Sen Wang

Haiyang Wang, Chen Shi, Shaoshuai Shi et al. · pku

Designing an efficient yet deployment-friendly 3D backbone to handle sparse point clouds is a fundamental problem in 3D perception. Compared with the customized sparse convolution, the attention mechanism in Transformers is more appropriate for flexibly modeling long-range relationships and is easier to be deployed in real-world applications. However, due to the sparse characteristics of point clouds, it is non-trivial to apply a standard transformer on sparse points. In this paper, we present Dynamic Sparse Voxel Transformer (DSVT), a single-stride window-based voxel Transformer backbone for outdoor 3D perception. In order to efficiently process sparse points in parallel, we propose Dynamic Sparse Window Attention, which partitions a series of local regions in each window according to its sparsity and then computes the features of all regions in a fully parallel manner. To allow the cross-set connection, we design a rotated set partitioning strategy that alternates between two partitioning configurations in consecutive self-attention layers. To support effective downsampling and better encode geometric information, we also propose an attention-style 3D pooling module on sparse points, which is powerful and deployment-friendly without utilizing any customized CUDA operations. Our model achieves state-of-the-art performance with a broad range of 3D perception tasks. More importantly, DSVT can be easily deployed by TensorRT with real-time inference speed (27Hz). Code will be available at \url{https://github.com/Haiyang-W/DSVT}.

Zhi Chen, Pengfei Zhang, Jingjing Li et al.

Zero-Shot Learning (ZSL) aims to recognize unseen classes by generalizing the knowledge, i.e., visual and semantic relationships, obtained from seen classes, where image augmentation techniques are commonly applied to improve the generalization ability of a model. However, this approach can also cause adverse effects on ZSL since the conventional augmentation techniques that solely depend on single-label supervision is not able to maintain semantic information and result in the semantic distortion issue consequently. In other words, image argumentation may falsify the semantic (e.g., attribute) information of an image. To take the advantage of image augmentations while mitigating the semantic distortion issue, we propose a novel ZSL approach by Harnessing Adversarial Samples (HAS). HAS advances ZSL through adversarial training which takes into account three crucial aspects: (1) robust generation by enforcing augmentations to be similar to negative classes, while maintaining correct labels, (2) reliable generation by introducing a latent space constraint to avert significant deviations from the original data manifold, and (3) diverse generation by incorporating attribute-based perturbation by adjusting images according to each semantic attribute's localization. Through comprehensive experiments on three prominent zero-shot benchmark datasets, we demonstrate the effectiveness of our adversarial samples approach in both ZSL and Generalized Zero-Shot Learning (GZSL) scenarios. Our source code is available at https://github.com/uqzhichen/HASZSL.

James Pak, Jyun-Yu Jiang, Fan Zhang et al.

Scaling a Search Conversion Rate (CVR) prediction model, especially in high-traffic environments, presents a challenge: superior model quality needs to be balanced with strict constraints on training cost and serving latency. This paper details an effective approach for scaling modern search CVR prediction models. We begin with an empirical study to understand the scaling performance of search CVR models, analyzing how quality improves as we scale three key factors of model backbone computation, the size of embedding parameters, and the volume of training data. We use a large-scale production dataset, comprising over a year of customer interaction logs from a high-traffic e-commerce platform, to evaluate the scalability of several state-of-the-art architectures and their ensembles. Our key findings are: (1) selecting the right backbone and scaling factors is crucial; (2) the impact of scaling backbone, embedding, and data is largely independent and additive, which has implications for more efficient scaling exploration; (3) a streamlined warmstart strategy can accelerate training iterations while simplifying new updates; (4) inference optimization strategies such as decoupled graph execution and dynamic batching can enable low-latency GPU serving even for high-capacity models. Compared to a baseline of a pre-scaling production model, we ultimately deployed a model trained on 2.5x larger training data with 8x more inference compute while having minimal latency impact. Online A/B tests also demonstrate that our launches achieved a combined +2.6% gain in a key metric of search conversion rate.

PSBC LLM Team, Huawei LLM Team, Ruihan Long et al.

Large language models (LLMs) drive significant financial innovations, yet their high-concurrency deployment is severely bottlenecked by KV cache memory overhead, which inflates infrastructure costs and throttles scalability. To address this, we propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline natively built on the Huawei Ascend ecosystem. At its algorithmic core, YouZhi-LLM features a layer-adaptive GQA-to-MLA transition framework that dynamically assigns per-layer FreqFold sizes, maximizing KV-cache compression while minimizing perplexity degradation. To recover representation capacity and inject domain expertise, the Ascend-based training pipeline seamlessly integrates generalized knowledge distillation with financial-specific supervised fine-tuning. Evaluations demonstrate the superiority of this systematic approach, with the adaptive transition reducing perplexity degradation by up to 35% over uniform baselines. Crucially, when evaluated on Ascend NPUs via vLLM-Ascend, the massive KV-cache reduction translates directly into deployment efficiency. Compared to their respective base models, YouZhi-7B yields a 12.3% improvement in average financial benchmark score alongside a 2.69$\times$ increase in maximum concurrency; similarly, YouZhi-14B achieves a 7.0% accuracy gain and a 2.43$\times$ concurrency boost, establishing a new paradigm for cost-effective, high-throughput financial inference.

Shihao Zou, Yuxuan Mu, Wei Ji et al.

Event camera, as an asynchronous vision sensor capturing scene dynamics, presents new opportunities for highly efficient 3D human pose tracking. Existing approaches typically adopt modern-day Artificial Neural Networks (ANNs), such as CNNs or Transformer, where sparse events are converted into dense images or paired with additional gray-scale images as input. Such practices, however, ignore the inherent sparsity of events, resulting in redundant computations, increased energy consumption, and potentially degraded performance. Motivated by these observations, we introduce the first sparse Spiking Neural Networks (SNNs) framework for 3D human pose tracking based solely on events. Our approach eliminates the need to convert sparse data to dense formats or incorporate additional images, thereby fully exploiting the innate sparsity of input events. Central to our framework is a novel Spiking Spatiotemporal Transformer, which enables bi-directional spatiotemporal fusion of spike pose features and provides a guaranteed similarity measurement between binary spike features in spiking attention. Moreover, we have constructed a large-scale synthetic dataset, SynEventHPD, that features a broad and diverse set of 3D human motions, as well as much longer hours of event streams. Empirical experiments demonstrate the superiority of our approach over existing state-of-the-art (SOTA) ANN-based methods, requiring only 19.1% FLOPs and 3.6% energy cost. Furthermore, our approach outperforms existing SNN-based benchmarks in this task, highlighting the effectiveness of our proposed SNN framework. The dataset will be released upon acceptance, and code can be found at https://github.com/JimmyZou/HumanPoseTracking_SNN.

Xiang Wang, Tingting Zhang, Sen Wang et al.

