refinement network for other matching methods, such as SuperGlue, to boost their performance further. The code will be publicly available at https://github.com/AbyssGaze/AdaMatcher.

Canqian Yang, Meiguang Jin, Xu Jia et al.

The 3D Lookup Table (3D LUT) is a highly-efficient tool for real-time image enhancement tasks, which models a non-linear 3D color transform by sparsely sampling it into a discretized 3D lattice. Previous works have made efforts to learn image-adaptive output color values of LUTs for flexible enhancement but neglect the importance of sampling strategy. They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform. Focusing on this problem, we present AdaInt (Adaptive Intervals Learning), a novel mechanism to achieve a more flexible sampling point allocation by adaptively learning the non-uniform sampling intervals in the 3D color space. In this way, a 3D LUT can increase its capability by conducting dense sampling in color ranges requiring highly non-linear transforms and sparse sampling for near-linear transforms. The proposed AdaInt could be implemented as a compact and efficient plug-and-play module for a 3D LUT-based method. To enable the end-to-end learning of AdaInt, we design a novel differentiable operator called AiLUT-Transform (Adaptive Interval LUT Transform) to locate input colors in the non-uniform 3D LUT and provide gradients to the sampling intervals. Experiments demonstrate that methods equipped with AdaInt can achieve state-of-the-art performance on two public benchmark datasets with a negligible overhead increase. Our source code is available at https://github.com/ImCharlesY/AdaInt.

Xiaohong Liu, Xiongkuo Min, Wei Sun et al. · eth-zurich

This paper reports on the NTIRE 2023 Quality Assessment of Video Enhancement Challenge, which will be held in conjunction with the New Trends in Image Restoration and Enhancement Workshop (NTIRE) at CVPR 2023. This challenge is to address a major challenge in the field of video processing, namely, video quality assessment (VQA) for enhanced videos. The challenge uses the VQA Dataset for Perceptual Video Enhancement (VDPVE), which has a total of 1211 enhanced videos, including 600 videos with color, brightness, and contrast enhancements, 310 videos with deblurring, and 301 deshaked videos. The challenge has a total of 167 registered participants. 61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions. A total of 176 submissions were submitted by 37 participating teams during the final testing phase. Finally, 19 participating teams submitted their models and fact sheets, and detailed the methods they used. Some methods have achieved better results than baseline methods, and the winning methods have demonstrated superior prediction performance.

Jie Song, Ying Chen, Jingwen Ye et al.

Knowledge distillation (KD) has become a well established paradigm for compressing deep neural networks. The typical way of conducting knowledge distillation is to train the student network under the supervision of the teacher network to harness the knowledge at one or multiple spots (i.e., layers) in the teacher network. The distillation spots, once specified, will not change for all the training samples, throughout the whole distillation process. In this work, we argue that distillation spots should be adaptive to training samples and distillation epochs. We thus propose a new distillation strategy, termed spot-adaptive KD (SAKD), to adaptively determine the distillation spots in the teacher network per sample, at every training iteration during the whole distillation period. As SAKD actually focuses on "where to distill" instead of "what to distill" that is widely investigated by most existing works, it can be seamlessly integrated into existing distillation methods to further improve their performance. Extensive experiments with 10 state-of-the-art distillers are conducted to demonstrate the effectiveness of SAKD for improving their distillation performance, under both homogeneous and heterogeneous distillation settings. Code is available at https://github.com/zju-vipa/spot-adaptive-pytorch

Meisong Zheng, Qunliang Xing, Minglang Qiao et al.

As a widely studied task, video restoration aims to enhance the quality of the videos with multiple potential degradations, such as noises, blurs and compression artifacts. Among video restorations, compressed video quality enhancement and video super-resolution are two of the main tacks with significant values in practical scenarios. Recently, recurrent neural networks and transformers attract increasing research interests in this field, due to their impressive capability in sequence-to-sequence modeling. However, the training of these models is not only costly but also relatively hard to converge, with gradient exploding and vanishing problems. To cope with these problems, we proposed a two-stage framework including a multi-frame recurrent network and a single-frame transformer. Besides, multiple training strategies, such as transfer learning and progressive training, are developed to shorten the training time and improve the model performance. Benefiting from the above technical contributions, our solution wins two champions and a runner-up in the NTIRE 2022 super-resolution and quality enhancement of compressed video challenges. Code is available at https://github.com/ryanxingql/winner-ntire22-vqe.

Team Seedance, De Chen, Liyang Chen et al. · gatech

Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale architecture for multi-modal audio-video joint generation. This allows it to support four input modalities: text, image, audio, and video, by integrating one of the most comprehensive suites of multi-modal content reference and editing capabilities available in the industry to date. It delivers substantial, well-rounded improvements across all key sub-dimensions of video and audio generation. In both expert evaluations and public user tests, the model has demonstrated performance on par with the leading levels in the field. Seedance 2.0 supports direct generation of audio-video content with durations ranging from 4 to 15 seconds, with native output resolutions of 480p and 720p. For multi-modal inputs as reference, its current open platform supports up to 3 video clips, 9 images, and 3 audio clips. In addition, we provide Seedance 2.0 Fast version, an accelerated variant of Seedance 2.0 designed to boost generation speed for low-latency scenarios. Seedance 2.0 has delivered significant improvements to its foundational generation capabilities and multi-modal generation performance, bringing an enhanced creative experience for end users.

Ying Chen, Liang Qiao, Zhanzhan Cheng et al.

End-to-end text spotting has attached great attention recently due to its benefits on global optimization and high maintainability for real applications. However, the input scale has always been a tough trade-off since recognizing a small text instance usually requires enlarging the whole image, which brings high computational costs. In this paper, to address this problem, we propose a novel cost-efficient Dynamic Low-resolution Distillation (DLD) text spotting framework, which aims to infer images in different small but recognizable resolutions and achieve a better balance between accuracy and efficiency. Concretely, we adopt a resolution selector to dynamically decide the input resolutions for different images, which is constraint by both inference accuracy and computational cost. Another sequential knowledge distillation strategy is conducted on the text recognition branch, making the low-res input obtains comparable performance to a high-res image. The proposed method can be optimized end-to-end and adopted in any current text spotting framework to improve the practicability. Extensive experiments on several text spotting benchmarks show that the proposed method vastly improves the usability of low-res models. The code is available at https://github.com/hikopensource/DAVAR-Lab-OCR/.

