Yan Zhu

Juntao Tan, Yingqiang Ge, Yan Zhu et al.

Modern recommender systems utilize users' historical behaviors to generate personalized recommendations. However, these systems often lack user controllability, leading to diminished user satisfaction and trust in the systems. Acknowledging the recent advancements in explainable recommender systems that enhance users' understanding of recommendation mechanisms, we propose leveraging these advancements to improve user controllability. In this paper, we present a user-controllable recommender system that seamlessly integrates explainability and controllability within a unified framework. By providing both retrospective and prospective explanations through counterfactual reasoning, users can customize their control over the system by interacting with these explanations. Furthermore, we introduce and assess two attributes of controllability in recommendation systems: the complexity of controllability and the accuracy of controllability. Experimental evaluations on MovieLens and Yelp datasets substantiate the effectiveness of our proposed framework. Additionally, our experiments demonstrate that offering users control options can potentially enhance recommendation accuracy in the future. Source code and data are available at \url{https://github.com/chrisjtan/ucr}.

Qiyu Dai, Yan Zhu, Yiran Geng et al. · pku

In this work, we tackle 6-DoF grasp detection for transparent and specular objects, which is an important yet challenging problem in vision-based robotic systems, due to the failure of depth cameras in sensing their geometry. We, for the first time, propose a multiview RGB-based 6-DoF grasp detection network, GraspNeRF, that leverages the generalizable neural radiance field (NeRF) to achieve material-agnostic object grasping in clutter. Compared to the existing NeRF-based 3-DoF grasp detection methods that rely on densely captured input images and time-consuming per-scene optimization, our system can perform zero-shot NeRF construction with sparse RGB inputs and reliably detect 6-DoF grasps, both in real-time. The proposed framework jointly learns generalizable NeRF and grasp detection in an end-to-end manner, optimizing the scene representation construction for the grasping. For training data, we generate a large-scale photorealistic domain-randomized synthetic dataset of grasping in cluttered tabletop scenes that enables direct transfer to the real world. Our extensive experiments in synthetic and real-world environments demonstrate that our method significantly outperforms all the baselines in all the experiments while remaining in real-time. Project page can be found at https://pku-epic.github.io/GraspNeRF

Yiyou Sun, Xinyang Han, Weichen Zhang et al.

Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional domains. We argue that this gap is largely an evaluation problem: widely used benchmarks lack sustained performance measurement on real and economically valuable workflows. This paper introduces Agents' Last Exam (ALE), a benchmark designed to evaluate AI agents on long-horizon, economically valuable, real-world tasks with verifiable outcomes. Developed in collaboration with 250+ industry experts, ALE covers non-physical industries defined with reference to O*NET / SOC 2018 (the U.S. federal occupational taxonomy). It is organized around a task taxonomy with 55 subfields grouped into 13 industry clusters covering 1K+ tasks. Current results show that the hardest tier remains far from saturated: across mainstream harness and backbone configurations, the average full pass rate is 2.6%. ALE is designed as a living benchmark: its task pool grows continuously as new workflows and industries are onboarded. More broadly, ALE is intended not merely as another leaderboard, but as an instrument for closing the gap between benchmark success and GDP-relevant impact.

Ya-Dong Wu, Yan Zhu, Ge Bai et al.

The task of testing whether two uncharacterized quantum devices behave in the same way is crucial for benchmarking near-term quantum computers and quantum simulators, but has so far remained open for continuous-variable quantum systems. In this Letter, we develop a machine learning algorithm for comparing unknown continuous variable states using limited and noisy data. The algorithm works on non-Gaussian quantum states for which similarity testing could not be achieved with previous techniques. Our approach is based on a convolutional neural network that assesses the similarity of quantum states based on a lower-dimensional state representation built from measurement data. The network can be trained offline with classically simulated data from a fiducial set of states sharing structural similarities with the states to be tested, or with experimental data generated by measurements on the fiducial states, or with a combination of simulated and experimental data. We test the performance of the model on noisy cat states and states generated by arbitrary selective number-dependent phase gates. Our network can also be applied to the problem of comparing continuous variable states across different experimental platforms, with different sets of achievable measurements, and to the problem of experimentally testing whether two states are equivalent up to Gaussian unitary transformations.

Ya-Dong Wu, Yan Zhu, Yuexuan Wang et al.

Characterizing multipartite quantum systems is crucial for quantum computing and many-body physics. The problem, however, becomes challenging when the system size is large and the properties of interest involve correlations among a large number of particles. Here we introduce a neural network model that can predict various quantum properties of many-body quantum states with constant correlation length, using only measurement data from a small number of neighboring sites. The model is based on the technique of multi-task learning, which we show to offer several advantages over traditional single-task approaches. Through numerical experiments, we show that multi-task learning can be applied to sufficiently regular states to predict global properties, like string order parameters, from the observation of short-range correlations, and to distinguish between quantum phases that cannot be distinguished by single-task networks. Remarkably, our model appears to be able to transfer information learnt from lower dimensional quantum systems to higher dimensional ones, and to make accurate predictions for Hamiltonians that were not seen in the training.

Manwen Liao, Yan Zhu, Giulio Chiribella et al.

Quantum error mitigation, a data processing technique for recovering the statistics of target processes from their noisy version, is a crucial task for near-term quantum technologies. Most existing methods require prior knowledge of the noise model or the noise parameters. Deep neural networks have a potential to lift this requirement, but current models require training data produced by ideal processes in the absence of noise. Here we build a neural model that achieves quantum error mitigation without any prior knowledge of the noise and without training on noise-free data. To achieve this feature, we introduce a quantum augmentation technique for error mitigation. Our approach applies to quantum circuits and to the dynamics of many-body and continuous-variable quantum systems, accommodating various types of noise models. We demonstrate its effectiveness by testing it both on simulated noisy circuits and on real quantum hardware.