Large Language Models are increasingly applied in the petroleum industry, highlighting the need for a domain-specific evaluation framework. This study develops a benchmark for LLMs in petroleum engineering, including a three-stage process of data preprocessing, quality filtering, and multi-model validation. Using expert review, a standardized question bank with strong domain relevance and discriminative capability was constructed. The benchmark covers production, reservoir, and drilling engineering, with 1,200 questions across multiple-choice, true or false, term definition, and short-answer formats. Eight mainstream LLMs were evaluated under a unified API environment. Results show that models performed better on subjective than objective questions, indicating weaknesses in factual knowledge discrimination. The highest accuracies for multiple-choice and true or false questions were 65.3% and 74.3%, respectively. Gemini-3-Pro, Kimi-K2.5, and Claude-Opus-4.6-Thinking achieved the best overall scores of 72%-74%. Models performed best in production engineering and weakest in reservoir engineering. Chinese models showed advantages in multiple-choice questions, while international models performed slightly better in short-answer questions. The benchmark provides a reproducible and practical reference for evaluating and deploying LLMs in petroleum engineering.

Zixin Wang, Yadan Luo, Liang Zheng et al.

This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival. Despite the recent proliferation of OTTA methods, conclusions from previous studies are inconsistent due to ambiguous settings, outdated backbones, and inconsistent hyperparameter tuning, which obscure core challenges and hinder reproducibility. To enhance clarity and enable rigorous comparison, we classify OTTA techniques into three primary categories and benchmark them using a modern backbone, the Vision Transformer (ViT). Our benchmarks cover conventional corrupted datasets such as CIFAR-10/100-C and ImageNet-C, as well as real-world shifts represented by CIFAR-10.1, OfficeHome, and CIFAR-10-Warehouse. The CIFAR-10-Warehouse dataset includes a variety of variations from different search engines and synthesized data generated through diffusion models. To measure efficiency in online scenarios, we introduce novel evaluation metrics, including GFLOPs, wall clock time, and GPU memory usage, providing a clearer picture of the trade-offs between adaptation accuracy and computational overhead. Our findings diverge from existing literature, revealing that (1) transformers demonstrate heightened resilience to diverse domain shifts, (2) the efficacy of many OTTA methods relies on large batch sizes, and (3) stability in optimization and resistance to perturbations are crucial during adaptation, particularly when the batch size is 1. Based on these insights, we highlight promising directions for future research. Our benchmarking toolkit and source code are available at https://github.com/Jo-wang/OTTA_ViT_survey.

Chuan Guo, Xinxin Zuo, Sen Wang et al.

Inspired by the strong ties between vision and language, the two intimate human sensing and communication modalities, our paper aims to explore the generation of 3D human full-body motions from texts, as well as its reciprocal task, shorthanded for text2motion and motion2text, respectively. To tackle the existing challenges, especially to enable the generation of multiple distinct motions from the same text, and to avoid the undesirable production of trivial motionless pose sequences, we propose the use of motion token, a discrete and compact motion representation. This provides one level playing ground when considering both motions and text signals, as the motion and text tokens, respectively. Moreover, our motion2text module is integrated into the inverse alignment process of our text2motion training pipeline, where a significant deviation of synthesized text from the input text would be penalized by a large training loss; empirically this is shown to effectively improve performance. Finally, the mappings in-between the two modalities of motions and texts are facilitated by adapting the neural model for machine translation (NMT) to our context. This autoregressive modeling of the distribution over discrete motion tokens further enables non-deterministic production of pose sequences, of variable lengths, from an input text. Our approach is flexible, could be used for both text2motion and motion2text tasks. Empirical evaluations on two benchmark datasets demonstrate the superior performance of our approach on both tasks over a variety of state-of-the-art methods. Project page: https://ericguo5513.github.io/TM2T/

Sen Wang, Jin Zheng

Monocular 3D object detection is an inherently ill-posed problem, as it is challenging to predict accurate 3D localization from a single image. Existing monocular 3D detection knowledge distillation methods usually project the LiDAR onto the image plane and train the teacher network accordingly. Transferring LiDAR-based model knowledge to RGB-based models is more complex, so a general distillation strategy is needed. To alleviate cross-modal prob-lem, we propose MonoSKD, a novel Knowledge Distillation framework for Monocular 3D detection based on Spearman correlation coefficient, to learn the relative correlation between cross-modal features. Considering the large gap between these features, strict alignment of features may mislead the training, so we propose a looser Spearman loss. Furthermore, by selecting appropriate distillation locations and removing redundant modules, our scheme saves more GPU resources and trains faster than existing methods. Extensive experiments are performed to verify the effectiveness of our framework on the challenging KITTI 3D object detection benchmark. Our method achieves state-of-the-art performance until submission with no additional inference computational cost. Our codes are available at https://github.com/Senwang98/MonoSKD

Xuwei Xu, Sen Wang, Yudong Chen et al.

Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands. To expedite pre-trained ViTs, token pruning and token merging approaches have been developed, which aim at reducing the number of tokens involved in the computation. However, these methods still have some limitations, such as image information loss from pruned tokens and inefficiency in the token-matching process. In this paper, we introduce a novel Graph-based Token Propagation (GTP) method to resolve the challenge of balancing model efficiency and information preservation for efficient ViTs. Inspired by graph summarization algorithms, GTP meticulously propagates less significant tokens' information to spatially and semantically connected tokens that are of greater importance. Consequently, the remaining few tokens serve as a summarization of the entire token graph, allowing the method to reduce computational complexity while preserving essential information of eliminated tokens. Combined with an innovative token selection strategy, GTP can efficiently identify image tokens to be propagated. Extensive experiments have validated GTP's effectiveness, demonstrating both efficiency and performance improvements. Specifically, GTP decreases the computational complexity of both DeiT-S and DeiT-B by up to 26% with only a minimal 0.3% accuracy drop on ImageNet-1K without finetuning, and remarkably surpasses the state-of-the-art token merging method on various backbones at an even faster inference speed. The source code is available at https://github.com/Ackesnal/GTP-ViT.

Chuan Guo, Yuxuan Mu, Muhammad Gohar Javed et al.

We introduce MoMask, a novel masked modeling framework for text-driven 3D human motion generation. In MoMask, a hierarchical quantization scheme is employed to represent human motion as multi-layer discrete motion tokens with high-fidelity details. Starting at the base layer, with a sequence of motion tokens obtained by vector quantization, the residual tokens of increasing orders are derived and stored at the subsequent layers of the hierarchy. This is consequently followed by two distinct bidirectional transformers. For the base-layer motion tokens, a Masked Transformer is designated to predict randomly masked motion tokens conditioned on text input at training stage. During generation (i.e. inference) stage, starting from an empty sequence, our Masked Transformer iteratively fills up the missing tokens; Subsequently, a Residual Transformer learns to progressively predict the next-layer tokens based on the results from current layer. Extensive experiments demonstrate that MoMask outperforms the state-of-art methods on the text-to-motion generation task, with an FID of 0.045 (vs e.g. 0.141 of T2M-GPT) on the HumanML3D dataset, and 0.228 (vs 0.514) on KIT-ML, respectively. MoMask can also be seamlessly applied in related tasks without further model fine-tuning, such as text-guided temporal inpainting.

MD Wahiduzzaman Khan, Hongwei Sheng, Hu Zhang et al.

