Jing Jin

Yuying Li, Leqi Zheng, Yongzi Yu et al.

On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on selecting which trajectories to learn from, which tokens are most informative, and which supervision signals are most reliable. Motivated by this trend, we rethink optimization granularity of OPD and propose \fireicon\ FiRe-OPD (Filter, then Reweight), which jointly adjusts supervision signals at both trajectory and token levels. In details, FiRe-OPD first filters trajectories to remove low-quality rollout samples, and then applies soft reweighting within the retained trajectories to emphasize informative tokens. Compared with hard token selection, FiRe-OPD leverages a soft-weighting mechanism to effectively mitigate information loss and enhance optimization stability, thereby achieving finer-grained OPD optimization. We validate the effectiveness of FiRe-OPD across strong-to-weak, single-teacher, and multi-teacher settings, and demonstrate its superiority over recent token-level OPD methods ( (e.g., +6.25 on AIME 2024 in strong-to-weak, +18.81 on Miner in multi-teacher). Our code is available at https://github.com/YuYingLi0/FiRe-OPD.

Meituan LongCat Team, Bin Xiao, Chao Wang et al.

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

Ping Zhou, Langqing Shi, Xiaoyang Liu et al.

Depth estimation is a fundamental problem in light field processing. Epipolar-plane image (EPI)-based methods often encounter challenges such as low accuracy in slope computation due to discretization errors and limited angular resolution. Besides, existing methods perform well in most regions but struggle to produce sharp edges in occluded regions and resolve ambiguities in texture-less regions. To address these issues, we propose the concept of stitched-EPI (SEPI) to enhance slope computation. SEPI achieves this by shifting and concatenating lines from different EPIs that correspond to the same 3D point. Moreover, we introduce the half-SEPI algorithm, which focuses exclusively on the non-occluded portion of lines to handle occlusion. Additionally, we present a depth propagation strategy aimed at improving depth estimation in texture-less regions. This strategy involves determining the depth of such regions by progressing from the edges towards the interior, prioritizing accurate regions over coarse regions. Through extensive experimental evaluations and ablation studies, we validate the effectiveness of our proposed method. The results demonstrate its superior ability to generate more accurate and robust depth maps across all regions compared to state-of-the-art methods. The source code will be publicly available at https://github.com/PingZhou-LF/Light-Field-Depth-Estimation-Based-on-Stitched-EPIs.

Fangzhi Li, Zhichu Ren, Cunhua Pan et al.

To enhance the performance of aerial-ground networks, this paper proposes an integrated sensing and communication (ISAC) framework for multi-UAV systems. In our model, ground base stations (BSs) cooperatively serve multiple unmanned aerial vehicles (UAVs), employing a dynamic time-division strategy where beam scanning for sensing precedes data communication in each time slot. To maximize the sum communication rate while satisfying a mission-level cumulative radar mutual information (MI) requirement, we jointly optimize the UAV trajectories, communication and sensing power allocation, and the time-division ratio. The resulting highly coupled non-convex optimization problem is efficiently solved using an alternating optimization (AO) and successive convex approximation (SCA) framework, which yields a non-decreasing objective sequence and convergence to a finite objective value under the adopted surrogate-based iterative procedure. Extensive simulation results demonstrate that our proposed joint design significantly outperforms benchmark schemes with static trajectories, partially optimized resources, or non-cooperative single-BS transmission. Furthermore, a comprehensive sensitivity analysis reveals the distinct mechanisms by which sensing thresholds and the number of UAVs influence resource allocation and spatial organization, highlighting the critical importance of dynamic, multi-dimensional resource management for effectively navigating the sensing-communication trade-off in low-altitude economies.

Xiran Zhao, Jing Jin, Yan Bai et al.

Industrial anomaly detection is critical for manufacturing quality control, yet existing datasets mainly focus on static images or sparse views, which do not fully reflect continuous inspection processes in real industrial scenarios. We introduce MMVIAD (Multi-view Multi-task Video Industrial Anomaly Detection), to the best of our knowledge the first continuous multi-view video dataset for industrial anomaly detection and understanding, together with a benchmark for multi-task evaluation. MMVIAD contains object-centric 2-second inspection clips with approximately 120 degrees of camera motion, covering 48 object categories, 14 environments, and 6 structural anomaly types. It supports anomaly detection, defect classification, object classification, and anomaly visible-time localization. Systematic evaluations on MMVIAD show that current commercial and open-source video MLLMs remain far below human performance, especially for fine-grained defect recognition and temporal grounding. To improve transferable anomaly understanding, we further develop a two-stage post-training pipeline where PS-SFT (Perception-Structured Supervised Fine-Tuning) initializes perception-structured reasoning and VISTA-GRPO (Visibility-grounded Industrial Structured Temporal Anomaly Group Relative Policy Optimization) refines the model with semantic-gated defect reward and visibility-aware temporal reward, producing the final model VISTA. On MMVIAD-Unseen, VISTA improves the base model's average score across the four tasks from 45.0 to 57.5, surpassing GPT-5.4. Source code is available at https://github.com/Georgekeepmoving/MMVIAD.

Qing Wang, Jing Jin, Xiaofeng Liu et al.