Xin Li, Jiachao Gong, Xijun Wang et al.

This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-UGC) video restoration benchmark, termed KwaiVIR, which is contributed by USTC and Kuaishou Technology. It contains both synthetically distorted videos and real-world short-form UGC videos in the wild. For this edition, the released data include 200 synthetic training videos, 48 wild training videos, 11 validation videos, and 20 testing videos. The primary goal of this challenge is to establish a strong and practical benchmark for restoring short-form UGC videos under complex real-world degradations, especially in the emerging paradigm of generative-model-based S-UGC video restoration. This challenge has two tracks: (i) the primary track is a subjective track, where the evaluation is based on a user study; (ii) the second track is an objective track. These two tracks enable a comprehensive assessment of restoration quality. In total, 95 teams have registered for this competition. And 12 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the KwaiVIR benchmark, demonstrating encouraging progress in short-form UGC video restoration in the wild.

Xinyu Xiong, Zihuang Wu, Shuangyi Tan et al.

Image segmentation plays an important role in vision understanding. Recently, the emerging vision foundation models continuously achieved superior performance on various tasks. Following such success, in this paper, we prove that the Segment Anything Model 2 (SAM2) can be a strong encoder for U-shaped segmentation models. We propose a simple but effective framework, termed SAM2-UNet, for versatile image segmentation. Specifically, SAM2-UNet adopts the Hiera backbone of SAM2 as the encoder, while the decoder uses the classic U-shaped design. Additionally, adapters are inserted into the encoder to allow parameter-efficient fine-tuning. Preliminary experiments on various downstream tasks, such as camouflaged object detection, salient object detection, marine animal segmentation, mirror detection, and polyp segmentation, demonstrate that our SAM2-UNet can simply beat existing specialized state-of-the-art methods without bells and whistles. Project page: \url{https://github.com/WZH0120/SAM2-UNet}.

Zicheng Zhang, Wei Wu, Wei Sun et al.

User-generated content (UGC) live videos are often bothered by various distortions during capture procedures and thus exhibit diverse visual qualities. Such source videos are further compressed and transcoded by media server providers before being distributed to end-users. Because of the flourishing of UGC live videos, effective video quality assessment (VQA) tools are needed to monitor and perceptually optimize live streaming videos in the distributing process. In this paper, we address \textbf{UGC Live VQA} problems by constructing a first-of-a-kind subjective UGC Live VQA database and developing an effective evaluation tool. Concretely, 418 source UGC videos are collected in real live streaming scenarios and 3,762 compressed ones at different bit rates are generated for the subsequent subjective VQA experiments. Based on the built database, we develop a \underline{M}ulti-\underline{D}imensional \underline{VQA} (\textbf{MD-VQA}) evaluator to measure the visual quality of UGC live videos from semantic, distortion, and motion aspects respectively. Extensive experimental results show that MD-VQA achieves state-of-the-art performance on both our UGC Live VQA database and existing compressed UGC VQA databases.

Juncheng Li, Bodong Cheng, Ying Chen et al.

Transformer-based image denoising methods have achieved encouraging results in the past year. However, it must uses linear operations to model long-range dependencies, which greatly increases model inference time and consumes GPU storage space. Compared with convolutional neural network-based methods, current Transformer-based image denoising methods cannot achieve a balance between performance improvement and resource consumption. In this paper, we propose an Efficient Wavelet Transformer (EWT) for image denoising. Specifically, we use Discrete Wavelet Transform (DWT) and Inverse Wavelet Transform (IWT) for downsampling and upsampling, respectively. This method can fully preserve the image features while reducing the image resolution, thereby greatly reducing the device resource consumption of the Transformer model. Furthermore, we propose a novel Dual-stream Feature Extraction Block (DFEB) to extract image features at different levels, which can further reduce model inference time and GPU memory usage. Experiments show that our method speeds up the original Transformer by more than 80%, reduces GPU memory usage by more than 60%, and achieves excellent denoising results. All code will be public.

Liang Qiao, Hui Jiang, Ying Chen et al.

This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms. DavarOCR provides detailed usage instructions and the trained models for each algorithm. Compared with the previous opensource OCR toolbox, DavarOCR has relatively more complete support for the sub-tasks of the cutting-edge technology of document understanding. In order to promote the development and application of OCR technology in academia and industry, we pay more attention to the use of modules that different sub-domains of technology can share. DavarOCR is publicly released at https://github.com/hikopensource/Davar-Lab-OCR.

Dihe Huang, Ying Chen, Yikang Ding et al.

Bird's eye view (BEV) is widely adopted by most of the current point cloud detectors due to the applicability of well-explored 2D detection techniques. However, existing methods obtain BEV features by simply collapsing voxel or point features along the height dimension, which causes the heavy loss of 3D spatial information. To alleviate the information loss, we propose a novel point cloud detection network based on a Multi-level feature dimensionality reduction strategy, called MDRNet. In MDRNet, the Spatial-aware Dimensionality Reduction (SDR) is designed to dynamically focus on the valuable parts of the object during voxel-to-BEV feature transformation. Furthermore, the Multi-level Spatial Residuals (MSR) is proposed to fuse the multi-level spatial information in the BEV feature maps. Extensive experiments on nuScenes show that the proposed method outperforms the state-of-the-art methods. The code will be available upon publication.

Zhongying Deng, Cheng Tang, Ziyan Huang et al. · pku

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

Bodong Cheng, Juncheng Li, Ying Chen et al.