Retinal vessel segmentation is generally grounded in image-based datasets collected with bench-top devices. The static images naturally lose the dynamic characteristics of retina fluctuation, resulting in diminished dataset richness, and the usage of bench-top devices further restricts dataset scalability due to its limited accessibility. Considering these limitations, we introduce the first video-based retinal dataset by employing handheld devices for data acquisition. The dataset comprises 635 smartphone-based fundus videos collected from four different clinics, involving 415 patients from 50 to 75 years old. It delivers comprehensive and precise annotations of retinal structures in both spatial and temporal dimensions, aiming to advance the landscape of vasculature segmentation. Specifically, the dataset provides three levels of spatial annotations: binary vessel masks for overall retinal structure delineation, general vein-artery masks for distinguishing the vein and artery, and fine-grained vein-artery masks for further characterizing the granularities of each artery and vein. In addition, the dataset offers temporal annotations that capture the vessel pulsation characteristics, assisting in detecting ocular diseases that require fine-grained recognition of hemodynamic fluctuation. In application, our dataset exhibits a significant domain shift with respect to data captured by bench-top devices, thus posing great challenges to existing methods. In the experiments, we provide evaluation metrics and benchmark results on our dataset, reflecting both the potential and challenges it offers for vessel segmentation tasks. We hope this challenging dataset would significantly contribute to the development of eye disease diagnosis and early prevention.

Yudong Chen, Sen Wang, Jiajun Liu et al.

In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the feature projector between the student and the teacher remains under-explored. In this paper, we first discuss a plausible mechanism of the projector with empirical evidence and then propose a new feature distillation method based on a projector ensemble for further performance improvement. We observe that the student network benefits from a projector even if the feature dimensions of the student and the teacher are the same. Training a student backbone without a projector can be considered as a multi-task learning process, namely achieving discriminative feature extraction for classification and feature matching between the student and the teacher for distillation at the same time. We hypothesize and empirically verify that without a projector, the student network tends to overfit the teacher's feature distributions despite having different architecture and weights initialization. This leads to degradation on the quality of the student's deep features that are eventually used in classification. Adding a projector, on the other hand, disentangles the two learning tasks and helps the student network to focus better on the main feature extraction task while still being able to utilize teacher features as a guidance through the projector. Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features. Experimental results on different datasets with a series of teacher-student pairs illustrate the effectiveness of the proposed method.

Xuwei Xu, Changlin Li, Yudong Chen et al.

Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resource-constrained environments. Various token pruning techniques have been introduced to alleviate the high computational burden of ViTs by dynamically dropping image tokens. However, some undesirable pruning at early stages may result in permanent loss of image information in subsequent layers, consequently hindering model performance. To address this problem, we propose IdleViT, a dynamic token-idle-based method that achieves an excellent trade-off between performance and efficiency. Specifically, in each layer, IdleViT selects a subset of the image tokens to participate in computations while keeping the rest of the tokens idle and directly passing them to this layer's output. By allowing the idle tokens to be re-selected in the following layers, IdleViT mitigates the negative impact of improper pruning in the early stages. Furthermore, inspired by the normalized graph cut, we devise a token cut loss on the attention map as regularization to improve IdleViT's token selection ability. Our method is simple yet effective and can be extended to pyramid ViTs since no token is completely dropped. Extensive experimental results on various ViT architectures have shown that IdleViT can diminish the complexity of pretrained ViTs by up to 33\% with no more than 0.2\% accuracy decrease on ImageNet, after finetuning for only 30 epochs. Notably, when the keep ratio is 0.5, IdleViT outperforms the state-of-the-art EViT on DeiT-S by 0.5\% higher accuracy and even faster inference speed. The source code is available in the supplementary material.

Zhifeng Xie, Sen Wang, Ke Xu et al.

Night-Time Scene Parsing (NTSP) is essential to many vision applications, especially for autonomous driving. Most of the existing methods are proposed for day-time scene parsing. They rely on modeling pixel intensity-based spatial contextual cues under even illumination. Hence, these methods do not perform well in night-time scenes as such spatial contextual cues are buried in the over-/under-exposed regions in night-time scenes. In this paper, we first conduct an image frequency-based statistical experiment to interpret the day-time and night-time scene discrepancies. We find that image frequency distributions differ significantly between day-time and night-time scenes, and understanding such frequency distributions is critical to NTSP problem. Based on this, we propose to exploit the image frequency distributions for night-time scene parsing. First, we propose a Learnable Frequency Encoder (LFE) to model the relationship between different frequency coefficients to measure all frequency components dynamically. Second, we propose a Spatial Frequency Fusion module (SFF) that fuses both spatial and frequency information to guide the extraction of spatial context features. Extensive experiments show that our method performs favorably against the state-of-the-art methods on the NightCity, NightCity+ and BDD100K-night datasets. In addition, we demonstrate that our method can be applied to existing day-time scene parsing methods and boost their performance on night-time scenes.

Pierre Nicolay, Yvan Petillot, Mykhaylo Marfeychuk et al.

Autonomous underwater vehicles (AUVs) play a crucial role in surveying marine environments, carrying out underwater inspection tasks, and ocean exploration. However, in order to ensure that the AUV is able to carry out its mission successfully, a control system capable of adapting to changing environmental conditions is required. Furthermore, to ensure the robotic platform's safe operation, the onboard controller should be able to operate under certain constraints. In this work, we investigate the feasibility of Model Predictive Path Integral Control (MPPI) for the control of an AUV. We utilise a non-linear model of the AUV to propagate the samples of the MPPI, which allow us to compute the control action in real time. We provide a detailed evaluation of the effect of the main hyperparameters on the performance of the MPPI controller. Furthermore, we compared the performance of the proposed method with a classical PID and Cascade PID approach, demonstrating the superiority of our proposed controller. Finally, we present results where environmental constraints are added and show how MPPI can handle them by simply incorporating those constraints in the cost function.

Sen Wang, Qing Cheng, Stefano Gasperini et al.

The generation of high-fidelity view synthesis is essential for robotic navigation and interaction but remains challenging, particularly in indoor environments and real-time scenarios. Existing techniques often require significant computational resources for both training and rendering, and they frequently result in suboptimal 3D representations due to insufficient geometric structuring. To address these limitations, we introduce VoxNeRF, a novel approach that utilizes easy-to-obtain geometry priors to enhance both the quality and efficiency of neural indoor reconstruction and novel view synthesis. We propose an efficient voxel-guided sampling technique that allocates computational resources selectively to the most relevant segments of rays based on a voxel-encoded geometry prior, significantly reducing training and rendering time. Additionally, we incorporate a robust depth loss to improve reconstruction and rendering quality in sparse view settings. Our approach is validated with extensive experiments on ScanNet and ScanNet++ where VoxNeRF outperforms existing state-of-the-art methods and establishes a new benchmark for indoor immersive interpolation and extrapolation settings.

Hrishikesh Patel, Ruihong Qiu, Adam Irwin et al.