Federated learning (FL) is a new distributed machine learning framework that can achieve reliably collaborative training without collecting users' private data. However, due to FL's frequent communication and average aggregation strategy, they experience challenges scaling to statistical diversity data and large-scale models. In this paper, we propose a personalized FL framework, named Tensor Decomposition based Personalized Federated learning (TDPFed), in which we design a novel tensorized local model with tensorized linear layers and convolutional layers to reduce the communication cost. TDPFed uses a bi-level loss function to decouple personalized model optimization from the global model learning by controlling the gap between the personalized model and the tensorized local model. Moreover, an effective distributed learning strategy and two different model aggregation strategies are well designed for the proposed TDPFed framework. Theoretical convergence analysis and thorough experiments demonstrate that our proposed TDPFed framework achieves state-of-the-art performance while reducing the communication cost.

Wenyuan Sun, Ping Zhou, Yangang Wang et al.

Face parsing assigns pixel-wise semantic labels as the face representation for computers, which is the fundamental part of many advanced face technologies. Compared with 2D face parsing, 3D face parsing shows more potential to achieve better performance and further application, but it is still challenging due to 3D mesh data computation. Recent works introduced different methods for 3D surface segmentation, while the performance is still limited. In this paper, we propose a method based on the "3D-2D-3D" strategy to accomplish 3D face parsing. The topological disk-like 2D face image containing spatial and textural information is transformed from the sampled 3D face data through the face parameterization algorithm, and a specific 2D network called CPFNet is proposed to achieve the semantic segmentation of the 2D parameterized face data with multi-scale technologies and feature aggregation. The 2D semantic result is then inversely re-mapped to 3D face data, which finally achieves the 3D face parsing. Experimental results show that both CPFNet and the "3D-2D-3D" strategy accomplish high-quality 3D face parsing and outperform state-of-the-art 2D networks as well as 3D methods in both qualitative and quantitative comparisons.

Jing Jin, Xu Liu, Te Gao et al.

Whole Slide Image (WSI) representation is critical for cancer subtyping, cancer recognition and mutation prediction.Training an end-to-end WSI representation model poses significant challenges, as a standard gigapixel slide can contain tens of thousands of image tiles, making it difficult to compute gradients of all tiles in a single mini-batch due to current GPU limitations. To address this challenge, we propose a method of dynamic residual encoding with slide-level contrastive learning (DRE-SLCL) for end-to-end WSI representation. Our approach utilizes a memory bank to store the features of tiles across all WSIs in the dataset. During training, a mini-batch usually contains multiple WSIs. For each WSI in the batch, a subset of tiles is randomly sampled and their features are computed using a tile encoder. Then, additional tile features from the same WSI are selected from the memory bank. The representation of each individual WSI is generated using a residual encoding technique that incorporates both the sampled features and those retrieved from the memory bank. Finally, the slide-level contrastive loss is computed based on the representations and histopathology reports ofthe WSIs within the mini-batch. Experiments conducted over cancer subtyping, cancer recognition, and mutation prediction tasks proved the effectiveness of the proposed DRE-SLCL method.

Haoran Ye, Jing Jin, Yuhang Xie et al. · pku

The advancement of large language models (LLMs) has outpaced traditional evaluation methodologies. This progress presents novel challenges, such as measuring human-like psychological constructs, moving beyond static and task-specific benchmarks, and establishing human-centered evaluation. These challenges intersect with psychometrics, the science of quantifying the intangible aspects of human psychology, such as personality, values, and intelligence. This review paper introduces and synthesizes the emerging interdisciplinary field of LLM Psychometrics, which leverages psychometric instruments, theories, and principles to evaluate, understand, and enhance LLMs. The reviewed literature systematically shapes benchmarking principles, broadens evaluation scopes, refines methodologies, validates results, and advances LLM capabilities. Diverse perspectives are integrated to provide a structured framework for researchers across disciplines, enabling a more comprehensive understanding of this nascent field. Ultimately, the review provides actionable insights for developing future evaluation paradigms that align with human-level AI and promote the advancement of human-centered AI systems for societal benefit. A curated repository of LLM psychometric resources is available at https://github.com/valuebyte-ai/Awesome-LLM-Psychometrics.

Jing Jin, Hao Liu, Yan Bai et al.

Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly verifiable feedback, but existing benchmarks often permit unimodal shortcuts due to modality redundancy and focus mainly on final-answer accuracy, overlooking the reasoning process itself. To address this challenge, we introduce StepSTEM: a graduate-level benchmark of 283 problems across mathematics, physics, chemistry, biology, and engineering for fine-grained evaluation of cross-modal reasoning in MLLMs. StepSTEM is constructed through a rigorous curation pipeline that enforces strict complementarity between textual and visual inputs. We further propose a general step-level evaluation framework for both text-only chain-of-thought and interleaved image-text reasoning, using dynamic programming to align predicted reasoning steps with multiple reference solutions. Experiments across a wide range of models show that current MLLMs still rely heavily on textual reasoning, with even Gemini 3.1 Pro and Claude Opus 4.6 achieving only 38.29% accuracy. These results highlight substantial headroom for genuine cross-modal STEM reasoning and position StepSTEM as a benchmark for fine-grained evaluation of multimodal reasoning. Source code is available at https://github.com/lll-hhh/STEPSTEM.

Yiran Ling, Rongqiang Zhao, Yixuan Shen et al.