Haoran Wang, Yan Zhu, Wenzheng Qin et al.

The advance of computer-aided detection systems using deep learning opened a new scope in endoscopic image analysis. However, the learning-based models developed on closed datasets are susceptible to unknown anomalies in complex clinical environments. In particular, the high false positive rate of polyp detection remains a major challenge in clinical practice. In this work, we release the FPPD-13 dataset, which provides a taxonomy and real-world cases of typical false positives during computer-aided polyp detection in real-world colonoscopy. We further propose a post-hoc module EndoBoost, which can be plugged into generic polyp detection models to filter out false positive predictions. This is realized by generative learning of the polyp manifold with normalizing flows and rejecting false positives through density estimation. Compared to supervised classification, this anomaly detection paradigm achieves better data efficiency and robustness in open-world settings. Extensive experiments demonstrate a promising false positive suppression in both retrospective and prospective validation. In addition, the released dataset can be used to perform 'stress' tests on established detection systems and encourages further research toward robust and reliable computer-aided endoscopic image analysis. The dataset and code will be publicly available at http://endoboost.miccai.cloud.

Yan Zhu, Junbao Zhuo, Bin Ma et al.

Zero-shot video recognition (ZSVR) is a task that aims to recognize video categories that have not been seen during the model training process. Recently, vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability for ZSVR. To make VLMs applicable to the video domain, existing methods often use an additional temporal learning module after the image-level encoder to learn the temporal relationships among video frames. Unfortunately, for video from unseen categories, we observe an abnormal phenomenon where the model that uses spatial-temporal feature performs much worse than the model that removes temporal learning module and uses only spatial feature. We conjecture that improper temporal modeling on video disrupts the spatial feature of the video. To verify our hypothesis, we propose Feature Factorization to retain the orthogonal temporal feature of the video and use interpolation to construct refined spatial-temporal feature. The model using appropriately refined spatial-temporal feature performs better than the one using only spatial feature, which verifies the effectiveness of the orthogonal temporal feature for the ZSVR task. Therefore, an Orthogonal Temporal Interpolation module is designed to learn a better refined spatial-temporal video feature during training. Additionally, a Matching Loss is introduced to improve the quality of the orthogonal temporal feature. We propose a model called OTI for ZSVR by employing orthogonal temporal interpolation and the matching loss based on VLMs. The ZSVR accuracies on popular video datasets (i.e., Kinetics-600, UCF101 and HMDB51) show that OTI outperforms the previous state-of-the-art method by a clear margin.

Li Zhang, Yan Zhu, Yifeng Gao et al.

Time series motif discovery has been a fundamental task to identify meaningful repeated patterns in time series. Recently, time series chains were introduced as an expansion of time series motifs to identify the continuous evolving patterns in time series data. Informally, a time series chain (TSC) is a temporally ordered set of time series subsequences, in which every subsequence is similar to the one that precedes it, but the last and the first can be arbitrarily dissimilar. TSCs are shown to be able to reveal latent continuous evolving trends in the time series, and identify precursors of unusual events in complex systems. Despite its promising interpretability, unfortunately, we have observed that existing TSC definitions lack the ability to accurately cover the evolving part of a time series: the discovered chains can be easily cut by noise and can include non-evolving patterns, making them impractical in real-world applications. Inspired by a recent work that tracks how the nearest neighbor of a time series subsequence changes over time, we introduce a new TSC definition which is much more robust to noise in the data, in the sense that they can better locate the evolving patterns while excluding the non-evolving ones. We further propose two new quality metrics to rank the discovered chains. With extensive empirical evaluations, we demonstrate that the proposed TSC definition is significantly more robust to noise than the state of the art, and the top ranked chains discovered can reveal meaningful regularities in a variety of real world datasets.

Shuo Wang, Yan Zhu, Xiaoyuan Luo et al.

The development of artificial intelligence systems for colonoscopy analysis often necessitates expert-annotated image datasets. However, limitations in dataset size and diversity impede model performance and generalisation. Image-text colonoscopy records from routine clinical practice, comprising millions of images and text reports, serve as a valuable data source, though annotating them is labour-intensive. Here we leverage recent advancements in large language and vision models and propose EndoKED, a data mining paradigm for deep knowledge extraction and distillation. EndoKED automates the transformation of raw colonoscopy records into image datasets with pixel-level annotation. We validate EndoKED using multi-centre datasets of raw colonoscopy records (~1 million images), demonstrating its superior performance in training polyp detection and segmentation models. Furthermore, the EndoKED pre-trained vision backbone enables data-efficient and generalisable learning for optical biopsy, achieving expert-level performance in both retrospective and prospective validation.

Hao Zhu, Shuo Jin, Wenbin Liao et al.

Pursuing training-free open-vocabulary semantic segmentation in an efficient and generalizable manner remains challenging due to the deep-seated spatial bias in CLIP. To overcome the limitations of existing solutions, this work moves beyond the CLIP-based paradigm and harnesses the recent spatially-aware dino.txt framework to facilitate more efficient and high-quality dense prediction. While dino.txt exhibits robust spatial awareness, we find that the semantic ambiguity of text queries gives rise to severe mismatch within its dense cross-modal interactions. To address this, we introduce \textcolor{oursblue}{\textbf{VI}}sual-guided \textcolor{oursblue}{\textbf{P}}rompt evolution (\textcolor{oursblue}{\textbf{\textit{VIP}}}) to rectify the semantic expressiveness of text queries in dino.txt, unleashing its potential for fine-grained object perception. Towards this end, \VIP integrates alias expansion with a visual-guided distillation mechanism to mine valuable semantic cues, which are robustly aggregated in a saliency-aware manner to yield a high-fidelity prediction. Extensive evaluations demonstrate that \VIP: \ding{182} surpasses the top-leading methods by $1.4\% \sim 8.4\%$ average mIoU, \ding{183} generalizes well to diverse challenging domains, and \ding{184} requires marginal inference time and memory overhead. \href{https://github.com/MiSsU-HH/VIP}{Our code is publicly available at GitHub \faGithub}.