Image restoration under severe weather is a challenging task. Most of the past works focused on removing rain and haze phenomena in images. However, snow is also an extremely common atmospheric phenomenon that will seriously affect the performance of high-level computer vision tasks, such as object detection and semantic segmentation. Recently, some methods have been proposed for snow removing, and most methods deal with snow images directly as the optimization object. However, the distribution of snow location and shape is complex. Therefore, failure to detect snowflakes / snow streak effectively will affect snow removing and limit the model performance. To solve these issues, we propose a Snow Mask Guided Adaptive Residual Network (SMGARN). Specifically, SMGARN consists of three parts, Mask-Net, Guidance-Fusion Network (GF-Net), and Reconstruct-Net. Firstly, we build a Mask-Net with Self-pixel Attention (SA) and Cross-pixel Attention (CA) to capture the features of snowflakes and accurately localized the location of the snow, thus predicting an accurate snow mask. Secondly, the predicted snow mask is sent into the specially designed GF-Net to adaptively guide the model to remove snow. Finally, an efficient Reconstruct-Net is used to remove the veiling effect and correct the image to reconstruct the final snow-free image. Extensive experiments show that our SMGARN numerically outperforms all existing snow removal methods, and the reconstructed images are clearer in visual contrast. All codes will be available.

Lai Wei, Zhen Ying, Muyang He et al.

Diabetes is a chronic disease with a significant global health burden, requiring multi-stakeholder collaboration for optimal management. Large language models (LLMs) have shown promise in various healthcare scenarios, but their effectiveness across diverse diabetes tasks remains unproven. Our study introduced a framework to train and validate diabetes-specific LLMs. We first developed a comprehensive data processing pipeline that includes data collection, filtering, augmentation and refinement. This created a high-quality, diabetes-specific dataset and evaluation benchmarks from scratch. Fine-tuned on the collected training dataset, our diabetes-specific LLM family demonstrated state-of-the-art proficiency in processing various diabetes tasks compared to other LLMs. Furthermore, clinical studies revealed the potential applications of our models in diabetes care, including providing personalized healthcare, assisting medical education, and streamlining clinical tasks. Generally, our introduced framework helps develop diabetes-specific LLMs and highlights their potential to enhance clinical practice and provide personalized, data-driven support for diabetes management across different end users. Our codes, benchmarks and models are available at https://github.com/waltonfuture/Diabetica.

Lijie Wang, Yaozong Shen, Shuyuan Peng et al.

While there is increasing concern about the interpretability of neural models, the evaluation of interpretability remains an open problem, due to the lack of proper evaluation datasets and metrics. In this paper, we present a novel benchmark to evaluate the interpretability of both neural models and saliency methods. This benchmark covers three representative NLP tasks: sentiment analysis, textual similarity and reading comprehension, each provided with both English and Chinese annotated data. In order to precisely evaluate the interpretability, we provide token-level rationales that are carefully annotated to be sufficient, compact and comprehensive. We also design a new metric, i.e., the consistency between the rationales before and after perturbations, to uniformly evaluate the interpretability on different types of tasks. Based on this benchmark, we conduct experiments on three typical models with three saliency methods, and unveil their strengths and weakness in terms of interpretability. We will release this benchmark https://www.luge.ai/#/luge/task/taskDetail?taskId=15 and hope it can facilitate the research in building trustworthy systems.

Zicheng Zhang, Wei Sun, Wei Wu et al.

Recent years have witnessed the rapid development of image storage and transmission systems, in which image compression plays an important role. Generally speaking, image compression algorithms are developed to ensure good visual quality at limited bit rates. However, due to the different compression optimization methods, the compressed images may have different levels of quality, which needs to be evaluated quantificationally. Nowadays, the mainstream full-reference (FR) metrics are effective to predict the quality of compressed images at coarse-grained levels (the bit rates differences of compressed images are obvious), however, they may perform poorly for fine-grained compressed images whose bit rates differences are quite subtle. Therefore, to better improve the Quality of Experience (QoE) and provide useful guidance for compression algorithms, we propose a full-reference image quality assessment (FR-IQA) method for compressed images of fine-grained levels. Specifically, the reference images and compressed images are first converted to $YCbCr$ color space. The gradient features are extracted from regions that are sensitive to compression artifacts. Then we employ the Log-Gabor transformation to further analyze the texture difference. Finally, the obtained features are fused into a quality score. The proposed method is validated on the fine-grained compression image quality assessment (FGIQA) database, which is especially constructed for assessing the quality of compressed images with close bit rates. The experimental results show that our metric outperforms mainstream FR-IQA metrics on the FGIQA database. We also test our method on other commonly used compression IQA databases and the results show that our method obtains competitive performance on the coarse-grained compression IQA databases as well.

Yuepeng Wang, Ken Kawano, Yongqi Zhou et al.

Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals. Existing RL formulations and simulated environments, however, are based on discrete-time MDP or POMDP abstractions with fixed or pre-specified decision intervals. Thus, it remains difficult to evaluate whether RL methods can handle time-interval-dependent disease progression, personalized treatment response, and safety between consecutive measurement points. To address this gap, we introduce MedGym, a benchmark environment for dynamic treatment recommendation. MedGym models longitudinal patient evolution in a continuous-time framework and constructs a configurable medical RL benchmark from clinical data by using Physics-Informed Neural Networks. The resulting benchmark supports both offline and online RL, and enables direct comparison between discrete-time and continuous-time methods under irregular treatment timing and patient-specific dynamics. Besides, MedGym supports evaluation from clinically important perspectives, including personalization, trajectory-level safety, and the performance gap between model-based offline learning and online deployment. By providing a standardized and configurable benchmark for continuous-time dynamic treatment, MedGym aims to facilitate more realistic and informative evaluation of medical RL methods.

Xun Shen, Yuepeng Wang, Akifumi Wachi et al.