Non-contact volume estimation of pile-type objects has considerable potential in industrial scenarios, including grain, coal, mining, and stone materials. However, using existing method for these scenarios is challenged by unstable measurement poses, significant light interference, the difficulty of training data collection, and the computational burden brought by large piles. To address the above issues, we propose the Depth Integrated Volume EStimation of Pile Of Things (DIVESPOT) based on point cloud technology in this study. For the challenges of unstable measurement poses, the point cloud pose correction and filtering algorithm is designed based on the Random Sample Consensus (RANSAC) and the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN). To cope with light interference and to avoid the relying on training data, the height-distribution-based ground feature extraction algorithm is proposed to achieve RGB-independent. To reduce the computational burden, the storage space optimizing strategy is developed, such that accurate estimation can be acquired by using compressed voxels. Experimental results demonstrate that the DIVESPOT method enables non-data-driven, RGB-independent segmentation of pile point clouds, maintaining a volume calculation relative error within 2%. Even with 90% compression of the voxel mesh, the average error of the results can be under 3%.

Wen Luo, Guangyue Peng, Wei Li et al.

Despite their impressive capabilities, large language models (LLMs) frequently generate hallucinations. Previous work shows that their internal states encode rich signals of truthfulness, yet the origins and mechanisms of these signals remain unclear. In this paper, we demonstrate that truthfulness cues arise from two distinct information pathways: (1) a Question-Anchored pathway that depends on question-answer information flow, and (2) an Answer-Anchored pathway that derives self-contained evidence from the generated answer itself. First, we validate and disentangle these pathways through attention knockout and token patching. Afterwards, we uncover notable and intriguing properties of these two mechanisms. Further experiments reveal that (1) the two mechanisms are closely associated with LLM knowledge boundaries; and (2) internal representations are aware of their distinctions. Finally, building on these insightful findings, two applications are proposed to enhance hallucination detection performance. Overall, our work provides new insight into how LLMs internally encode truthfulness, offering directions for more reliable and self-aware generative systems.

Xuanyu Zhu, Yan Bai, Yang Shi et al.

Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods universally extract features from only the last encoder layer, discarding the rich hierarchical information distributed across intermediate layers. We show that low-level visual details survive in the last layer merely as attenuated residuals after multiple layers of semantic abstraction, and that explicitly fusing multi-layer features can substantially recover this lost information. We propose DRoRAE (Depth-Routed Representation AutoEncoder), a lightweight fusion module that adaptively aggregates all encoder layers via energy-constrained routing and incremental correction, producing an enriched latent compatible with a frozen pretrained decoder. A three-phase decoupled training strategy first learns the fusion under the implicit distributional constraint of the frozen decoder, then fine-tunes the decoder to fully exploit the enriched representation. On ImageNet-256, DRoRAE reduces rFID from 0.57 to 0.29 and improves generation FID from 1.74 to 1.65 (with AutoGuidance), with gains also transferring to text-to-image synthesis. Furthermore, we uncover a log-linear scaling law ($R^2{=}0.86$) between fusion capacity and reconstruction quality, identifying \textit{representation richness} as a new, predictably scalable dimension for visual tokenizers analogous to vocabulary size in NLP.

Chenyang Shi, Hanxiao Liu, Jing Jin et al.

Video frame interpolation aims to generate high-quality intermediate frames from boundary frames and increase frame rate. While existing linear, symmetric and nonlinear models are used to bridge the gap from the lack of inter-frame motion, they cannot reconstruct real motions. Event cameras, however, are ideal for capturing inter-frame dynamics with their extremely high temporal resolution. In this paper, we propose an event-and-frame-based video frame interpolation method named IDO-VFI that assigns varying amounts of computation for different sub-regions via optical flow guidance. The proposed method first estimates the optical flow based on frames and events, and then decides whether to further calculate the residual optical flow in those sub-regions via a Gumbel gating module according to the optical flow amplitude. Intermediate frames are eventually generated through a concise Transformer-based fusion network. Our proposed method maintains high-quality performance while reducing computation time and computational effort by 10% and 17% respectively on Vimeo90K datasets, compared with a unified process on the whole region. Moreover, our method outperforms state-of-the-art frame-only and frames-plus-events methods on multiple video frame interpolation benchmarks. Codes and models are available at https://github.com/shicy17/IDO-VFI.

Mantang Guo, Junhui Hou, Jing Jin et al.

Existing image-based rendering methods usually adopt depth-based image warping operation to synthesize novel views. In this paper, we reason the essential limitations of the traditional warping operation to be the limited neighborhood and only distance-based interpolation weights. To this end, we propose content-aware warping, which adaptively learns the interpolation weights for pixels of a relatively large neighborhood from their contextual information via a lightweight neural network. Based on this learnable warping module, we propose a new end-to-end learning-based framework for novel view synthesis from a set of input source views, in which two additional modules, namely confidence-based blending and feature-assistant spatial refinement, are naturally proposed to handle the occlusion issue and capture the spatial correlation among pixels of the synthesized view, respectively. Besides, we also propose a weight-smoothness loss term to regularize the network. Experimental results on light field datasets with wide baselines and multi-view datasets show that the proposed method significantly outperforms state-of-the-art methods both quantitatively and visually. The source code will be publicly available at https://github.com/MantangGuo/CW4VS.

Mantang Guo, Jing Jin, Hui Liu et al.