Yan Zhu, Te Luo, Pei-Yao Fu et al.

Multimodal Large Language Models (MLLMs) show promise in gastroenterology, yet their performance against comprehensive clinical workflows and human benchmarks remains unverified. To systematically evaluate state-of-the-art MLLMs across a panoramic gastrointestinal endoscopy workflow and determine their clinical utility compared with human endoscopists. We constructed GI-Bench, a benchmark encompassing 20 fine-grained lesion categories. Twelve MLLMs were evaluated across a five-stage clinical workflow: anatomical localization, lesion identification, diagnosis, findings description, and management. Model performance was benchmarked against three junior endoscopists and three residency trainees using Macro-F1, mean Intersection-over-Union (mIoU), and multi-dimensional Likert scale. Gemini-3-Pro achieved state-of-the-art performance. In diagnostic reasoning, top-tier models (Macro-F1 0.641) outperformed trainees (0.492) and rivaled junior endoscopists (0.727; p>0.05). However, a critical "spatial grounding bottleneck" persisted; human lesion localization (mIoU >0.506) significantly outperformed the best model (0.345; p<0.05). Furthermore, qualitative analysis revealed a "fluency-accuracy paradox": models generated reports with superior linguistic readability compared with humans (p<0.05) but exhibited significantly lower factual correctness (p<0.05) due to "over-interpretation" and hallucination of visual features. GI-Bench maintains a dynamic leaderboard that tracks the evolving performance of MLLMs in clinical endoscopy. The current rankings and benchmark results are available at https://roterdl.github.io/GIBench/.

Gan Pei, Junhao Ning, Boqiu Shen et al.

Remote photoplethysmography (rPPG) enables non-contact heart rate measurement from facial videos, but its performance is significantly degraded by facial motions such as speaking and head shaking. To address this issue, we propose two plug-and-play modules. The Angle-guided ROI Adaptive Optimization module quantifies ROI-Camera angles to refine motion-affected signals and capture global motion, while the Multi-region Joint Graph Signal Denoising module jointly models intra- and inter-regional ROI signals using graph signal processing to suppress motion artifacts. The modules are compatible with reflection model-based rPPG methods and validated on three public datasets. Results show that jointly use markedly reduces MAE, with an average decrease of 20.38\% over the baseline, while ablation studies confirm the effectiveness of each module. The work demonstrates the potential of angle-guided optimization and graph-based denoising to enhance rPPG performance in motion scenarios.

Juyuan Kang, Hao Zhu, Yan Zhu et al.

Crop mapping based on satellite images time-series (SITS) holds substantial economic value in agricultural production settings, in which parcel segmentation is an essential step. Existing approaches have achieved notable advancements in SITS segmentation with predetermined sequence lengths. However, we found that these approaches overlooked the generalization capability of models across scenarios with varying temporal length, leading to markedly poor segmentation results in such cases. To address this issue, we propose TEA, a TEmporal Adaptive SITS semantic segmentation method to enhance the model's resilience under varying sequence lengths. We introduce a teacher model that encapsulates the global sequence knowledge to guide a student model with adaptive temporal input lengths. Specifically, teacher shapes the student's feature space via intermediate embedding, prototypes and soft label perspectives to realize knowledge transfer, while dynamically aggregating student model to mitigate knowledge forgetting. Finally, we introduce full-sequence reconstruction as an auxiliary task to further enhance the quality of representations across inputs of varying temporal lengths. Through extensive experiments, we demonstrate that our method brings remarkable improvements across inputs of different temporal lengths on common benchmarks. Our code will be publicly available.

Hao Zhu, Yan Zhu, Jiayu Xiao et al.

Automated crop mapping through Satellite Image Time Series (SITS) has emerged as a crucial avenue for agricultural monitoring and management. However, due to the low resolution and unclear parcel boundaries, annotating pixel-level masks is exceptionally complex and time-consuming in SITS. This paper embraces the weakly supervised paradigm (i.e., only image-level categories available) to liberate the crop mapping task from the exhaustive annotation burden. The unique characteristics of SITS give rise to several challenges in weakly supervised learning: (1) noise perturbation from spatially neighboring regions, and (2) erroneous semantic bias from anomalous temporal periods. To address the above difficulties, we propose a novel method, termed exploring space-time perceptive clues (Exact). First, we introduce a set of spatial clues to explicitly capture the representative patterns of different crops from the most class-relative regions. Besides, we leverage the temporal-to-class interaction of the model to emphasize the contributions of pivotal clips, thereby enhancing the model perception for crop regions. Build upon the space-time perceptive clues, we derive the clue-based CAMs to effectively supervise the SITS segmentation network. Our method demonstrates impressive performance on various SITS benchmarks. Remarkably, the segmentation network trained on Exact-generated masks achieves 95% of its fully supervised performance, showing the bright promise of weakly supervised paradigm in crop mapping scenario. Our code will be publicly available.

Ruijie Yang, Yan Zhu, Peiyao Fu et al.

Determining the necessity of resecting malignant polyps during colonoscopy screen is crucial for patient outcomes, yet challenging due to the time-consuming and costly nature of histopathology examination. While deep learning-based classification models have shown promise in achieving optical biopsy with endoscopic images, they often suffer from a lack of explainability. To overcome this limitation, we introduce EndoFinder, a content-based image retrieval framework to find the 'digital twin' polyp in the reference database given a newly detected polyp. The clinical semantics of the new polyp can be inferred referring to the matched ones. EndoFinder pioneers a polyp-aware image encoder that is pre-trained on a large polyp dataset in a self-supervised way, merging masked image modeling with contrastive learning. This results in a generic embedding space ready for different downstream clinical tasks based on image retrieval. We validate the framework on polyp re-identification and optical biopsy tasks, with extensive experiments demonstrating that EndoFinder not only achieves explainable diagnostics but also matches the performance of supervised classification models. EndoFinder's reliance on image retrieval has the potential to support diverse downstream decision-making tasks during real-time colonoscopy procedures.