Dynamic medical treatment requires deciding treatment intensity and intervention timing, while patient states evolve continuously and adverse events may occur between clinical interactions. Most existing treatment learning methods assume fixed schedules or enforce safety only at discrete decision points. We propose Interaction-Limited Safe Continuous-Time Reinforcement Learning, a framework that jointly optimizes treatment administration and clinical interaction timing under trajectory-level safety constraints. Our key idea is to reformulate the continuous time treatment problem as an option-based semi-Markov decision process, where each option specifies a continuous-time treatment policy and its duration. We develop a safety-tightening mechanism showing that suitably constructed constraints at interaction times guarantee safety over the full continuous-time trajectory with high probability. We further establish finite-sample guarantees for policy learning from logged treatment trajectories and introduce a practical data-driven conservative surrogate. Experiments show that the proposed adaptive interaction-timing mechanism improves both safety and treatment effectiveness over equidistant interaction schemes across different safe policy optimization methods.

Dennis Thumm, Ruben Wiedemann, Ying Chen

Extending discrete-time causal Prior-data Fitted Networks for time series to continuous time invites writing the mechanism as a stochastic differential equation (SDE) -- but if the SDE is integrated \emph{once per observation gap}, the trajectory law depends on when it is observed, and the prior remains a discrete-time Markov model in SDE clothing. We propose a precise continuity criterion -- trajectory-law invariance to the observation schedule -- together with a three-tier taxonomy (discrete; naive observation-grid integration; fine-grid integration with decoupled observation) and a construction realising the top tier on a random DAG with OU or small-MLP nonlinear drifts, irregular observation schedules, and hard / soft / time-varying interventions. A $2 \times 2$ encoder $\times$ integrator ablation, run independently on a linear and a nonlinear prior, finds fine-grid integration beats naive on 8/8 cells (sign-consistency $p < 1/256$) with the gap growing as the eval grid refines; the encoder axis is null with fine integration but time-aware-leading with naive. We release the prior and a preliminary zero-shot protocol on pharmacokinetic and physical-system data.

Jianlin Liu, Zhuofei Huang, Dihe Huang et al.

3D object detection from monocular image(s) is a challenging and long-standing problem of computer vision. To combine information from different perspectives without troublesome 2D instance tracking, recent methods tend to aggregate multiview feature by sampling regular 3D grid densely in space, which is inefficient. In this paper, we attempt to improve multi-view feature aggregation by proposing a learnable keypoints sampling method, which scatters pseudo surface points in 3D space, in order to keep data sparsity. The scattered points augmented by multi-view geometric constraints and visual features are then employed to infer objects location and shape in the scene. To make up the limitations of single frame and model multi-view geometry explicitly, we further propose a surface filter module for noise suppression. Experimental results show that our method achieves significantly better performance than previous works in terms of 3D detection (more than 0.1 AP improvement on some categories of ScanNet). The code will be publicly available.

Zhuoqun Liu, Meiguang Jin, Ying Chen et al.

Deep convolutional neural networks have achieved great progress in image denoising tasks. However, their complicated architectures and heavy computational cost hinder their deployments on mobile devices. Some recent efforts in designing lightweight denoising networks focus on reducing either FLOPs (floating-point operations) or the number of parameters. However, these metrics are not directly correlated with the on-device latency. In this paper, we identify the real bottlenecks that affect the CNN-based models' run-time performance on mobile devices: memory access cost and NPU-incompatible operations, and build the model based on these. To further improve the denoising performance, the mobile-friendly attention module MFA and the model reparameterization module RepConv are proposed, which enjoy both low latency and excellent denoising performance. To this end, we propose a mobile-friendly denoising network, namely MFDNet. The experiments show that MFDNet achieves state-of-the-art performance on real-world denoising benchmarks SIDD and DND under real-time latency on mobile devices. The code and pre-trained models will be released.

Ying Chen, Siwei Qiang, Mingming Ha et al.

In recent years, semi-supervised graph learning with data augmentation (DA) is currently the most commonly used and best-performing method to enhance model robustness in sparse scenarios with few labeled samples. Differing from homogeneous graph, DA in heterogeneous graph has greater challenges: heterogeneity of information requires DA strategies to effectively handle heterogeneous relations, which considers the information contribution of different types of neighbors and edges to the target nodes. Furthermore, over-squashing of information is caused by the negative curvature that formed by the non-uniformity distribution and strong clustering in complex graph. To address these challenges, this paper presents a novel method named Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentation (HG-MDA). For the problem of heterogeneity of information in DA, node and topology augmentation strategies are proposed for the characteristics of heterogeneous graph. And meta-relation-based attention is applied as one of the indexes for selecting augmented nodes and edges. For the problem of over-squashing of information, triangle based edge adding and removing are designed to alleviate the negative curvature and bring the gain of topology. Finally, the loss function consists of the cross-entropy loss for labeled data and the consistency regularization for unlabeled data. In order to effectively fuse the prediction results of various DA strategies, the sharpening is used. Existing experiments on public datasets, i.e., ACM, DBLP, OGB, and industry dataset MB show that HG-MDA outperforms current SOTA models. Additionly, HG-MDA is applied to user identification in internet finance scenarios, helping the business to add 30% key users, and increase loans and balances by 3.6%, 11.1%, and 9.8%.

Xuechao Chen, Ying Chen, Jialin Li et al.

3D pre-training is crucial to 3D perception tasks. Nevertheless, limited by the difficulties in collecting clean and complete 3D data, 3D pre-training has persistently faced data scaling challenges. In this work, we introduce a novel self-supervised pre-training framework that incorporates millions of images into 3D pre-training corpora by leveraging a large depth estimation model. New pre-training corpora encounter new challenges in representation ability and embedding efficiency of models. Previous pre-training methods rely on farthest point sampling and k-nearest neighbors to embed a fixed number of 3D tokens. However, these approaches prove inadequate when it comes to embedding millions of samples that feature a diverse range of point numbers, spanning from 1,000 to 100,000. In contrast, we propose a tokenizer with linear-time complexity, which enables the efficient embedding of a flexible number of tokens. Accordingly, a new 3D reconstruction target is proposed to cooperate with our 3D tokenizer. Our method achieves state-of-the-art performance in 3D classification, few-shot learning, and 3D segmentation. Code is available at https://github.com/XuechaoChen/P3P-MAE.