Irregular time series, where data points are recorded at uneven intervals, are prevalent in healthcare settings, such as emergency wards where vital signs and laboratory results are captured at varying times. This variability, which reflects critical fluctuations in patient health, is essential for informed clinical decision-making. Existing self-supervised learning research on irregular time series often relies on generic pretext tasks like forecasting, which may not fully utilise the signal provided by irregular time series. There is a significant need for specialised pretext tasks designed for the characteristics of irregular time series to enhance model performance and robustness, especially in scenarios with limited data availability. This paper proposes a novel pretraining framework, EMIT, an event-based masking for irregular time series. EMIT focuses on masking-based reconstruction in the latent space, selecting masking points based on the rate of change in the data. This method preserves the natural variability and timing of measurements while enhancing the model's ability to process irregular intervals without losing essential information. Extensive experiments on the MIMIC-III and PhysioNet Challenge datasets demonstrate the superior performance of our event-based masking strategy. The code has been released at https://github.com/hrishi-ds/EMIT.

Yi Zhang, Ruihong Qiu, Jiajun Liu et al.

Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on model-based RL through learning a world model from offline data and building the recommendation policy by interacting with this model. Although these methods have made progress in the recommendation performance, the effectiveness of model-based offline RL methods is often constrained by the accuracy of the estimation of the reward model and the model uncertainties, primarily due to the extreme discrepancy between offline logged data and real-world data in user interactions with online platforms. To fill this gap, a more accurate reward model and uncertainty estimation are needed for the model-based RL methods. In this paper, a novel model-based Reward Shaping in Offline Reinforcement Learning for Recommender Systems, ROLeR, is proposed for reward and uncertainty estimation in recommendation systems. Specifically, a non-parametric reward shaping method is designed to refine the reward model. In addition, a flexible and more representative uncertainty penalty is designed to fit the needs of recommendation systems. Extensive experiments conducted on four benchmark datasets showcase that ROLeR achieves state-of-the-art performance compared with existing baselines. The source code can be downloaded at https://github.com/ArronDZhang/ROLeR.

Zhi Chen, Yadan Luo, Sen Wang et al.

Zero-shot learning is a learning regime that recognizes unseen classes by generalizing the visual-semantic relationship learned from the seen classes. To obtain an effective ZSL model, one may resort to curating training samples from multiple sources, which may inevitably raise the privacy concerns about data sharing across different organizations. In this paper, we propose a novel Federated Zero-Shot Learning FedZSL framework, which learns a central model from the decentralized data residing on edge devices. To better generalize to previously unseen classes, FedZSL allows the training data on each device sampled from the non-overlapping classes, which are far from the i.i.d. that traditional federated learning commonly assumes. We identify two key challenges in our FedZSL protocol: 1) the trained models are prone to be biased to the locally observed classes, thus failing to generalize to the unseen classes and/or seen classes appeared on other devices; 2) as each category in the training data comes from a single source, the central model is highly vulnerable to model replacement (backdoor) attacks. To address these issues, we propose three local objectives for visual-semantic alignment and cross-device alignment through relation distillation, which leverages the normalized class-wise covariance to regularize the consistency of the prediction logits across devices. To defend against the backdoor attacks, a feature magnitude defending technique is proposed. As malicious samples are less correlated to the given semantic attributes, the visual features of low magnitude will be discarded to stabilize model updates. The effectiveness and robustness of FedZSL are demonstrated by extensive experiments conducted on three zero-shot benchmark datasets.

Zhi Chen, Yadan Luo, Sen Wang et al.

Generalized Zero-Shot Learning (GZSL) aims to recognize images from both the seen and unseen classes by transferring semantic knowledge from seen to unseen classes. It is a promising solution to take the advantage of generative models to hallucinate realistic unseen samples based on the knowledge learned from the seen classes. However, due to the generation shifts, the synthesized samples by most existing methods may drift from the real distribution of the unseen data. To address this issue, we propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation. Specifically, we discover and address three potential problems that trigger the generation shifts, i.e., semantic inconsistency, variance collapse, and structure disorder. First, to enhance the reflection of the semantic information in the generated samples, we explicitly embed the semantic information into the transformation in each conditional affine coupling layer. Second, to recover the intrinsic variance of the real unseen features, we introduce a boundary sample mining strategy with entropy maximization to discover more difficult visual variants of semantic prototypes and hereby adjust the decision boundary of the classifiers. Third, a relative positioning strategy is proposed to revise the attribute embeddings, guiding them to fully preserve the inter-class geometric structure and further avoid structure disorder in the semantic space. Extensive experimental results on four GZSL benchmark datasets demonstrate that GSMFlow achieves the state-of-the-art performance on GZSL.

Yi Dong, Xingyu Zhao, Sen Wang et al.

Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies. Unexplored states may lead the agent to make wrong decisions that could result in hazards, especially in applications where DRL-trained end-to-end controllers govern the behaviour of RAS. This paper proposes a novel quantitative reliability assessment framework for DRL-controlled RAS, leveraging verification evidence generated from formal reliability analysis of neural networks. A two-level verification framework is introduced to check the safety property with respect to inaccurate observations that are due to, e.g., environmental noise and state changes. Reachability verification tools are leveraged locally to generate safety evidence of trajectories. In contrast, at the global level, we quantify the overall reliability as an aggregated metric of local safety evidence, corresponding to a set of distinct tasks and their occurrence probabilities. The effectiveness of the proposed verification framework is demonstrated and validated via experiments on real RAS.

Zixin Wang, Yadan Luo, Zhi Chen et al.

The prevalence of domain adaptive semantic segmentation has prompted concerns regarding source domain data leakage, where private information from the source domain could inadvertently be exposed in the target domain. To circumvent the requirement for source data, source-free domain adaptation has emerged as a viable solution that leverages self-training methods to pseudo-label high-confidence regions and adapt the model to the target data. However, the confidence scores obtained are often highly biased due to over-confidence and class-imbalance issues, which render both model selection and optimization problematic. In this paper, we propose a novel calibration-guided source-free domain adaptive semantic segmentation (Cal-SFDA) framework. The core idea is to estimate the expected calibration error (ECE) from the segmentation predictions, serving as a strong indicator of the model's generalization capability to the unlabeled target domain. The estimated ECE scores, in turn, assist the model training and fair selection in both source training and target adaptation stages. During model pre-training on the source domain, we ensure the differentiability of the ECE objective by leveraging the LogSumExp trick and using ECE scores to select the best source checkpoints for adaptation. To enable ECE estimation on the target domain without requiring labels, we train a value net for ECE estimation and apply statistic warm-up on its BatchNorm layers for stability. The estimated ECE scores assist in determining the reliability of prediction and enable class-balanced pseudo-labeling by positively guiding the adaptation progress and inhibiting potential error accumulation. Extensive experiments on two widely-used synthetic-to-real transfer tasks show that the proposed approach surpasses previous state-of-the-art by up to 5.25% of mIoU with fair model selection criteria.

Wei Zhang, Tiecheng Sun, Sen Wang et al.