In this paper, we tackle the problem of dense light field (LF) reconstruction from sparsely-sampled ones with wide baselines and propose a learnable model, namely dynamic interpolation, to replace the commonly-used geometry warping operation. Specifically, with the estimated geometric relation between input views, we first construct a lightweight neural network to dynamically learn weights for interpolating neighbouring pixels from input views to synthesize each pixel of novel views independently. In contrast to the fixed and content-independent weights employed in the geometry warping operation, the learned interpolation weights implicitly incorporate the correspondences between the source and novel views and adapt to different image content information. Then, we recover the spatial correlation between the independently synthesized pixels of each novel view by referring to that of input views using a geometry-based spatial refinement module. We also constrain the angular correlation between the novel views through a disparity-oriented LF structure loss. Experimental results on LF datasets with wide baselines show that the reconstructed LFs achieve much higher PSNR/SSIM and preserve the LF parallax structure better than state-of-the-art methods. The source code is publicly available at https://github.com/MantangGuo/DI4SLF.

Jing Jin, Junhui Hou, Jie Chen et al.

This paper explores the problem of reconstructing high-resolution light field (LF) images from hybrid lenses, including a high-resolution camera surrounded by multiple low-resolution cameras. To tackle this challenge, we propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input from two complementary and parallel perspectives. Specifically, one module regresses a spatially consistent intermediate estimation by learning a deep multidimensional and cross-domain feature representation; the other one constructs another intermediate estimation, which maintains the high-frequency textures, by propagating the information of the high-resolution view. We finally leverage the advantages of the two intermediate estimations via the learned attention maps, leading to the final high-resolution LF image. Extensive experiments demonstrate the significant superiority of our approach over state-of-the-art ones. That is, our method not only improves the PSNR by more than 2 dB, but also preserves the LF structure much better. To the best of our knowledge, this is the first end-to-end deep learning method for reconstructing a high-resolution LF image with a hybrid input. We believe our framework could potentially decrease the cost of high-resolution LF data acquisition and also be beneficial to LF data storage and transmission. The code is available at https://github.com/jingjin25/LFhybridSR-Fusion.

Tingcheng Bian, Yuzhe Zhang, Jing Jin et al.

Large reasoning models (LRMs) achieve strong performance via extended chain-of-thought (CoT) reasoning, yet suffer from excessive token consumption and high inference latency. Existing reinforcement learning (RL) approaches for CoT compression rely on uniform, static length penalties that neglect model capability dynamics and problem-level difficulty variation. We propose \textbf{ExpThink}\xspace, an RL framework that addresses both dimensions through two complementary mechanisms. First, \emph{experience-guided reward shaping} tracks the shortest correct solution found so far for each problem and applies a three-tier reward: full credit for concise correct responses, discounted credit for verbose correct ones, and zero for incorrect ones. The threshold tightens automatically with model improvement, forming a self-evolving curriculum that requires no manual scheduling. Second, \emph{difficulty-adaptive advantage} replaces standard deviation normalization with correct-count normalization, yielding monotonically difficulty-scaled gradients that amplify learning on hard problems to preserve accuracy while suppressing gradients on easy ones to encourage brevity. Together, these mechanisms enforce an accuracy-first, compression-second training objective. Experiments on multiple mathematical reasoning benchmarks demonstrate that \textbf{ExpThink}\xspace reduces average response length by up to 77\% while simultaneously improving accuracy, achieving up to $3\times$ higher accuracy-efficiency ratio (accuracy divided by average token count) than the vanilla baseline and outperforming existing RL-based compression methods on both metrics.

Zhongyi Zhou, Jing Jin, Vrushank Phadnis et al.

Visual programming has the potential of providing novice programmers with a low-code experience to build customized processing pipelines. Existing systems typically require users to build pipelines from scratch, implying that novice users are expected to set up and link appropriate nodes from a blank workspace. In this paper, we introduce InstructPipe, an AI assistant for prototyping machine learning (ML) pipelines with text instructions. We contribute two large language model (LLM) modules and a code interpreter as part of our framework. The LLM modules generate pseudocode for a target pipeline, and the interpreter renders the pipeline in the node-graph editor for further human-AI collaboration. Both technical and user evaluation (N=16) shows that InstructPipe empowers users to streamline their ML pipeline workflow, reduce their learning curve, and leverage open-ended commands to spark innovative ideas.

Yen-Shan Chen, Jing Jin, Peng-Ting Kuo et al.

Recent studies have demonstrated that large language models (LLMs) exhibit significant biases in evaluation tasks, particularly in preferentially rating and favoring self-generated content. However, the extent to which this bias manifests in fact-oriented tasks, especially within retrieval-augmented generation (RAG) frameworks-where keyword extraction and factual accuracy take precedence over stylistic elements-remains unclear. Our study addresses this knowledge gap by simulating two critical phases of the RAG framework. In the first phase, we access the suitability of human-authored versus model-generated passages, emulating the pointwise reranking process. The second phase involves conducting pairwise reading comprehension tests to simulate the generation process. Contrary to previous findings indicating a self-preference in rating tasks, our results reveal no significant self-preference effect in RAG frameworks. Instead, we observe that factual accuracy significantly influences LLMs' output, even in the absence of prior knowledge. Our research contributes to the ongoing discourse on LLM biases and their implications for RAG-based system, offering insights that may inform the development of more robust and unbiased LLM systems.

Ziyao Xu, Shaohang Wei, Zhuoheng Han et al. · pku

Citation faithfulness detection is critical for enhancing retrieval-augmented generation (RAG) systems, yet large-scale Chinese datasets for this task are scarce. Existing methods face prohibitive costs due to the need for manually annotated negative samples. To address this, we introduce the first large-scale Chinese dataset CiteCheck for citation faithfulness detection, constructed via a cost-effective approach using two-stage manual annotation. This method balances positive and negative samples while significantly reducing annotation expenses. CiteCheck comprises training and test splits. Experiments demonstrate that: (1) the test samples are highly challenging, with even state-of-the-art LLMs failing to achieve high accuracy; and (2) training data augmented with LLM-generated negative samples enables smaller models to attain strong performance using parameter-efficient fine-tuning. CiteCheck provides a robust foundation for advancing citation faithfulness detection in Chinese RAG systems. The dataset is publicly available to facilitate research.