Ruijie Yang, Yan Zhu, Peiyao Fu et al.

Automatic speech recognition (ASR) is a critical interface for human-AI interaction in gastrointestinal endoscopy, yet its reliability in real-world clinical settings is limited by domain-specific terminology and complex acoustic conditions. Here, we present EndoASR, a domain-adapted ASR system designed for real-time deployment in endoscopic workflows. We develop a two-stage adaptation strategy based on synthetic endoscopy reports, targeting domain-specific language modeling and noise robustness. In retrospective evaluation across six endoscopists, EndoASR substantially improves both transcription accuracy and clinical usability, reducing character error rate (CER) from 20.52% to 14.14% and increasing medical term accuracy (Med ACC) from 54.30% to 87.59%. In a prospective multi-center study spanning five independent endoscopy centers, EndoASR demonstrates consistent generalization under heterogeneous real-world conditions. Compared with the baseline Paraformer model, CER is reduced from 16.20% to 14.97%, while Med ACC is improved from 61.63% to 84.16%, confirming its robustness in practical deployment scenarios. Notably, EndoASR achieves a real-time factor (RTF) of 0.005, significantly faster than Whisper-large-v3 (RTF 0.055), while maintaining a compact model size of 220M parameters, enabling efficient edge deployment. Furthermore, integration with large language models demonstrates that improved ASR quality directly enhances downstream structured information extraction and clinician-AI interaction. These results demonstrate that domain-adapted ASR can serve as a reliable interface for human-AI teaming in gastrointestinal endoscopy, with consistent performance validated across multi-center real-world clinical settings.

Jia Yu, Yan Zhu, Peiyao Fu et al.

Rare gastrointestinal lesions are infrequently encountered in routine endoscopy, restricting the data available for developing reliable artificial intelligence (AI) models and training novice clinicians. Here we present EndoRare, a one-shot, retraining-free generative framework that synthesizes diverse, high-fidelity lesion exemplars from a single reference image. By leveraging language-guided concept disentanglement, EndoRare separates pathognomonic lesion features from non-diagnostic attributes, encoding the former into a learnable prototype embedding while varying the latter to ensure diversity. We validated the framework across four rare pathologies (calcifying fibrous tumor, juvenile polyposis syndrome, familial adenomatous polyposis, and Peutz-Jeghers syndrome). Synthetic images were judged clinically plausible by experts and, when used for data augmentation, significantly enhanced downstream AI classifiers, improving the true positive rate at low false-positive rates. Crucially, a blinded reader study demonstrated that novice endoscopists exposed to EndoRare-generated cases achieved a 0.400 increase in recall and a 0.267 increase in precision. These results establish a practical, data-efficient pathway to bridge the rare-disease gap in both computer-aided diagnostics and clinical education.

Yuandong Tian, Yan Zhu

Competing with top human players in the ancient game of Go has been a long-term goal of artificial intelligence. Go's high branching factor makes traditional search techniques ineffective, even on leading-edge hardware, and Go's evaluation function could change drastically with one stone change. Recent works [Maddison et al. (2015); Clark & Storkey (2015)] show that search is not strictly necessary for machine Go players. A pure pattern-matching approach, based on a Deep Convolutional Neural Network (DCNN) that predicts the next move, can perform as well as Monte Carlo Tree Search (MCTS)-based open source Go engines such as Pachi [Baudis & Gailly (2012)] if its search budget is limited. We extend this idea in our bot named darkforest, which relies on a DCNN designed for long-term predictions. Darkforest substantially improves the win rate for pattern-matching approaches against MCTS-based approaches, even with looser search budgets. Against human players, the newest versions, darkfores2, achieve a stable 3d level on KGS Go Server as a ranked bot, a substantial improvement upon the estimated 4k-5k ranks for DCNN reported in Clark & Storkey (2015) based on games against other machine players. Adding MCTS to darkfores2 creates a much stronger player named darkfmcts3: with 5000 rollouts, it beats Pachi with 10k rollouts in all 250 games; with 75k rollouts it achieves a stable 5d level in KGS server, on par with state-of-the-art Go AIs (e.g., Zen, DolBaram, CrazyStone) except for AlphaGo [Silver et al. (2016)]; with 110k rollouts, it won the 3rd place in January KGS Go Tournament.

Junjie Yu, Yue Wang, Zihan Deng et al.

Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions remain unexplored during finetuning? Are these stable directions irrelevant to downstream tasks, or do they already encode task-relevant structure that requires no further adjustment? Answering this question is central to understanding how pretrained knowledge transfers. Through systematic spectral analysis across vision and language models, we show that the leading singular vectors of pretrained weight matrices remain highly stable under finetuning and are shared across unrelated downstream tasks, revealing that pretraining establishes a reusable spectral coordinate system. Models pretrained on larger datasets exhibit greater spectral stability under distribution shift or task change, directly linking pretraining scale to geometric transferability. Motivated by these findings, we propose a parameter-efficient method that freezes pretrained singular vectors and optimizes only leading spectral coefficients, achieving competitive performance on GLUE with 0.2% trainable parameters. Our results reveal that the stable directions encode transferable structure rather than irrelevant noise: successful pretraining discovers spectral bases that downstream tasks inherit and operate within.

Zhaoxuan Tan, Xiang Zhai, Yan Zhu et al.