In this letter, we present a neural field-based real-time monocular mapping framework for accurate and dense Simultaneous Localization and Mapping (SLAM). Recent neural mapping frameworks show promising results, but rely on RGB-D or pose inputs, or cannot run in real-time. To address these limitations, our approach integrates dense-SLAM with neural implicit fields. Specifically, our dense SLAM approach runs parallel tracking and global optimization, while a neural field-based map is constructed incrementally based on the latest SLAM estimates. For the efficient construction of neural fields, we employ multi-resolution grid encoding and signed distance function (SDF) representation. This allows us to keep the map always up-to-date and adapt instantly to global updates via loop closing. For global consistency, we propose an efficient Sim(3)-based pose graph bundle adjustment (PGBA) approach to run online loop closing and mitigate the pose and scale drift. To enhance depth accuracy further, we incorporate learned monocular depth priors. We propose a novel joint depth and scale adjustment (JDSA) module to solve the scale ambiguity inherent in depth priors. Extensive evaluations across synthetic and real-world datasets validate that our approach outperforms existing methods in accuracy and map completeness while preserving real-time performance.

Xiuding Cai, Xueyao Wang, Sen Wang et al.

Intraoperative monitoring and prediction of vital signs are critical for ensuring patient safety and improving surgical outcomes. Despite recent advances in deep learning models for medical time-series forecasting, several challenges persist, including the lack of standardized benchmarks, incomplete data, and limited cross-center validation. To address these challenges, we introduce VitalBench, a novel benchmark specifically designed for intraoperative vital sign prediction. VitalBench includes data from over 4,000 surgeries across two independent medical centers, offering three evaluation tracks: complete data, incomplete data, and cross-center generalization. This framework reflects the real-world complexities of clinical practice, minimizing reliance on extensive preprocessing and incorporating masked loss techniques for robust and unbiased model evaluation. By providing a standardized and unified platform for model development and comparison, VitalBench enables researchers to focus on architectural innovation while ensuring consistency in data handling. This work lays the foundation for advancing predictive models for intraoperative vital sign forecasting, ensuring that these models are not only accurate but also robust and adaptable across diverse clinical environments. Our code and data are available at https://github.com/XiudingCai/VitalBench.

Zixin Wang, Yadan Luo, Peng-Fei Zhang et al.

A typical multi-source domain adaptation (MSDA) approach aims to transfer knowledge learned from a set of labeled source domains, to an unlabeled target domain. Nevertheless, prior works strictly assume that each source domain shares the identical group of classes with the target domain, which could hardly be guaranteed as the target label space is not observable. In this paper, we consider a more versatile setting of MSDA, namely Generalized Multi-source Domain Adaptation, wherein the source domains are partially overlapped, and the target domain is allowed to contain novel categories that are not presented in any source domains. This new setting is more elusive than any existing domain adaptation protocols due to the coexistence of the domain and category shifts across the source and target domains. To address this issue, we propose a variational domain disentanglement (VDD) framework, which decomposes the domain representations and semantic features for each instance by encouraging dimension-wise independence. To identify the target samples of unknown classes, we leverage online pseudo labeling, which assigns the pseudo-labels to unlabeled target data based on the confidence scores. Quantitative and qualitative experiments conducted on two benchmark datasets demonstrate the validity of the proposed framework.

Bingqing Zhang, Sen Wang, Yifan Liu et al.

Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased computational complexity. In this work, we propose an image-level Object Detection Difficulty (ODD) metric to quantify the difficulty of detecting objects in a given image. The derived ODD scores can be used in the VOD process to mitigate over-aggregation. Specifically, we train an ODD predictor as an auxiliary head of a still-image object detector to compute the ODD score for each image based on the discrepancies between detection results and ground-truth bounding boxes. The ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD Scheduler to eliminate the aggregation of frames that are easy to detect, thus accelerating the VOD process. Comprehensive experiments demonstrate that, when utilized for selecting global reference frames, ODD-VOD consistently enhances the accuracy of Global-frame-based VOD models. When employed for acceleration, ODD-VOD consistently improves the frames per second (FPS) by an average of 73.3% across 8 different VOD models without sacrificing accuracy. When combined, ODD-VOD attains state-of-the-art performance when competing with many VOD methods in both accuracy and speed. Our work represents a significant advancement towards making VOD more practical for real-world applications.

Sen Wang, Bangwei Liu, Zhenkun Gao et al.

An ideal embodied agent should possess lifelong learning capabilities to handle long-horizon and complex tasks, enabling continuous operation in general environments. This not only requires the agent to accurately accomplish given tasks but also to leverage long-term episodic memory to optimize decision-making. However, existing mainstream one-shot embodied tasks primarily focus on task completion results, neglecting the crucial process of exploration and memory utilization. To address this, we propose Long-term Memory Embodied Exploration (LMEE), which aims to unify the agent's exploratory cognition and decision-making behaviors to promote lifelong learning. We further construct a corresponding dataset and benchmark, LMEE-Bench, incorporating multi-goal navigation and memory-based question answering to comprehensively evaluate both the process and outcome of embodied exploration. To enhance the agent's memory recall and proactive exploration capabilities, we propose MemoryExplorer, a novel method that fine-tunes a multimodal large language model through reinforcement learning to encourage active memory querying. By incorporating a multi-task reward function that includes action prediction, frontier selection, and question answering, our model achieves proactive exploration. Extensive experiments against state-of-the-art embodied exploration models demonstrate that our approach achieves significant advantages in long-horizon embodied tasks. Our dataset and code will be released at https://wangsen99.github.io/papers/lmee/

Bingqing Zhang, Zhuo Cao, Heming Du et al.

Text-Video Retrieval (TVR) methods typically match query-candidate pairs by aligning text and video features in coarse-grained, fine-grained, or combined (coarse-to-fine) manners. However, these frameworks predominantly employ a one(query)-to-one(candidate) alignment paradigm, which struggles to discern nuanced differences among candidates, leading to frequent mismatches. Inspired by Comparative Judgement in human cognitive science, where decisions are made by directly comparing items rather than evaluating them independently, we propose TokenBinder. This innovative two-stage TVR framework introduces a novel one-to-many coarse-to-fine alignment paradigm, imitating the human cognitive process of identifying specific items within a large collection. Our method employs a Focused-view Fusion Network with a sophisticated cross-attention mechanism, dynamically aligning and comparing features across multiple videos to capture finer nuances and contextual variations. Extensive experiments on six benchmark datasets confirm that TokenBinder substantially outperforms existing state-of-the-art methods. These results demonstrate its robustness and the effectiveness of its fine-grained alignment in bridging intra- and inter-modality information gaps in TVR tasks.

Sen Wang, Huaiyi Dong, Jingyi Tian et al.

Prevailing 2D-centric visuomotor policies exhibit a pronounced deficiency in novel view generalization, as their reliance on static observations hinders consistent action mapping across unseen views. In response, we introduce GenSplat, a feed-forward 3D Gaussian Splatting framework that facilitates view-generalized policy learning through novel view rendering. GenSplat employs a permutation-equivariant architecture to reconstruct high-fidelity 3D scenes from sparse, uncalibrated inputs in a single forward pass. To ensure structural integrity, we design a 3D-prior distillation strategy that regularizes the 3DGS optimization, preventing the geometric collapse typical of purely photometric supervision. By rendering diverse synthetic views from these stable 3D representations, we systematically augment the observational manifold during training. This augmentation forces the policy to ground its decisions in underlying 3D structures, thereby ensuring robust execution under severe spatial perturbations where baselines severely degrade.

Mateusz Ochal, Massimiliano Patacchiola, Malik Boudiaf et al.