Chenyang Shi, Shasha Guo, Boyi Wei et al.

Event cameras are renowned for their high efficiency due to outputting a sparse, asynchronous stream of events. However, they are plagued by noisy events, especially in low light conditions. Denoising is an essential task for event cameras, but evaluating denoising performance is challenging. Label-dependent denoising metrics involve artificially adding noise to clean sequences, complicating evaluations. Moreover, the majority of these metrics are monotonic, which can inflate scores by removing substantial noise and valid events. To overcome these limitations, we propose the first label-free and non-monotonic evaluation metric, the area of the continuous contrast curve (AOCC), which utilizes the area enclosed by event frame contrast curves across different time intervals. This metric is inspired by how events capture the edge contours of scenes or objects with high temporal resolution. An effective denoising method removes noise without eliminating these edge-contour events, thus preserving the contrast of event frames. Consequently, contrast across various time ranges serves as a metric to assess denoising effectiveness. As the time interval lengthens, the curve will initially rise and then fall. The proposed metric is validated through both theoretical and experimental evidence.

Kaihua Ding, Jingsong Cui, Mohammad Soltani et al.

The field of causal Machine Learning (ML) has made significant strides in recent years. Notable breakthroughs include methods such as meta learners (arXiv:1706.03461v6) and heterogeneous doubly robust estimators (arXiv:2004.14497) introduced in the last five years. Despite these advancements, the field still faces challenges, particularly in managing tightly coupled systems where both the causal treatment variable and a confounding covariate must serve as key decision-making indicators. This scenario is common in applications of causal ML for marketing, such as marketing segmentation and incremental marketing uplift. In this work, we present our formally proven algorithm, iterative causal segmentation, to address this issue.

Jing Jin, Houfeng Wang

Machine Reading Comprehension(MRC) has achieved a remarkable result since some powerful models, such as BERT, are proposed. However, these models are not robust enough and vulnerable to adversarial input perturbation and generalization examples. Some works tried to improve the performance on specific types of data by adding some related examples into training data while it leads to degradation on the original dataset, because the shift of data distribution makes the answer ranking based on the softmax probability of model unreliable. In this paper, we propose a method to improve the robustness by using a calibrator as the post-hoc reranker, which is implemented based on XGBoost model. The calibrator combines both manual features and representation learning features to rerank candidate results. Experimental results on adversarial datasets show that our model can achieve performance improvement by more than 10\% and also make improvement on the original and generalization datasets.

Aichun Zhu, Zijie Wang, Yifeng Li et al.

Many previous methods on text-based person retrieval tasks are devoted to learning a latent common space mapping, with the purpose of extracting modality-invariant features from both visual and textual modality. Nevertheless, due to the complexity of high-dimensional data, the unconstrained mapping paradigms are not able to properly catch discriminative clues about the corresponding person while drop the misaligned information. Intuitively, the information contained in visual data can be divided into person information (PI) and surroundings information (SI), which are mutually exclusive from each other. To this end, we propose a novel Deep Surroundings-person Separation Learning (DSSL) model in this paper to effectively extract and match person information, and hence achieve a superior retrieval accuracy. A surroundings-person separation and fusion mechanism plays the key role to realize an accurate and effective surroundings-person separation under a mutually exclusion constraint. In order to adequately utilize multi-modal and multi-granular information for a higher retrieval accuracy, five diverse alignment paradigms are adopted. Extensive experiments are carried out to evaluate the proposed DSSL on CUHK-PEDES, which is currently the only accessible dataset for text-base person retrieval task. DSSL achieves the state-of-the-art performance on CUHK-PEDES. To properly evaluate our proposed DSSL in the real scenarios, a Real Scenarios Text-based Person Reidentification (RSTPReid) dataset is constructed to benefit future research on text-based person retrieval, which will be publicly available.

Jing Jin, Junhui Hou

Depth estimation is a fundamental issue in 4-D light field processing and analysis. Although recent supervised learning-based light field depth estimation methods have significantly improved the accuracy and efficiency of traditional optimization-based ones, these methods rely on the training over light field data with ground-truth depth maps which are challenging to obtain or even unavailable for real-world light field data. Besides, due to the inevitable gap (or domain difference) between real-world and synthetic data, they may suffer from serious performance degradation when generalizing the models trained with synthetic data to real-world data. By contrast, we propose an unsupervised learning-based method, which does not require ground-truth depth as supervision during training. Specifically, based on the basic knowledge of the unique geometry structure of light field data, we present an occlusion-aware strategy to improve the accuracy on occlusion areas, in which we explore the angular coherence among subsets of the light field views to estimate initial depth maps, and utilize a constrained unsupervised loss to learn their corresponding reliability for final depth prediction. Additionally, we adopt a multi-scale network with a weighted smoothness loss to handle the textureless areas. Experimental results on synthetic data show that our method can significantly shrink the performance gap between the previous unsupervised method and supervised ones, and produce depth maps with comparable accuracy to traditional methods with obviously reduced computational cost. Moreover, experiments on real-world datasets show that our method can avoid the domain shift problem presented in supervised methods, demonstrating the great potential of our method.