Personalized systems rely on user representations to connect behavioral history with downstream recommendation applications. Existing methods typically employ either supervised latent user embeddings, which are effective for retrieval but difficult to interpret, or textual user profiles, which are interpretable but challenging to optimize for downstream utility due to lack of direct supervision. To bridge this gap, we present BLUE, a reinforcement learning framework that unifies these two forms of user representation by aligning language-based user profiles with embedding-based recommendation objectives. Given a user interaction history, BLUE leverages a profiler Large Language Model (LLM) to generate textual profiles, while an embedding model provides reward signals. This encourages the resulting textual representations to move closer to positive items and farther from negative ones in the embedding space. We further introduce a text-space supervision signal based on next-item prediction, ensuring the learned profiles remain both semantically meaningful and highly effective for downstream retrieval. Experiments on Amazon Reviews 2023 and Google Local Reviews in zero-shot sequential recommendation settings demonstrate that BLUE consistently outperforms strong baselines under both frozen and trainable embedding conditions. Notably, BLUE achieves clear gains in cross-domain transfer, highlighting the strong generalization ability of the learned user profiles. Furthermore, these generated profiles provide superior personalized context for question answering compared to raw user histories or alternative profile optimization methods. Overall, these results show that BLUE provides an effective way to unify interpretable textual profiling with discriminative latent embeddings for personalization.

Mi Yan, Jiazhao Zhang, Yan Zhu et al.

Open-vocabulary 3D instance segmentation is cutting-edge for its ability to segment 3D instances without predefined categories. However, progress in 3D lags behind its 2D counterpart due to limited annotated 3D data. To address this, recent works first generate 2D open-vocabulary masks through 2D models and then merge them into 3D instances based on metrics calculated between two neighboring frames. In contrast to these local metrics, we propose a novel metric, view consensus rate, to enhance the utilization of multi-view observations. The key insight is that two 2D masks should be deemed part of the same 3D instance if a significant number of other 2D masks from different views contain both these two masks. Using this metric as edge weight, we construct a global mask graph where each mask is a node. Through iterative clustering of masks showing high view consensus, we generate a series of clusters, each representing a distinct 3D instance. Notably, our model is training-free. Through extensive experiments on publicly available datasets, including ScanNet++, ScanNet200 and MatterPort3D, we demonstrate that our method achieves state-of-the-art performance in open-vocabulary 3D instance segmentation. Our project page is at https://pku-epic.github.io/MaskClustering.

Haotian Xia, Zhengbang Yang, Yuqing Wang et al. · stanford

A deep understanding of sports, a field rich in strategic and dynamic content, is crucial for advancing Natural Language Processing (NLP). This holds particular significance in the context of evaluating and advancing Large Language Models (LLMs), given the existing gap in specialized benchmarks. To bridge this gap, we introduce SportQA, a novel benchmark specifically designed for evaluating LLMs in the context of sports understanding. SportQA encompasses over 70,000 multiple-choice questions across three distinct difficulty levels, each targeting different aspects of sports knowledge from basic historical facts to intricate, scenario-based reasoning tasks. We conducted a thorough evaluation of prevalent LLMs, mainly utilizing few-shot learning paradigms supplemented by chain-of-thought (CoT) prompting. Our results reveal that while LLMs exhibit competent performance in basic sports knowledge, they struggle with more complex, scenario-based sports reasoning, lagging behind human expertise. The introduction of SportQA marks a significant step forward in NLP, offering a tool for assessing and enhancing sports understanding in LLMs.

Huan Ma, Yan Zhu, Changqing Zhang et al.

Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data. However, these models also display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of ``decision shortcuts'' that hinder their generalization capabilities. In this work, we find that the CLIP model possesses a rich set of features, encompassing both \textit{desired invariant causal features} and \textit{undesired decision shortcuts}. Moreover, the underperformance of CLIP on downstream tasks originates from its inability to effectively utilize pre-trained features in accordance with specific task requirements. To address this challenge, we propose a simple yet effective method, Spurious Feature Eraser (SEraser), to alleviate the decision shortcuts by erasing the spurious features. Specifically, we introduce a test-time prompt tuning paradigm that optimizes a learnable prompt, thereby compelling the model to exploit invariant features while disregarding decision shortcuts during the inference phase. The proposed method effectively alleviates excessive dependence on potentially misleading spurious information. We conduct comparative analysis of the proposed method against various approaches which validates the significant superiority.

Yuxuan Du, Yan Zhu, Yuan-Hang Zhang et al.

Efficient characterization of large-scale quantum systems, especially those produced by quantum analog simulators and megaquop quantum computers, poses a central challenge in quantum science due to the exponential scaling of the Hilbert space with respect to system size. Recent advances in artificial intelligence (AI), with its aptitude for high-dimensional pattern recognition and function approximation, have emerged as a powerful tool to address this challenge. A growing body of research has leveraged AI to represent and characterize scalable quantum systems, spanning from theoretical foundations to experimental realizations. Depending on how prior knowledge and learning architectures are incorporated, the integration of AI into quantum system characterization can be categorized into three synergistic paradigms: machine learning, and, in particular, deep learning and language models. This review discusses how each of these AI paradigms contributes to two core tasks in quantum systems characterization: quantum property prediction and the construction of surrogates for quantum states. These tasks underlie diverse applications, from quantum certification and benchmarking to the enhancement of quantum algorithms and the understanding of strongly correlated phases of matter. Key challenges and open questions are also discussed, together with future prospects at the interface of AI and quantum science.

Jiaxin Huang, Yan Zhu, Giulio Chiribella et al.