Jiajun Zhu, Ying Chen, Peihao Wang et al.

Graph foundation models (GFMs) aim to reuse a single backbone across diverse graph domains, yet their transfer is often uneven and can exhibit negative transfer. While most prior work improves transfer through architectural or adaptation choices, we ask a data-centric question: which properties of two graph domains determine how much a fixed representation model changes its outputs? Using a graphon-based continuous limit for dense graphs, we show that for both set-based and message-passing tokenizations, any Lipschitz backbone admits an explicit decomposition of cross-domain output shift into (i) graph-specific finite-sample approximation terms and (ii) an intrinsic, relabeling-invariant domain discrepancy capturing structural mismatch. A key ingredient is positional-encoding (PE) stability: we establish stability guarantees for spectral PEs and highlight contrasting behaviors of eigenvector- versus subspace-based PEs. Experiments on synthetic and real graphs validate the theory and translate the decomposition into guidance for data curation in GFM transfer.

Chong Li, Zhun Fan, Ying Chen et al.

Automatic pavement crack detection is an important task to ensure the functional performances of pavements during their service life. Inspired by deep learning (DL), the encoder-decoder framework is a powerful tool for crack detection. However, these models are usually open-loop (OL) systems that tend to treat thin cracks as the background. Meanwhile, these models can not automatically correct errors in the prediction, nor can it adapt to the changes of the environment to automatically extract and detect thin cracks. To tackle this problem, we embed closed-loop feedback (CLF) into the neural network so that the model could learn to correct errors on its own, based on generative adversarial networks (GAN). The resulting model is called CrackCLF and includes the front and back ends, i.e. segmentation and adversarial network. The front end with U-shape framework is employed to generate crack maps, and the back end with a multi-scale loss function is used to correct higher-order inconsistencies between labels and crack maps (generated by the front end) to address open-loop system issues. Empirical results show that the proposed CrackCLF outperforms others methods on three public datasets. Moreover, the proposed CLF can be defined as a plug and play module, which can be embedded into different neural network models to improve their performances.

Siyuan Zhang, Linbo Xie, Ying Chen

In the past few years, Softmax has become a common component in neural network frameworks. In this paper, a gradient decay hyperparameter is introduced in Softmax to control the probability-dependent gradient decay rate during training. By following the theoretical analysis and empirical results of a variety of model architectures trained on MNIST, CIFAR-10/100 and SVHN, we find that the generalization performance depends significantly on the gradient decay rate as the confidence probability rises, i.e., the gradient decreases convexly or concavely as the sample probability increases. Moreover, optimization with the small gradient decay shows a similar curriculum learning sequence where hard samples are in the spotlight only after easy samples are convinced sufficiently, and well-separated samples gain a higher gradient to reduce intra-class distance. Based on the analysis results, we can provide evidence that the large margin Softmax will affect the local Lipschitz constraint of the loss function by regulating the probability-dependent gradient decay rate. This paper provides a new perspective and understanding of the relationship among concepts of large margin Softmax, local Lipschitz constraint and curriculum learning by analyzing the gradient decay rate. Besides, we propose a warm-up strategy to dynamically adjust Softmax loss in training, where the gradient decay rate increases from over-small to speed up the convergence rate.

Zehao Zhu, Wei Sun, Jun Jia et al.

In recent years, live video streaming has gained widespread popularity across various social media platforms. Quality of experience (QoE), which reflects end-users' satisfaction and overall experience, plays a critical role for media service providers to optimize large-scale live compression and transmission strategies to achieve perceptually optimal rate-distortion trade-off. Although many QoE metrics for video-on-demand (VoD) have been proposed, there remain significant challenges in developing QoE metrics for live video streaming. To bridge this gap, we conduct a comprehensive study of subjective and objective QoE evaluations for live video streaming. For the subjective QoE study, we introduce the first live video streaming QoE dataset, TaoLive QoE, which consists of $42$ source videos collected from real live broadcasts and $1,155$ corresponding distorted ones degraded due to a variety of streaming distortions, including conventional streaming distortions such as compression, stalling, as well as live streaming-specific distortions like frame skipping, variable frame rate, etc. Subsequently, a human study was conducted to derive subjective QoE scores of videos in the TaoLive QoE dataset. For the objective QoE study, we benchmark existing QoE models on the TaoLive QoE dataset as well as publicly available QoE datasets for VoD scenarios, highlighting that current models struggle to accurately assess video QoE, particularly for live content. Hence, we propose an end-to-end QoE evaluation model, Tao-QoE, which integrates multi-scale semantic features and optical flow-based motion features to predicting a retrospective QoE score, eliminating reliance on statistical quality of service (QoS) features.

Haifeng Wang, Hua Wu, Tian Wu et al.

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

Canqian Yang, Meiguang Jin, Yi Xu et al.

Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms. However, they embed the complete transform, including the color component-independent and the component-correlated parts, into only a single type of LUTs, either 1D or 3D, in a coupled manner. This scheme raises a dilemma of improving model expressiveness or efficiency due to two factors. On the one hand, the 1D LUTs provide high computational efficiency but lack the critical capability of color components interaction. On the other, the 3D LUTs present enhanced component-correlated transform capability but suffer from heavy memory footprint, high training difficulty, and limited cell utilization. Inspired by the conventional divide-and-conquer practice in the image signal processor, we present SepLUT (separable image-adaptive lookup table) to tackle the above limitations. Specifically, we separate a single color transform into a cascade of component-independent and component-correlated sub-transforms instantiated as 1D and 3D LUTs, respectively. In this way, the capabilities of two sub-transforms can facilitate each other, where the 3D LUT complements the ability to mix up color components, and the 1D LUT redistributes the input colors to increase the cell utilization of the 3D LUT and thus enable the use of a more lightweight 3D LUT. Experiments demonstrate that the proposed method presents enhanced performance on photo retouching benchmark datasets than the current state-of-the-art and achieves real-time processing on both GPUs and CPUs.

Runpeng Geng, Yanting Wang, Chenlong Yin et al.

Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an attacker-desired output. Existing prompt injection defenses are designed for short contexts. When extended to long-context scenarios, they have limited effectiveness. The reason is that an injected instruction constitutes only a very small portion of a long context, making the defense very challenging. In this work, we propose PISanitizer, which first pinpoints and sanitizes potential injected tokens (if any) in a context before letting a backend LLM generate a response, thereby eliminating the influence of the injected instruction. To sanitize injected tokens, PISanitizer builds on two observations: (1) prompt injection attacks essentially craft an instruction that compels an LLM to follow it, and (2) LLMs intrinsically leverage the attention mechanism to focus on crucial input tokens for output generation. Guided by these two observations, we first intentionally let an LLM follow arbitrary instructions in a context and then sanitize tokens receiving high attention that drive the instruction-following behavior of the LLM. By design, PISanitizer presents a dilemma for an attacker: the more effectively an injected instruction compels an LLM to follow it, the more likely it is to be sanitized by PISanitizer. Our extensive evaluation shows that PISanitizer can successfully prevent prompt injection, maintain utility, outperform existing defenses, is efficient, and is robust to optimization-based and strong adaptive attacks. The code is available at https://github.com/sleeepeer/PISanitizer.

Yapeng Cui, Ruoxi Yun, Shumin Zhang et al.

Response variability limits the clinical utility of transcutaneous auricular vagus nerve stimulation (taVNS) for negative symptoms in treatment-resistant schizophrenia (TRS). This study aimed to develop an electroencephalography (EEG)-based machine learning (ML) model to predict individual response and explore associated neurophysiological mechanisms. We used ML to develop and validate predictive models based on pre-treatment EEG data features (power, coherence, and dynamic functional connectivity) from 50 TRS patients enrolled in the taVNS trial, within a nested cross-validation framework. Participants received 20 sessions of active or sham taVNS (n = 25 each) over two weeks, followed by a two-week follow-up. The prediction target was the percentage change in the positive and negative syndrome scale-factor score for negative symptoms (PANSS-FSNS) from baseline to post-treatment, with further evaluation of model specificity and neurophysiological relevance.The optimal model accurately predicted taVNS response in the active group, with predicted PANSS-FSNS changes strongly correlated with observed changes (r = 0.87, p < .001); permutation testing confirmed performance above chance (p < .001). Nine consistently retained features were identified, predominantly fronto-parietal and fronto-temporal coherence features. Negligible predictive performance in the sham group and failure to predict positive symptom change support the predictive specificity of this oscillatory signature for taVNS-related negative symptom improvement. Two coherence features within fronto-parietal-temporal networks showed post-taVNS changes significantly associated with symptom improvement, suggesting dual roles as predictors and potential therapeutic targets. EEG oscillatory neuromarkers enable accurate prediction of individual taVNS response in TRS, supporting mechanism-informed precision neuromodulation strategies.

Yaozong Shen, Lijie Wang, Ying Chen et al.

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain capability with some downstream tasks. There is a lack of datasets for directly evaluating the masked word prediction performance and the interpretability of pre-trained LMs. To fill in the gap, we propose a novel evaluation benchmark providing with both English and Chinese annotated data. It tests LMs abilities in multiple dimensions, i.e., grammar, semantics, knowledge, reasoning and computation. In addition, it provides carefully annotated token-level rationales that satisfy sufficiency and compactness. It contains perturbed instances for each original instance, so as to use the rationale consistency under perturbations as the metric for faithfulness, a perspective of interpretability. We conduct experiments on several widely-used pre-trained LMs. The results show that they perform very poorly on the dimensions of knowledge and computation. And their plausibility in all dimensions is far from satisfactory, especially when the rationale is short. In addition, the pre-trained LMs we evaluated are not robust on syntax-aware data. We will release this evaluation benchmark at \url{http://xyz}, and hope it can facilitate the research progress of pre-trained LMs.

Zhengyang Lu, Ying Chen

Significant attention has been attracted to deep learning-based depth estimates. Dynamic objects become the most hard problems in inter-frame-supervised depth estimates due to the uncertainty in adjacent frames. Thus, integrating optical flow information with depth estimation is a feasible solution, as the optical flow is an essential motion representation. In this work, we construct a joint inter-frame-supervised depth and optical flow estimation framework, which predicts depths in various motions by minimizing pixel wrap errors in bilateral photometric re-projections and optical vectors. For motion segmentation, we adaptively segment the preliminary estimated optical flow map with large areas of connectivity. In self-supervised depth estimation, different motion regions are predicted independently and then composite into a complete depth. Further, the pose and depth estimations re-synthesize the optical flow maps, serving to compute reconstruction errors with the preliminary predictions. Our proposed joint depth and optical flow estimation outperforms existing depth estimators on the KITTI Depth dataset, both with and without Cityscapes pretraining. Additionally, our optical flow results demonstrate competitive performance on the KITTI Flow 2015 dataset.

Yunpeng Qu, Kaidong Zhang, Yukang Ding et al.

Visual generative models based on latent space have achieved great success, underscoring the significance of visual tokenization. Mapping images to latents boosts efficiency and enables multimodal alignment for scaling up in downstream tasks. Existing visual tokenizers primarily map images into fixed 2D spatial grids and focus on pixel-level restoration, which hinders the capture of representations with compact global semantics. To address these issues, we propose \textbf{SemTok}, a semantic one-dimensional tokenizer that compresses 2D images into 1D discrete tokens with high-level semantics. SemTok sets a new state-of-the-art in image reconstruction, achieving superior fidelity with a remarkably compact token representation. This is achieved via a synergistic framework with three key innovations: a 2D-to-1D tokenization scheme, a semantic alignment constraint, and a two-stage generative training strategy. Building on SemTok, we construct a masked autoregressive generation framework, which yields notable improvements in downstream image generation tasks. Experiments confirm the effectiveness of our semantic 1D tokenization. Our code will be open-sourced.

Lingfeng Shen, Ze Zhang, Haiyun Jiang et al.