Jing Jin, Mantang Guo, Junhui Hou et al.

This paper explores the problem of reconstructing high-resolution light field (LF) images from hybrid lenses, including a high-resolution camera surrounded by multiple low-resolution cameras. The performance of existing methods is still limited, as they produce either blurry results on plain textured areas or distortions around depth discontinuous boundaries. To tackle this challenge, we propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input from two complementary and parallel perspectives. Specifically, one module regresses a spatially consistent intermediate estimation by learning a deep multidimensional and cross-domain feature representation, while the other module warps another intermediate estimation, which maintains the high-frequency textures, by propagating the information of the high-resolution view. We finally leverage the advantages of the two intermediate estimations adaptively via the learned attention maps, leading to the final high-resolution LF image with satisfactory results on both plain textured areas and depth discontinuous boundaries. Besides, to promote the effectiveness of our method trained with simulated hybrid data on real hybrid data captured by a hybrid LF imaging system, we carefully design the network architecture and the training strategy. Extensive experiments on both real and simulated hybrid data demonstrate the significant superiority of our approach over state-of-the-art ones. To the best of our knowledge, this is the first end-to-end deep learning method for LF reconstruction from a real hybrid input. We believe our framework could potentially decrease the cost of high-resolution LF data acquisition and benefit LF data storage and transmission.

Jing Jin, Cai Liang, Tiancheng Wu et al.

Recently, transformer-based language models such as BERT have shown tremendous performance improvement for a range of natural language processing tasks. However, these language models usually are computation expensive and memory intensive during inference. As a result, it is difficult to deploy them on resource-restricted devices. To improve the inference performance, as well as reduce the model size while maintaining the model accuracy, we propose a novel quantization method named KDLSQ-BERT that combines knowledge distillation (KD) with learned step size quantization (LSQ) for language model quantization. The main idea of our method is that the KD technique is leveraged to transfer the knowledge from a "teacher" model to a "student" model when exploiting LSQ to quantize that "student" model during the quantization training process. Extensive experiment results on GLUE benchmark and SQuAD demonstrate that our proposed KDLSQ-BERT not only performs effectively when doing different bit (e.g. 2-bit $\sim$ 8-bit) quantization, but also outperforms the existing BERT quantization methods, and even achieves comparable performance as the full-precision base-line model while obtaining 14.9x compression ratio. Our code will be public available.

Haoli Bai, Wei Zhang, Lu Hou et al.

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit by weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscape. Therefore, we propose ternary weight splitting, which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary one, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that our BinaryBERT has only a slight performance drop compared with the full-precision model while being 24x smaller, achieving the state-of-the-art compression results on the GLUE and SQuAD benchmarks.

Jing Jin, Junhui Hou, Zhiyu Zhu et al.

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited detector resolution has to be shared with the angular dimension. LF spatial super-resolution (SR) thus becomes an indispensable part of the LF camera processing pipeline. The high-dimensionality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. The performance of existing methods is still limited as they fail to thoroughly explore the coherence among LF sub-aperture images (SAIs) and are insufficient in accurately preserving the scene's parallax structure. To tackle this challenge, we propose a novel learning-based LF spatial SR framework. Specifically, each SAI of an LF image is first coarsely and individually super-resolved by exploring the complementary information among SAIs with selective combinatorial geometry embedding. To achieve efficient and effective selection of the complementary information, we propose two novel sub-modules conducted hierarchically: the patch selector provides an option of retrieving similar image patches based on offline disparity estimation to handle large-disparity correlations; and the SAI selector adaptively and flexibly selects the most informative SAIs to improve the embedding efficiency. To preserve the parallax structure among the reconstructed SAIs, we subsequently append a consistency regularization network trained over a structure-aware loss function to refine the parallax relationships over the coarse estimation. In addition, we extend the proposed method to irregular LF data. To the best of our knowledge, this is the first learning-based SR method for irregular LF data. Experimental results over both synthetic and real-world LF datasets demonstrate the significant advantage of our approach over state-of-the-art methods.

Jing Jin, Junhui Hou, Jie Chen et al.

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension. LF spatial super-resolution (SR) thus becomes an indispensable part of the LF camera processing pipeline. The high-dimensionality characteristic and complex geometrical structure of LF images make the problem more challenging than traditional single-image SR. The performance of existing methods is still limited as they fail to thoroughly explore the coherence among LF views and are insufficient in accurately preserving the parallax structure of the scene. In this paper, we propose a novel learning-based LF spatial SR framework, in which each view of an LF image is first individually super-resolved by exploring the complementary information among views with combinatorial geometry embedding. For accurate preservation of the parallax structure among the reconstructed views, a regularization network trained over a structure-aware loss function is subsequently appended to enforce correct parallax relationships over the intermediate estimation. Our proposed approach is evaluated over datasets with a large number of testing images including both synthetic and real-world scenes. Experimental results demonstrate the advantage of our approach over state-of-the-art methods, i.e., our method not only improves the average PSNR by more than 1.0 dB but also preserves more accurate parallax details, at a lower computational cost.

Jing Jin, Junhui Hou, Hui Yuan et al.