Characterization of quantum systems from experimental data is a central problem in quantum science and technology. But which measurements should be used to gather data in the first place? While optimal measurement choices can be worked out for small quantum systems, the optimization becomes intractable as the system size grows large. To address this problem, we introduce a deep neural network with a sequence model architecture that searches for efficient measurement choices in a data-driven, adaptive manner. The model can be applied to a variety of tasks, including the prediction of linear and nonlinear properties of quantum states, as well as state clustering and state tomography tasks. In all these tasks, we find that the measurement choices identified by our neural network consistently outperform the uniformly random choice. Intriguingly, for topological quantum systems, our model tends to recommend measurements at the system's boundaries, even when the task is to predict bulk properties. This behavior suggests that the neural network may have independently discovered a connection between boundaries and bulk, without having been provided any built-in knowledge of quantum physics.

Yan Zhu, Shihao Wang, Yong Han et al.

Air pollution, particularly airborne particulate matter (PM), poses a significant threat to public health globally. It is crucial to comprehend the association between PM-associated toxic components and their cellular targets in humans to understand the mechanisms by which air pollution impacts health and to establish causal relationships between air pollution and public health consequences. Although many studies have explored the impact of PM on human health, the understanding of the association between toxins and the associated targets remain limited. Leveraging cutting-edge deep learning technologies, we developed tipFormer (toxin-protein interaction prediction based on transformer), a novel deep-learning tool for identifying toxic components capable of penetrating human cells and instigating pathogenic biological activities and signaling cascades. Experimental results show that tipFormer effectively captures interactions between proteins and toxic components. It incorporates dual pre-trained language models to encode protein sequences and chemicals. It employs a convolutional encoder to assimilate the sequential attributes of proteins and chemicals. It then introduces a learning module with a cross-attention mechanism to decode and elucidate the multifaceted interactions pivotal for the hotspots binding proteins and chemicals. Experimental results show that tipFormer effectively captures interactions between proteins and toxic components. This approach offers significant value to air quality and toxicology researchers by allowing high-throughput identification and prioritization of hazards. It supports more targeted laboratory studies and field measurements, ultimately enhancing our understanding of how air pollution impacts human health.

Jia Yu, Yan Zhu, Peiyao Fu et al.

Colorectal cancer (CRC) is a significant global health concern, and early detection through screening plays a critical role in reducing mortality. While deep learning models have shown promise in improving polyp detection, classification, and segmentation, their generalization across diverse clinical environments, particularly with out-of-distribution (OOD) data, remains a challenge. Multi-center datasets like PolypGen have been developed to address these issues, but their collection is costly and time-consuming. Traditional data augmentation techniques provide limited variability, failing to capture the complexity of medical images. Diffusion models have emerged as a promising solution for generating synthetic polyp images, but the image generation process in current models mainly relies on segmentation masks as the condition, limiting their ability to capture the full clinical context. To overcome these limitations, we propose a Progressive Spectrum Diffusion Model (PSDM) that integrates diverse clinical annotations-such as segmentation masks, bounding boxes, and colonoscopy reports-by transforming them into compositional prompts. These prompts are organized into coarse and fine components, allowing the model to capture both broad spatial structures and fine details, generating clinically accurate synthetic images. By augmenting training data with PSDM-generated samples, our model significantly improves polyp detection, classification, and segmentation. For instance, on the PolypGen dataset, PSDM increases the F1 score by 2.12% and the mean average precision by 3.09%, demonstrating superior performance in OOD scenarios and enhanced generalization.

Zhe Liu, Kai Han, Siqi Ma et al.

Computer-aided diagnosis (CAD) technology can assist clinicians in evaluating liver lesions and intervening with treatment in time. Although CAD technology has advanced in recent years, the application scope of existing datasets remains relatively limited, typically supporting only single tasks, which has somewhat constrained the development of CAD technology. To address the above limitation, in this paper, we construct a multi-task liver dataset (LiMT) used for liver and tumor segmentation, multi-label lesion classification, and lesion detection based on arterial phase-enhanced computed tomography (CT), potentially providing an exploratory solution that is able to explore the correlation between tasks and does not need to worry about the heterogeneity between task-specific datasets during training. The dataset includes CT volumes from 150 different cases, comprising four types of liver diseases as well as normal cases. Each volume has been carefully annotated and calibrated by experienced clinicians. This public multi-task dataset may become a valuable resource for the medical imaging research community in the future. In addition, this paper not only provides relevant baseline experimental results but also reviews existing datasets and methods related to liver-related tasks. Our dataset is available at https://drive.google.com/drive/folders/1l9HRK13uaOQTNShf5pwgSz3OTanWjkag?usp=sharing.

Yili He, Yan Zhu, Peiyao Fu et al.

Pre-training on image-text colonoscopy records offers substantial potential for improving endoscopic image analysis, but faces challenges including non-informative background images, complex medical terminology, and ambiguous multi-lesion descriptions. We introduce Endo-CLIP, a novel self-supervised framework that enhances Contrastive Language-Image Pre-training (CLIP) for this domain. Endo-CLIP's three-stage framework--cleansing, attunement, and unification--addresses these challenges by (1) removing background frames, (2) leveraging large language models to extract clinical attributes for fine-grained contrastive learning, and (3) employing patient-level cross-attention to resolve multi-polyp ambiguities. Extensive experiments demonstrate that Endo-CLIP significantly outperforms state-of-the-art pre-training methods in zero-shot and few-shot polyp detection and classification, paving the way for more accurate and clinically relevant endoscopic analysis.

Yan Zhu, Jingyang Zhu, Ting Wang et al.