In Few-Shot Learning (FSL), models are trained to recognise unseen objects from a query set, given a few labelled examples from a support set. In standard FSL, models are evaluated on query instances sampled from the same class distribution of the support set. In this work, we explore the more nuanced and practical challenge of Open-Set Few-Shot Recognition (OSFSL). Unlike standard FSL, OSFSL incorporates unknown classes into the query set, thereby requiring the model not only to classify known classes but also to identify outliers. Building on the groundwork laid by previous studies, we define a novel transductive inference technique that leverages the InfoMax principle to exploit the unlabelled query set. We called our approach the Enhanced Outlier Logit (EOL) method. EOL refines class prototype representations through model calibration, effectively balancing the inlier-outlier ratio. This calibration enhances pseudo-label accuracy for the query set and improves the optimisation objective within the transductive inference process. We provide a comprehensive empirical evaluation demonstrating that EOL consistently surpasses traditional methods, recording performance improvements ranging from approximately $+1.3%$ to $+6.3%$ across a variety of classification and outlier detection metrics and benchmarks, even in the presence of inlier-outlier imbalance.

Yudong Chen, Sen Wang, Jiajun Liu et al.

Conventionally, during the knowledge distillation process (e.g. feature distillation), an additional projector is often required to perform feature transformation due to the dimension mismatch between the teacher and the student networks. Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance. In addition, projectors even improve logit distillation if we add them to the architecture too. Inspired by these surprising findings and the general lack of understanding of the projectors in the knowledge distillation process from existing literature, this paper investigates the implicit role that projectors play but so far have been overlooked. Our empirical study shows that the student with a projector (1) obtains a better trade-off between the training accuracy and the testing accuracy compared to the student without a projector when it has the same feature dimensions as the teacher, (2) better preserves its similarity to the teacher beyond shallow and numeric resemblance, from the view of Centered Kernel Alignment (CKA), and (3) avoids being over-confident as the teacher does at the testing phase. Motivated by the positive effects of projectors, we propose a projector ensemble-based feature distillation method to further improve distillation performance. Despite the simplicity of the proposed strategy, empirical results from the evaluation of classification tasks on benchmark datasets demonstrate the superior classification performance of our method on a broad range of teacher-student pairs and verify from the aspects of CKA and model calibration that the student's features are of improved quality with the projector ensemble design.

Zhuo Cao, Bingqing Zhang, Heming Du et al.

Text-guided Video Temporal Grounding (VTG) aims to localize relevant segments in untrimmed videos based on textual descriptions, encompassing two subtasks: Moment Retrieval (MR) and Highlight Detection (HD). Although previous typical methods have achieved commendable results, it is still challenging to retrieve short video moments. This is primarily due to the reliance on sparse and limited decoder queries, which significantly constrain the accuracy of predictions. Furthermore, suboptimal outcomes often arise because previous methods rank predictions based on isolated predictions, neglecting the broader video context. To tackle these issues, we introduce FlashVTG, a framework featuring a Temporal Feature Layering (TFL) module and an Adaptive Score Refinement (ASR) module. The TFL module replaces the traditional decoder structure to capture nuanced video content variations across multiple temporal scales, while the ASR module improves prediction ranking by integrating context from adjacent moments and multi-temporal-scale features. Extensive experiments demonstrate that FlashVTG achieves state-of-the-art performance on four widely adopted datasets in both MR and HD. Specifically, on the QVHighlights dataset, it boosts mAP by 5.8% for MR and 3.3% for HD. For short-moment retrieval, FlashVTG increases mAP to 125% of previous SOTA performance. All these improvements are made without adding training burdens, underscoring its effectiveness. Our code is available at https://github.com/Zhuo-Cao/FlashVTG.

Haodong Hong, Sen Wang, Zi Huang et al.

Real-world navigation often involves dealing with unexpected obstructions such as closed doors, moved objects, and unpredictable entities. However, mainstream Vision-and-Language Navigation (VLN) tasks typically assume instructions perfectly align with the fixed and predefined navigation graphs without any obstructions. This assumption overlooks potential discrepancies in actual navigation graphs and given instructions, which can cause major failures for both indoor and outdoor agents. To address this issue, we integrate diverse obstructions into the R2R dataset by modifying both the navigation graphs and visual observations, introducing an innovative dataset and task, R2R with UNexpected Obstructions (R2R-UNO). R2R-UNO contains various types and numbers of path obstructions to generate instruction-reality mismatches for VLN research. Experiments on R2R-UNO reveal that state-of-the-art VLN methods inevitably encounter significant challenges when facing such mismatches, indicating that they rigidly follow instructions rather than navigate adaptively. Therefore, we propose a novel method called ObVLN (Obstructed VLN), which includes a curriculum training strategy and virtual graph construction to help agents effectively adapt to obstructed environments. Empirical results show that ObVLN not only maintains robust performance in unobstructed scenarios but also achieves a substantial performance advantage with unexpected obstructions.

Zhi Chen, Yadan Luo, Zi Huang et al.

In this paper, we propose a Distributed Zero-Shot Learning (DistZSL) framework that can fully exploit decentralized data to learn an effective model for unseen classes. Considering the data heterogeneity issues across distributed nodes, we introduce two key components to ensure the effective learning of DistZSL: a cross-node attribute regularizer and a global attribute-to-visual consensus. Our proposed cross-node attribute regularizer enforces the distances between attribute features to be similar across different nodes. In this manner, the overall attribute feature space would be stable during learning, and thus facilitate the establishment of visual-to-attribute(V2A) relationships. Then, we introduce the global attribute-tovisual consensus to mitigate biased V2A mappings learned from individual nodes. Specifically, we enforce the bilateral mapping between the attribute and visual feature distributions to be consistent across different nodes. Thus, the learned consistent V2A mapping can significantly enhance zero-shot learning across different nodes. Extensive experiments demonstrate that DistZSL achieves superior performance to the state-of-the-art in learning from distributed data.

Shida Xu, Kaicheng Zhang, Sen Wang

Underwater environments pose significant challenges for visual Simultaneous Localization and Mapping (SLAM) systems due to limited visibility, inadequate illumination, and sporadic loss of structural features in images. Addressing these challenges, this paper introduces a novel, tightly-coupled Acoustic-Visual-Inertial SLAM approach, termed AQUA-SLAM, to fuse a Doppler Velocity Log (DVL), a stereo camera, and an Inertial Measurement Unit (IMU) within a graph optimization framework. Moreover, we propose an efficient sensor calibration technique, encompassing multi-sensor extrinsic calibration (among the DVL, camera and IMU) and DVL transducer misalignment calibration, with a fast linear approximation procedure for real-time online execution. The proposed methods are extensively evaluated in a tank environment with ground truth, and validated for offshore applications in the North Sea. The results demonstrate that our method surpasses current state-of-the-art underwater and visual-inertial SLAM systems in terms of localization accuracy and robustness. The proposed system will be made open-source for the community.

Shida Xu, Jingqi Jiang, Jonatan Scharff Willners et al.