The acquisition of light field images with high angular resolution is costly. Although many methods have been proposed to improve the angular resolution of a sparsely-sampled light field, they always focus on the light field with a small baseline, which is captured by a consumer light field camera. By making full use of the intrinsic \textit{geometry} information of light fields, in this paper we propose an end-to-end learning-based approach aiming at angularly super-resolving a sparsely-sampled light field with a large baseline. Our model consists of two learnable modules and a physically-based module. Specifically, it includes a depth estimation module for explicitly modeling the scene geometry, a physically-based warping for novel views synthesis, and a light field blending module specifically designed for light field reconstruction. Moreover, we introduce a novel loss function to promote the preservation of the light field parallax structure. Experimental results over various light field datasets including large baseline light field images demonstrate the significant superiority of our method when compared with state-of-the-art ones, i.e., our method improves the PSNR of the second best method up to 2 dB in average, while saves the execution time 48$\times$. In addition, our method preserves the light field parallax structure better.

Jie Fu, Xinran Zhong, Ning Li et al.

Radiomic features achieve promising results in cancer diagnosis, treatment response prediction, and survival prediction. Our goal is to compare the handcrafted (explicitly designed) and deep learning (DL)-based radiomic features extracted from pre-treatment diffusion-weighted magnetic resonance images (DWIs) for predicting neoadjuvant chemoradiation treatment (nCRT) response in patients with locally advanced rectal cancer (LARC). 43 patients receiving nCRT were included. All patients underwent DWIs before nCRT and total mesorectal excision surgery 6-12 weeks after completion of nCRT. Gross tumor volume (GTV) contours were drawn by an experienced radiation oncologist on DWIs. The patient-cohort was split into the responder group (n=22) and the non-responder group (n=21) based on the post-nCRT response assessed by postoperative pathology, MRI or colonoscopy. Handcrafted and DL-based features were extracted from the apparent diffusion coefficient (ADC) map of the DWI using conventional computer-aided diagnosis methods and a pre-trained convolution neural network, respectively. Least absolute shrinkage and selection operator (LASSO)-logistic regression models were constructed using extracted features for predicting treatment response. The model performance was evaluated with repeated 20 times stratified 4-fold cross-validation using receiver operating characteristic (ROC) curves and compared using the corrected resampled t-test. The model built with handcrafted features achieved the mean area under the ROC curve (AUC) of 0.64, while the one built with DL-based features yielded the mean AUC of 0.73. The corrected resampled t-test on AUC showed P-value < 0.05. DL-based features extracted from pre-treatment DWIs achieved significantly better classification performance compared with handcrafted features for predicting nCRT response in patients with LARC.

Jing Jin, Junhui Hou, Jie Chen et al.

A densely-sampled light field (LF) is highly desirable in various applications, such as 3-D reconstruction, post-capture refocusing and virtual reality. However, it is costly to acquire such data. Although many computational methods have been proposed to reconstruct a densely-sampled LF from a sparsely-sampled one, they still suffer from either low reconstruction quality, low computational efficiency, or the restriction on the regularity of the sampling pattern. To this end, we propose a novel learning-based method, which accepts sparsely-sampled LFs with irregular structures, and produces densely-sampled LFs with arbitrary angular resolution accurately and efficiently. We also propose a simple yet effective method for optimizing the sampling pattern. Our proposed method, an end-to-end trainable network, reconstructs a densely-sampled LF in a coarse-to-fine manner. Specifically, the coarse sub-aperture image (SAI) synthesis module first explores the scene geometry from an unstructured sparsely-sampled LF and leverages it to independently synthesize novel SAIs, in which a confidence-based blending strategy is proposed to fuse the information from different input SAIs, giving an intermediate densely-sampled LF. Then, the efficient LF refinement module learns the angular relationship within the intermediate result to recover the LF parallax structure. Comprehensive experimental evaluations demonstrate the superiority of our method on both real-world and synthetic LF images when compared with state-of-the-art methods. In addition, we illustrate the benefits and advantages of the proposed approach when applied in various LF-based applications, including image-based rendering and depth estimation enhancement.

Zhaoyang Qiu, Shugeng Chen, Ian Daly et al.

Stroke is the leading cause of serious and long-term disability worldwide. Some studies have shown that motor imagery (MI) based BCI has a positive effect in poststroke rehabilitation. It could help patients promote the reorganization processes in the damaged brain regions. However, offline motor imagery and conventional online motor imagery with feedback (such as rewarding sounds and movements of an avatar) could not reflect the true intention of the patients. In this study, both virtual limbs and functional electrical stimulation (FES) were used as feedback to provide patients a closed-loop sensorimotor integration for motor rehabilitation. The FES system would activate if the user was imagining hand movement of instructed side. Ten stroke patients (7 male, aged 22-70 years, mean 49.5+-15.1) were involved in this study. All of them participated in BCI-FES rehabilitation training for 4 weeks.The average motor imagery accuracies of the ten patients in the last week were 71.3%, which has improved 3% than that in the first week. Five patients' Fugl-Meyer Assessment (FMA) scores have been raised. Patient 6, who has have suffered from stroke over two years, achieved the greatest improvement after rehabilitation training (pre FMA: 20, post FMA: 35). In the aspect of brain patterns, the active patterns of the five patients gradually became centralized and shifted to sensorimotor areas (channel C3 and C4) and premotor area (channel FC3 and FC4).In this study, motor imagery based BCI and FES system were combined to provided stoke patients with a closed-loop sensorimotor integration for motor rehabilitation. Result showed evidences that the BCI-FES system is effective in restoring upper extremities motor function in stroke. In future work, more cases are needed to demonstrate its superiority over conventional therapy and explore the potential role of MI in poststroke rehabilitation.