Advancements in artificial intelligence (AI) and low-earth orbit (LEO) satellites have promoted the application of large remote sensing foundation models for various downstream tasks. However, direct downloading of these models for fine-tuning on the ground is impeded by privacy concerns and limited bandwidth. Satellite federated learning (FL) offers a solution by enabling model fine-tuning directly on-board satellites and aggregating model updates without data downloading. Nevertheless, for large foundation models, the computational capacity of satellites is insufficient to support effective on-board fine-tuning in traditional satellite FL frameworks. To address these challenges, we propose a satellite-ground collaborative federated fine-tuning framework. The key of the framework lies in how to reasonably decompose and allocate model components to alleviate insufficient on-board computation capabilities. During fine-tuning, satellites exchange intermediate results with ground stations or other satellites for forward propagation and back propagation, which brings communication challenges due to the special communication topology of space transmission networks, such as intermittent satellite-ground communication, short duration of satellite-ground communication windows, and unstable inter-orbit inter-satellite links (ISLs). To reduce transmission delays, we further introduce tailored communication strategies that integrate both communication and computing resources. Specifically, we propose a parallel intra-orbit communication strategy, a topology-aware satellite-ground communication strategy, and a latency-minimalization inter-orbit communication strategy to reduce space communication costs. Simulation results demonstrate significant reductions in training time with improvements of approximately 33%.

Yan Zhu, Huan Ma, Changqing Zhang

With the development of Vision Foundation Models (VFMs) in recent years, Visual In-Context Learning (VICL) has become a better choice compared to modifying models in most scenarios. Different from retraining or fine-tuning model, VICL does not require modifications to the model's weights or architecture, and only needs a prompt with demonstrations to teach VFM how to solve tasks. Currently, significant computational cost for finding optimal prompts for every test sample hinders the deployment of VICL, as determining which demonstrations to use for constructing prompts is very costly. In this paper, however, we find a counterintuitive phenomenon that most test samples actually achieve optimal performance under the same prompts, and searching for sample-level prompts only costs more time but results in completely identical prompts. Therefore, we propose task-level prompting to reduce the cost of searching for prompts during the inference stage and introduce two time-saving yet effective task-level prompt search strategies. Extensive experimental results show that our proposed method can identify near-optimal prompts and reach the best VICL performance with a minimal cost that prior work has never achieved.

Jian Kang, Yan Zhu, Yinglong Xia et al.

Graph Convolutional Network (GCN) plays pivotal roles in many real-world applications. Despite the successes of GCN deployment, GCN often exhibits performance disparity with respect to node degrees, resulting in worse predictive accuracy for low-degree nodes. We formulate the problem of mitigating the degree-related performance disparity in GCN from the perspective of the Rawlsian difference principle, which is originated from the theory of distributive justice. Mathematically, we aim to balance the utility between low-degree nodes and high-degree nodes while minimizing the task-specific loss. Specifically, we reveal the root cause of this degree-related unfairness by analyzing the gradients of weight matrices in GCN. Guided by the gradients of weight matrices, we further propose a pre-processing method RawlsGCN-Graph and an in-processing method RawlsGCN-Grad that achieves fair predictive accuracy in low-degree nodes without modification on the GCN architecture or introduction of additional parameters. Extensive experiments on real-world graphs demonstrate the effectiveness of our proposed RawlsGCN methods in significantly reducing degree-related bias while retaining comparable overall performance.

Yan Zhu, Ya-Dong Wu, Ge Bai et al.

Deep neural networks are a powerful tool for the characterization of quantum states. Existing networks are typically trained with experimental data gathered from the specific quantum state that needs to be characterized. But is it possible to train a neural network offline and to make predictions about quantum states other than the ones used for the training? Here we introduce a model of network that can be trained with classically simulated data from a fiducial set of states and measurements, and can later be used to characterize quantum states that share structural similarities with the states in the fiducial set. With little guidance of quantum physics, the network builds its own data-driven representation of quantum states, and then uses it to predict the outcome statistics of quantum measurements that have not been performed yet. The state representation produced by the network can also be used for tasks beyond the prediction of outcome statistics, including clustering of quantum states and identification of different phases of matter. Our network model provides a flexible approach that can be applied to online learning scenarios, where predictions must be generated as soon as experimental data become available, and to blind learning scenarios where the learner has only access to an encrypted description of the quantum hardware.

Xinshi Chen, Yan Zhu, Haowen Xu et al.

Dynamic graphs with ordered sequences of events between nodes are prevalent in real-world industrial applications such as e-commerce and social platforms. However, representation learning for dynamic graphs has posed great computational challenges due to the time and structure dependency and irregular nature of the data, preventing such models from being deployed to real-world applications. To tackle this challenge, we propose an efficient algorithm, Efficient Dynamic Graph lEarning (EDGE), which selectively expresses certain temporal dependency via training loss to improve the parallelism in computations. We show that EDGE can scale to dynamic graphs with millions of nodes and hundreds of millions of temporal events and achieve new state-of-the-art (SOTA) performance.

Tigran Ishkhanov, Maxim Naumov, Xianjie Chen et al.

In this paper we develop a novel recommendation model that explicitly incorporates time information. The model relies on an embedding layer and TSL attention-like mechanism with inner products in different vector spaces, that can be thought of as a modification of multi-headed attention. This mechanism allows the model to efficiently treat sequences of user behavior of different length. We study the properties of our state-of-the-art model on statistically designed data set. Also, we show that it outperforms more complex models with longer sequence length on the Taobao User Behavior dataset.

Chin-Chia Michael Yeh, Yan Zhu, Evangelos E. Papalexakis et al.

Since its introduction, unsupervised representation learning has attracted a lot of attention from the research community, as it is demonstrated to be highly effective and easy-to-apply in tasks such as dimension reduction, clustering, visualization, information retrieval, and semi-supervised learning. In this work, we propose a novel unsupervised representation learning framework called neighbor-encoder, in which domain knowledge can be easily incorporated into the learning process without modifying the general encoder-decoder architecture of the classic autoencoder.In contrast to autoencoder, which reconstructs the input data itself, neighbor-encoder reconstructs the input data's neighbors. As the proposed representation learning problem is essentially a neighbor reconstruction problem, domain knowledge can be easily incorporated in the form of an appropriate definition of similarity between objects. Based on that observation, our framework can leverage any off-the-shelf similarity search algorithms or side information to find the neighbor of an input object. Applications of other algorithms (e.g., association rule mining) in our framework are also possible, given that the appropriate definition of neighbor can vary in different contexts. We have demonstrated the effectiveness of our framework in many diverse domains, including images, text, and time series, and for various data mining tasks including classification, clustering, and visualization. Experimental results show that neighbor-encoder not only outperforms autoencoder in most of the scenarios we consider, but also achieves the state-of-the-art performance on text document clustering.