Underwater sonar imaging plays a crucial role in various applications, including autonomous navigation in murky water, marine archaeology, and environmental monitoring. However, the unique characteristics of sonar images, such as complex noise patterns and the lack of elevation information, pose significant challenges for 3D reconstruction and novel view synthesis. In this paper, we present NAS-GS, a novel Noise-Aware Sonar Gaussian Splatting framework specifically designed to address these challenges. Our approach introduces a Two-Ways Splatting technique that accurately models the dual directions for intensity accumulation and transmittance calculation inherent in sonar imaging, significantly improving rendering speed without sacrificing quality. Moreover, we propose a Gaussian Mixture Model (GMM) based noise model that captures complex sonar noise patterns, including side-lobes, speckle, and multi-path noise. This model enhances the realism of synthesized images while preventing 3D Gaussian overfitting to noise, thereby improving reconstruction accuracy. We demonstrate state-of-the-art performance on both simulated and real-world large-scale offshore sonar scenarios, achieving superior results in novel view synthesis and 3D reconstruction.

Xuwei Xu, Sen Wang, Yudong Chen et al.

Vision Transformers (ViTs) have demonstrated remarkable performance in various computer vision tasks. However, the high computational complexity hinders ViTs' applicability on devices with limited memory and computing resources. Although certain investigations have delved into the fusion of convolutional layers with self-attention mechanisms to enhance the efficiency of ViTs, there remains a knowledge gap in constructing tiny yet effective ViTs solely based on the self-attention mechanism. Furthermore, the straightforward strategy of reducing the feature channels in a large but outperforming ViT often results in significant performance degradation despite improved efficiency. To address these challenges, we propose a novel channel shuffle module to improve tiny-size ViTs, showing the potential of pure self-attention models in environments with constrained computing resources. Inspired by the channel shuffle design in ShuffleNetV2 \cite{ma2018shufflenet}, our module expands the feature channels of a tiny ViT and partitions the channels into two groups: the \textit{Attended} and \textit{Idle} groups. Self-attention computations are exclusively employed on the designated \textit{Attended} group, followed by a channel shuffle operation that facilitates information exchange between the two groups. By incorporating our module into a tiny ViT, we can achieve superior performance while maintaining a comparable computational complexity to the vanilla model. Specifically, our proposed channel shuffle module consistently improves the top-1 accuracy on the ImageNet-1K dataset for various tiny ViT models by up to 2.8\%, with the changes in model complexity being less than 0.03 GMACs.

Xuwei Xu, Yang Li, Yudong Chen et al.

We reveal that feedforward network (FFN) layers, rather than attention layers, are the primary contributors to Vision Transformer (ViT) inference latency, with their impact signifying as model size increases. This finding highlights a critical opportunity for optimizing the efficiency of large-scale ViTs by focusing on FFN layers. In this work, we propose a novel channel idle mechanism that facilitates post-training structural reparameterization for efficient FFN layers during testing. Specifically, a set of feature channels remains idle and bypasses the nonlinear activation function in each FFN layer, thereby forming a linear pathway that enables structural reparameterization during inference. This mechanism results in a family of ReParameterizable Vision Transformers (RePaViTs), which achieve remarkable latency reductions with acceptable sacrifices (sometimes gains) in accuracy across various ViTs. The benefits of our method scale consistently with model sizes, demonstrating greater speed improvements and progressively narrowing accuracy gaps or even higher accuracies on larger models. In particular, RePa-ViT-Large and RePa-ViT-Huge enjoy 66.8% and 68.7% speed-ups with +1.7% and +1.1% higher top-1 accuracies under the same training strategy, respectively. RePaViT is the first to employ structural reparameterization on FFN layers to expedite ViTs to our best knowledge, and we believe that it represents an auspicious direction for efficient ViTs. Source code is available at https://github.com/Ackesnal/RePaViT.

Bingqing Zhang, Yi Zhang, Zhuo Cao et al.

Composed video retrieval (CoVR) searches for target videos using a reference video and a modification text, but existing methods are restricted to a single interaction round and cannot support the progressive nature of real-world visual search. To bridge this gap, we first formalize interactive composed video retrieval, a multi-turn extension of CoVR, where users progressively refine their search intent through natural-language feedback across turns. Adapting existing interactive retrieval methods to this setting reveals two structural weaknesses: reliance on a single retrieval channel and an open-loop retrieval design that consumes user feedback but does not diagnose whether its own retrieval trajectory is drifting or stagnating. To address these limitations, we propose ReCoVR (Reflexive Composed Video Retrieval), a dual-pathway architecture built on reflexive perception, where the system treats its retrieval history as diagnostic evidence alongside user feedback. Specifically, an Intent Pathway routes heterogeneous feedback to complementary retrieval channels, while a Reflection Pathway performs trajectory-level reflection to monitor result evolution and correct retrieval errors across turns. Experiments on multiple benchmarks show that ReCoVR consistently outperforms interactive baselines, notably achieving 74.30% R@1 after just one interactive round on the WebVid-CoVR-Test dataset.

Yining Ding, João F. C. Mota, Andrew M. Wallace et al.

We propose a method which, given a sequence of stereo foggy images, estimates the parameters of a fog model and updates them dynamically. In contrast with previous approaches, which estimate the parameters sequentially and thus are prone to error propagation, our algorithm estimates all the parameters simultaneously by solving a novel optimisation problem. By assuming that fog is only locally homogeneous, our method effectively handles real-world fog, which is often globally inhomogeneous. The proposed algorithm can be easily used as an add-on module in existing visual Simultaneous Localisation and Mapping (SLAM) or odometry systems in the presence of fog. In order to assess our method, we also created a new dataset, the Stereo Driving In Real Fog (SDIRF), consisting of high-quality, consecutive stereo frames of real, foggy road scenes under a variety of visibility conditions, totalling over 40 minutes and 34k frames. As a first-of-its-kind, SDIRF contains the camera's photometric parameters calibrated in a lab environment, which is a prerequisite for correctly applying the atmospheric scattering model to foggy images. The dataset also includes the counterpart clear data of the same routes recorded in overcast weather, which is useful for companion work in image defogging and depth reconstruction. We conducted extensive experiments using both synthetic foggy data and real foggy sequences from SDIRF to demonstrate the superiority of the proposed algorithm over prior methods. Our method not only produces the most accurate estimates on synthetic data, but also adapts better to real fog. We make our code and SDIRF publicly available\footnote{https://github.com/SenseRoboticsLab/estimating-fog-parameters} to the community with the aim of advancing the research on visual perception in fog.

Tianyi Chen, Michael Solodko, Sen Wang et al.

Computer Using Agents (CUAs) are increasingly equipped with external tools, enabling them to perform complex and realistic tasks. For CUAs to operate effectively, application selection, which refers to deciding which application to use before invoking fine-grained tools such as APIs, is a fundamental capability. It determines whether the agent initializes the correct environment, avoids orchestration confusion, and efficiently focuses on relevant context. However, existing benchmarks primarily assess fine-grained API selection, offering limited insight into whether models can reason across and choose between different applications. To fill this gap, we introduce AppSelectBench, a comprehensive benchmark for evaluating application selection in CUAs. AppSelectBench contains a novel user task generation pipeline that produces realistic, diverse, and semantically grounded user intents at scale, together with unified evaluation protocols covering random, heuristic, zero-shot, few-shot, and retrieval-augmented-settings. AppSelectBench covers one hundred widely used desktop applications and includes more than one hundred thousand realistic, diverse, and semantically grounded user tasks. Extensive experiments across both closed-source and open-source large language models reveal systematic strengths and weaknesses in inter-application reasoning, showing that even the most capable models still struggle to make consistent application choices. Together, these results establish AppSelectBench as a foundation for studying and advancing application level reasoning, an essential yet underexplored capability of intelligent CUAs. The source is available at https://microsoft.github.io/appselectbench/.