Adversarial attack serves as a major challenge for neural network models in NLP, which precludes the model's deployment in safety-critical applications. A recent line of work, detection-based defense, aims to distinguish adversarial sentences from benign ones. However, {the core limitation of previous detection methods is being incapable of giving correct predictions on adversarial sentences unlike defense methods from other paradigms.} To solve this issue, this paper proposes TextShield: (1) we discover a link between text attack and saliency information, and then we propose a saliency-based detector, which can effectively detect whether an input sentence is adversarial or not. (2) We design a saliency-based corrector, which converts the detected adversary sentences to benign ones. By combining the saliency-based detector and corrector, TextShield extends the detection-only paradigm to a detection-correction paradigm, thus filling the gap in the existing detection-based defense. Comprehensive experiments show that (a) TextShield consistently achieves higher or comparable performance than state-of-the-art defense methods across various attacks on different benchmarks. (b) our saliency-based detector outperforms existing detectors for detecting adversarial sentences.

Yu Lu, Yi-Jia Wang, Ying Chen et al.

We present that by predicting the spectrum in discrete space from the phase shift in continuous space, the neural network can remarkably reproduce the numerical Lüscher's formula to a high precision. The model-independent property of the Lüscher's formula is naturally realized by the generalizability of the neural network. This exhibits the great potential of the neural network to extract model-independent relation between model-dependent quantities, and this data-driven approach could greatly facilitate the discovery of the physical principles underneath the intricate data.

Wanghan Xu, Yuhao Zhou, Yifan Zhou et al.

Despite advances in scientific AI, a coherent framework for Scientific General Intelligence (SGI)-the ability to autonomously conceive, investigate, and reason across scientific domains-remains lacking. We present an operational SGI definition grounded in the Practical Inquiry Model (PIM: Deliberation, Conception, Action, Perception) and operationalize it via four scientist-aligned tasks: deep research, idea generation, dry/wet experiments, and experimental reasoning. SGI-Bench comprises over 1,000 expert-curated, cross-disciplinary samples inspired by Science's 125 Big Questions, enabling systematic evaluation of state-of-the-art LLMs. Results reveal gaps: low exact match (10--20%) in deep research despite step-level alignment; ideas lacking feasibility and detail; high code executability but low execution result accuracy in dry experiments; low sequence fidelity in wet protocols; and persistent multimodal comparative-reasoning challenges. We further introduce Test-Time Reinforcement Learning (TTRL), which optimizes retrieval-augmented novelty rewards at inference, enhancing hypothesis novelty without reference answer. Together, our PIM-grounded definition, workflow-centric benchmark, and empirical insights establish a foundation for AI systems that genuinely participate in scientific discovery.

Zhengyang Lu, Ying Chen

Deep-learning-based approaches to depth estimation are rapidly advancing, offering superior performance over existing methods. To estimate the depth in real-world scenarios, depth estimation models require the robustness of various noise environments. In this work, a Pyramid Frequency Network(PFN) with Spatial Attention Residual Refinement Module(SARRM) is proposed to deal with the weak robustness of existing deep-learning methods. To reconstruct depth maps with accurate details, the SARRM constructs a residual fusion method with an attention mechanism to refine the blur depth. The frequency division strategy is designed, and the frequency pyramid network is developed to extract features from multiple frequency bands. With the frequency strategy, PFN achieves better visual accuracy than state-of-the-art methods in both indoor and outdoor scenes on Make3D, KITTI depth, and NYUv2 datasets. Additional experiments on the noisy NYUv2 dataset demonstrate that PFN is more reliable than existing deep-learning methods in high-noise scenes.

Jevin Jiang, Ying Chen, Blake A. Hechtman et al.

Large Language Model (LLM) deployment is increasingly shifting to cost-efficient accelerators like Google's Tensor Processing Units (TPUs), prioritizing both performance and total cost of ownership (TCO). However, existing LLM inference kernels and serving systems remain largely GPU-centric, and there is no well-established approach for efficiently mapping LLM workloads onto TPU architectures--particularly under the dynamic and ragged execution patterns common in modern serving. In this paper, we present Ragged Paged Attention (RPA), a high-performance and flexible attention kernel for TPUs, implemented using Pallas and Mosaic. RPA addresses these challenges through three key techniques: (1) fine-grained tiling to enable efficient dynamic slicing over ragged memory, (2) a custom software pipeline that fuses KV cache updates with attention computation, and (3) a distribution-aware compilation strategy that generates specialized kernels for decode, prefill, and mixed workloads. Evaluated on Llama 3 8B on TPU7x, RPA achieves up to 86% memory bandwidth utilization (MBU) in decode and 73% model FLOPs utilization (MFU) in prefill. Integrated as the primary TPU backend in vLLM and SGLang, RPA provides a production-grade foundation for efficient TPU inference and offers practical insights into kernel design.

Jiaqi Liu, Kai Wu, Qiang Nie et al.

Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible. However, continual learning methods primarily rely on supervised annotations, while the application in UAD is limited due to the absence of supervision. Current UAD methods train separate models for different classes sequentially, leading to catastrophic forgetting and a heavy computational burden. To address this issue, we introduce a novel Unsupervised Continual Anomaly Detection framework called UCAD, which equips the UAD with continual learning capability through contrastively-learned prompts. In the proposed UCAD, we design a Continual Prompting Module (CPM) by utilizing a concise key-prompt-knowledge memory bank to guide task-invariant `anomaly' model predictions using task-specific `normal' knowledge. Moreover, Structure-based Contrastive Learning (SCL) is designed with the Segment Anything Model (SAM) to improve prompt learning and anomaly segmentation results. Specifically, by treating SAM's masks as structure, we draw features within the same mask closer and push others apart for general feature representations. We conduct comprehensive experiments and set the benchmark on unsupervised continual anomaly detection and segmentation, demonstrating that our method is significantly better than anomaly detection methods, even with rehearsal training. The code will be available at https://github.com/shirowalker/UCAD.