Hoang Anh Dau, Anthony Bagnall, Kaveh Kamgar et al.

The UCR Time Series Archive - introduced in 2002, has become an important resource in the time series data mining community, with at least one thousand published papers making use of at least one data set from the archive. The original incarnation of the archive had sixteen data sets but since that time, it has gone through periodic expansions. The last expansion took place in the summer of 2015 when the archive grew from 45 to 85 data sets. This paper introduces and will focus on the new data expansion from 85 to 128 data sets. Beyond expanding this valuable resource, this paper offers pragmatic advice to anyone who may wish to evaluate a new algorithm on the archive. Finally, this paper makes a novel and yet actionable claim: of the hundreds of papers that show an improvement over the standard baseline (1-nearest neighbor classification), a large fraction may be mis-attributing the reasons for their improvement. Moreover, they may have been able to achieve the same improvement with a much simpler modification, requiring just a single line of code.

Yan Zhu, Abdullah Mueen, Eamonn Keogh

The discovery of time series motifs has emerged as one of the most useful primitives in time series data mining. Researchers have shown its utility for exploratory data mining, summarization, visualization, segmentation, classification, clustering, and rule discovery. Although there has been more than a decade of extensive research, there is still no technique to allow the discovery of time series motifs in the presence of missing data, despite the well-documented ubiquity of missing data in scientific, industrial, and medical datasets. In this work, we introduce a technique for motif discovery in the presence of missing data. We formally prove that our method is admissible, producing no false negatives. We also show that our method can piggy-back off the fastest known motif discovery method with a small constant factor time/space overhead. We will demonstrate our approach on diverse datasets with varying amounts of missing data

Yan Zhu, Shaoting Zhang, Dimitris Metaxas

Humans are able to identify a referred visual object in a complex scene via a few rounds of natural language communications. Success communication requires both parties to engage and learn to adapt for each other. In this paper, we introduce an interactive training method to improve the natural language conversation system for a visual grounding task. During interactive training, both agents are reinforced by the guidance from a common reward function. The parametrized reward function also cooperatively updates itself via interactions, and contribute to accomplishing the task. We evaluate the method on GuessWhat?! visual grounding task, and significantly improve the task success rate. However, we observe language drifting problem during training and propose to use reward engineering to improve the interpretability for the generated conversations. Our result also indicates evaluating goal-ended visual conversation tasks require semantic relevant metrics beyond task success rate.

Yan Zhu, Yuandong Tian, Dimitris Mexatas et al.

Common visual recognition tasks such as classification, object detection, and semantic segmentation are rapidly reaching maturity, and given the recent rate of progress, it is not unreasonable to conjecture that techniques for many of these problems will approach human levels of performance in the next few years. In this paper we look to the future: what is the next frontier in visual recognition? We offer one possible answer to this question. We propose a detailed image annotation that captures information beyond the visible pixels and requires complex reasoning about full scene structure. Specifically, we create an amodal segmentation of each image: the full extent of each region is marked, not just the visible pixels. Annotators outline and name all salient regions in the image and specify a partial depth order. The result is a rich scene structure, including visible and occluded portions of each region, figure-ground edge information, semantic labels, and object overlap. We create two datasets for semantic amodal segmentation. First, we label 500 images in the BSDS dataset with multiple annotators per image, allowing us to study the statistics of human annotations. We show that the proposed full scene annotation is surprisingly consistent between annotators, including for regions and edges. Second, we annotate 5000 images from COCO. This larger dataset allows us to explore a number of algorithmic ideas for amodal segmentation and depth ordering. We introduce novel metrics for these tasks, and along with our strong baselines, define concrete new challenges for the community.

Cheng-yi Zhang, Shuanghua Luo, Yan Zhu

To solve non-Hermitian linear system Ax=b on parallel and vector machines, some paralell multisplitting methods are considered. In this work, in particular: i) We establish the convergence results of the paralell multisplitting methods, together with its relaxed version, some of which can be regarded as generalizations of analogous results for the Hermitian positive definite case; ii) We extend the positive-definite and skew-Hermitian splitting (PSS) method methods in [{\em SIAM J. Sci. Comput.}, 26:844--863, 2005] to the parallel PSS methods and propose the corresponding convergence results.

Haoyu Li, Di Ma, Nitesh Saxena et al.

In this paper, we introduce a lightweight permission enforcement approach - Tap-Wave-Rub (TWR) - for smartphone malware prevention. TWR is based on simple human gestures that are very quick and intuitive but less likely to be exhibited in users' daily activities. Presence or absence of such gestures, prior to accessing an application, can effectively inform the OS whether the access request is benign or malicious. Specifically, we present the design of two mechanisms: (1) accelerometer based phone tapping detection; and (2) proximity sensor based finger tapping, rubbing or hand waving detection. The first mechanism is geared for NFC applications, which usually require the user to tap her phone with another device. The second mechanism involves very simple gestures, i.e., tapping or rubbing a finger near the top of phone's screen or waving a hand close to the phone, and broadly appeals to many applications (e.g., SMS). In addition, we present the TWR-enhanced Android permission model, the prototypes implementing the underlying gesture recognition mechanisms, and a variety of novel experiments to evaluate these mechanisms. Our results suggest the proposed approach could be very effective for malware detection and prevention, with quite low false positives and false negatives, while imposing little to no additional burden on the users.