Olivier Deiss, Siddharth Biswal, Jing Jin et al.

Efficient label acquisition processes are key to obtaining robust classifiers. However, data labeling is often challenging and subject to high levels of label noise. This can arise even when classification targets are well defined, if instances to be labeled are more difficult than the prototypes used to define the class, leading to disagreements among the expert community. Here, we enable efficient training of deep neural networks. From low-confidence labels, we iteratively improve their quality by simultaneous learning of machines and experts. We call it Human And Machine co-LEarning Technique (HAMLET). Throughout the process, experts become more consistent, while the algorithm provides them with explainable feedback for confirmation. HAMLET uses a neural embedding function and a memory module filled with diverse reference embeddings from different classes. Its output includes classification labels and highly relevant reference embeddings as explanation. We took the study of brain monitoring at intensive care unit (ICU) as an application of HAMLET on continuous electroencephalography (cEEG) data. Although cEEG monitoring yields large volumes of data, labeling costs and difficulty make it hard to build a classifier. Additionally, while experts agree on the labels of clear-cut examples of cEEG patterns, labeling many real-world cEEG data can be extremely challenging. Thus, a large minority of sequences might be mislabeled. HAMLET has shown significant performance gain against deep learning and other baselines, increasing accuracy from 7.03% to 68.75% on challenging inputs. Besides improved performance, clinical experts confirmed the interpretability of those reference embeddings in helping explaining the classification results by HAMLET.

Jing Jin, Brendan Z. Allison, Yu Zhang et al.

Objective: Amyotrophic lateral sclerosis (ALS) is a rare disease, but is also one of the most common motor neuron diseases, and people of all races and ethnic backgrounds are affected. There is currently no cure. Brain computer interfaces (BCIs) can establish a communication channel directly between the brain and an external device by recognizing brain activities that reflect user intent. Therefore, this technology could help ALS patients in promoting functional independence through BCI-based speller systems and motor assistive devices. Methods: In this paper, two kinds of ERP-based speller systems were tested on 18 ALS patients to: (1) assess performance when they spelled 42 characters online continuously, without a break; and (2) to compare performance between a matrix-based speller paradigm (MS-P, mean visual angle 6 degree) and a new speller paradigm that used a larger visual angle called the large visual angle speller paradigm (LS-P, mean visual angle 8 degree). Results: Although results showed that there were no significant differences between the two paradigms in accuracy trend over continuous use (p>0.05), the fatigue during the LS-P condition was significantly lower than that of MS-P (p<0.05). Results also showed that continuous use slightly reduced the performance of this ERP-based BCI. Conclusion: 15 subjects obtained higher than 80% feedback accuracy (online output accuracy) and 9 subjects obtained higher than 90% feedback accuracy in one of the two paradigms, thus validating the BCI approaches in this study. Significance: Most ALS subjects in this study could spell effectively after continuous use of an ERP-based BCI. The new LS-P display may be easier for subjects to use, resulting in lower fatigue.

Zhaoyang Qiu, Brendan Z. Allison, Jing Jin et al.

Motor imagery (MI) is a mental representation of motor behavior that has been widely used as a control method for a brain-computer interface (BCI), allowing communication for the physically impaired. The performance of MI based BCI mainly depends on the subject's ability to self-modulate EEG signals. Proper training can help naive subjects learn to modulate brain activity proficiently. However, training subjects typically involves abstract motor tasks and is time-consuming. To improve the performance of naive subjects during motor imagery, a novel paradigm was presented that would guide naive subjects to modulate brain activity effectively. In this new paradigm, pictures of the left or right hand were used as cues for subjects to finish the motor imagery task. Fourteen healthy subjects (11 male, aged 22-25 years, mean 23.6+/-1.16) participated in this study. The task was to imagine writing a Chinese character. Specifically, subjects could imagine hand movements following the sequence of writing strokes in the Chinese character. This paradigm was meant to find an effective and familiar action for most Chinese people, to provide them with a specific, extensively practiced task and help them modulate brain activity. Results showed that the writing task paradigm yielded significantly better performance than the traditional arrow paradigm (p<0.001). Questionnaire replies indicated that most subjects thought the new paradigm was easier and more comfortable. The proposed new motor imagery paradigm could guide subjects to help them modulate brain activity effectively. Results showed that there were significant improvements using new paradigm, both in classification accuracy and usability.

Yu Zhang, Guoxu Zhou, Jing Jin et al.

Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Despite its efficiency, a potential problem is that using pre-constructed sine-cosine waves as the required reference signals in the CCA method often does not result in the optimal recognition accuracy due to their lack of features from the real EEG data. To address this problem, this study proposes a novel method based on multiset canonical correlation analysis (MsetCCA) to optimize the reference signals used in the CCA method for SSVEP frequency recognition. The MsetCCA method learns multiple linear transforms that implement joint spatial filtering to maximize the overall correlation among canonical variates, and hence extracts SSVEP common features from multiple sets of EEG data recorded at the same stimulus frequency. The optimized reference signals are formed by combination of the common features and completely based on training data. Experimental study with EEG data from ten healthy subjects demonstrates that the MsetCCA method improves the recognition accuracy of SSVEP frequency in comparison with the CCA method and other two competing methods (multiway CCA (MwayCCA) and phase constrained CCA (PCCA)), especially for a small number of channels and a short time window length. The superiority indicates that the proposed MsetCCA method is a new promising candidate for frequency recognition in SSVEP-based BCIs.