Xinyu Zhang, Weiyu Sun, Hao Lu et al.

Remote photoplethysmography (rPPG) is a noninvasive technique that aims to capture subtle variations in facial pixels caused by changes in blood volume resulting from cardiac activities. Most existing unsupervised methods for rPPG tasks focus on the contrastive learning between samples while neglecting the inherent self-similar prior in physiological signals. In this paper, we propose a Self-Similarity Prior Distillation (SSPD) framework for unsupervised rPPG estimation, which capitalizes on the intrinsic self-similarity of cardiac activities. Specifically, we first introduce a physical-prior embedded augmentation technique to mitigate the effect of various types of noise. Then, we tailor a self-similarity-aware network to extract more reliable self-similar physiological features. Finally, we develop a hierarchical self-distillation paradigm to assist the network in disentangling self-similar physiological patterns from facial videos. Comprehensive experiments demonstrate that the unsupervised SSPD framework achieves comparable or even superior performance compared to the state-of-the-art supervised methods. Meanwhile, SSPD maintains the lowest inference time and computation cost among end-to-end models.

Zitong Huang, Kaidong Zhang, Yukang Ding et al.

Aligning text-to-video diffusion models with human preferences is crucial for generating high-quality videos. Existing Direct Preference Otimization (DPO) methods rely on multi-sample ranking and task-specific critic models, which is inefficient and often yields ambiguous global supervision. To address these limitations, we propose LocalDPO, a novel post-training framework that constructs localized preference pairs from real videos and optimizes alignment at the spatio-temporal region level. We design an automated pipeline to efficiently collect preference pair data that generates preference pairs with a single inference per prompt, eliminating the need for external critic models or manual annotation. Specifically, we treat high-quality real videos as positive samples and generate corresponding negatives by locally corrupting them with random spatio-temporal masks and restoring only the masked regions using the frozen base model. During training, we introduce a region-aware DPO loss that restricts preference learning to corrupted areas for rapid convergence. Experiments on Wan2.1 and CogVideoX demonstrate that LocalDPO consistently improves video fidelity, temporal coherence and human preference scores over other post-training approaches, establishing a more efficient and fine-grained paradigm for video generator alignment.

Ruichuan An, Sihan Yang, Ming Lu et al.

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies investigate VLM personalization to understand user-provided concepts. However, they mainly focus on single-concept personalization, neglecting the existence and interplay of multiple concepts, which limits real-world applicability. This paper proposes the first multi-concept personalization paradigm, MC-LLaVA. Specifically, MC-LLaVA employs a multi-concept instruction tuning strategy, effectively integrating multiple concepts in a single training step. To reduce the costs related to joint training, we propose a personalized textual prompt that uses visual token information to initialize concept tokens. Additionally, we introduce a personalized visual prompt during inference, aggregating location confidence maps for enhanced recognition and grounding capabilities. To advance multi-concept personalization research, we further contribute a high-quality instruction tuning dataset. We carefully collect images with multiple characters and objects from movies and manually generate question-answer samples for multi-concept scenarios, featuring superior diversity. Comprehensive qualitative and quantitative experiments demonstrate that MC-LLaVA can achieve impressive multi-concept personalized responses, paving the way for VLMs to become better user-specific assistants. The code and dataset will be publicly available at https://github.com/arctanxarc/MC-LLaVA}.

Ruichuan An, Sihan Yang, Ming Lu et al.

Current vision-language models (VLMs) show exceptional abilities across diverse tasks, such as visual question answering. To enhance user experience, recent studies investigate VLM personalization to understand user-provided concepts. However, they mainly focus on single-concept personalization, neglecting the existence and interplay of multiple concepts, which limits real-world applicability. This paper proposes the first multi-concept personalization paradigm, MC-LLaVA. Specifically, MC-LLaVA employs a multi-concept instruction tuning strategy, effectively integrating multiple concepts in a single training step. To reduce the costs related to joint training, we propose a personalized textual prompt that uses visual token information to initialize concept tokens. Additionally, we introduce a personalized visual prompt during inference, aggregating location confidence maps for enhanced recognition and grounding capabilities. To advance multi-concept personalization research, we further contribute a high-quality instruction tuning dataset. We carefully collect images with multiple characters and objects from movies and manually generate question-answer samples for multi-concept scenarios, featuring superior diversity. Comprehensive qualitative and quantitative experiments demonstrate that MC-LLaVA can achieve impressive multi-concept personalized responses, paving the way for VLMs to become better user-specific assistants. The code and dataset will be publicly available at https://github.com/arctanxarc/MC-LLaVA.

Hao Li, Ying Chen, Yifei Chen et al.

Whole Slide Image (WSI) classification is often formulated as a Multiple Instance Learning (MIL) problem. Recently, Vision-Language Models (VLMs) have demonstrated remarkable performance in WSI classification. However, existing methods leverage coarse-grained pathogenetic descriptions for visual representation supervision, which are insufficient to capture the complex visual appearance of pathogenetic images, hindering the generalizability of models on diverse downstream tasks. Additionally, processing high-resolution WSIs can be computationally expensive. In this paper, we propose a novel "Fine-grained Visual-Semantic Interaction" (FiVE) framework for WSI classification. It is designed to enhance the model's generalizability by leveraging the interaction between localized visual patterns and fine-grained pathological semantics. Specifically, with meticulously designed queries, we start by utilizing a large language model to extract fine-grained pathological descriptions from various non-standardized raw reports. The output descriptions are then reconstructed into fine-grained labels used for training. By introducing a Task-specific Fine-grained Semantics (TFS) module, we enable prompts to capture crucial visual information in WSIs, which enhances representation learning and augments generalization capabilities significantly. Furthermore, given that pathological visual patterns are redundantly distributed across tissue slices, we sample a subset of visual instances during training. Our method demonstrates robust generalizability and strong transferability, dominantly outperforming the counterparts on the TCGA Lung Cancer dataset with at least 9.19% higher accuracy in few-shot experiments. The code is available at: https://github.com/ls1rius/WSI_FiVE.