Sen Wang, Peizhi Zhao, Qinglong Ma et al.

Physics-Informed Neural Networks (PINNs) have become a promising research direction in the field of solving Partial Differential Equations (PDEs). Dealing with singular perturbation problems continues to be a difficult challenge in the field of PINN. The solution of singular perturbation problems often exhibits sharp boundary layers and steep gradients, and traditional PINN cannot achieve approximation of boundary layers. In this manuscript, we propose the General-Kindred Physics-Informed Neural Network (GKPINN) for solving Singular Perturbation Differential Equations (SPDEs). This approach utilizes asymptotic analysis to acquire prior knowledge of the boundary layer from the equation and establishes a novel network to assist PINN in approximating the boundary layer. It is compared with traditional PINN by solving examples of one-dimensional, two-dimensional, and time-varying SPDE equations. The research findings underscore the exceptional performance of our novel approach, GKPINN, which delivers a remarkable enhancement in reducing the $L_2$ error by two to four orders of magnitude compared to the established PINN methodology. This significant improvement is accompanied by a substantial acceleration in convergence rates, without compromising the high precision that is critical for our applications. Furthermore, GKPINN still performs well in extreme cases with perturbation parameters of ${1\times10}^{-38}$, demonstrating its excellent generalization ability.

Zhuo Cao, Heming Du, Bingqing Zhang et al.

Existing Moment retrieval (MR) methods focus on Single-Moment Retrieval (SMR). However, one query can correspond to multiple relevant moments in real-world applications. This makes the existing datasets and methods insufficient for video temporal grounding. By revisiting the gap between current MR tasks and real-world applications, we introduce a high-quality datasets called QVHighlights Multi-Moment Dataset (QV-M$^2$), along with new evaluation metrics tailored for multi-moment retrieval (MMR). QV-M$^2$ consists of 2,212 annotations covering 6,384 video segments. Building on existing efforts in MMR, we propose a framework called FlashMMR. Specifically, we propose a Multi-moment Post-verification module to refine the moment boundaries. We introduce constrained temporal adjustment and subsequently leverage a verification module to re-evaluate the candidate segments. Through this sophisticated filtering pipeline, low-confidence proposals are pruned, and robust multi-moment alignment is achieved. We retrain and evaluate 6 existing MR methods on QV-M$^2$ and QVHighlights under both SMR and MMR settings. Results show that QV-M$^2$ serves as an effective benchmark for training and evaluating MMR models, while FlashMMR provides a strong baseline. Specifically, on QV-M$^2$, it achieves improvements over prior SOTA method by 3.00% on G-mAP, 2.70% on mAP@3+tgt, and 2.56% on mR@3. The proposed benchmark and method establish a foundation for advancing research in more realistic and challenging video temporal grounding scenarios. Code is released at https://github.com/Zhuo-Cao/QV-M2.

Xueping Peng, Guodong Long, Tao Shen et al.

Sequential diagnosis prediction on the Electronic Health Record (EHR) has been proven crucial for predictive analytics in the medical domain. EHR data, sequential records of a patient's interactions with healthcare systems, has numerous inherent characteristics of temporality, irregularity and data insufficiency. Some recent works train healthcare predictive models by making use of sequential information in EHR data, but they are vulnerable to irregular, temporal EHR data with the states of admission/discharge from hospital, and insufficient data. To mitigate this, we propose an end-to-end robust transformer-based model called SETOR, which exploits neural ordinary differential equation to handle both irregular intervals between a patient's visits with admitted timestamps and length of stay in each visit, to alleviate the limitation of insufficient data by integrating medical ontology, and to capture the dependencies between the patient's visits by employing multi-layer transformer blocks. Experiments conducted on two real-world healthcare datasets show that, our sequential diagnoses prediction model SETOR not only achieves better predictive results than previous state-of-the-art approaches, irrespective of sufficient or insufficient training data, but also derives more interpretable embeddings of medical codes. The experimental codes are available at the GitHub repository (https://github.com/Xueping/SETOR).

Zhi Chen, Yadan Luo, Sen Wang et al.

Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. It is natural to derive generative models and hallucinate training samples for unseen classes based on the knowledge learned from the seen samples. However, most of these models suffer from the `generation shifts', where the synthesized samples may drift from the real distribution of unseen data. In this paper, we conduct an in-depth analysis on this issue and propose a novel Generation Shifts Mitigating Flow (GSMFlow) framework, which is comprised of multiple conditional affine coupling layers for learning unseen data synthesis efficiently and effectively. In particular, we identify three potential problems that trigger the generation shifts, i.e., semantic inconsistency, variance decay, and structural permutation and address them respectively. First, to reinforce the correlations between the generated samples and the respective attributes, we explicitly embed the semantic information into the transformations in each of the coupling layers. Second, to recover the intrinsic variance of the synthesized unseen features, we introduce a visual perturbation strategy to diversify the intra-class variance of generated data and hereby help adjust the decision boundary of the classifier. Third, to avoid structural permutation in the semantic space, we propose a relative positioning strategy to manipulate the attribute embeddings, guiding which to fully preserve the inter-class geometric structure. Experimental results demonstrate that GSMFlow achieves state-of-the-art recognition performance in both conventional and generalized zero-shot settings. Our code is available at: https://github.com/uqzhichen/GSMFlow

Mateusz Ochal, Massimiliano Patacchiola, Amos Storkey et al.

Meta-Learning (ML) has proven to be a useful tool for training Few-Shot Learning (FSL) algorithms by exposure to batches of tasks sampled from a meta-dataset. However, the standard training procedure overlooks the dynamic nature of the real-world where object classes are likely to occur at different frequencies. While it is generally understood that imbalanced tasks harm the performance of supervised methods, there is no significant research examining the impact of imbalanced meta-datasets on the FSL evaluation task. This study exposes the magnitude and extent of this problem. Our results show that ML methods are more robust against meta-dataset imbalance than imbalance at the task-level with a similar imbalance ratio ($ρ<20$), with the effect holding even in long-tail datasets under a larger imbalance ($ρ=65$). Overall, these results highlight an implicit strength of ML algorithms, capable of learning generalizable features under dataset imbalance and domain-shift. The code to reproduce the experiments is released under an open-source license.

Zhi Chen, Yadan Luo, Ruihong Qiu et al.

Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training. To bridge the gap between the seen and unseen classes, most GZSL methods attempt to associate the visual features of seen classes with attributes or to generate unseen samples directly. Nevertheless, the visual features used in the prior approaches do not necessarily encode semantically related information that the shared attributes refer to, which degrades the model generalization to unseen classes. To address this issue, in this paper, we propose a novel semantics disentangling framework for the generalized zero-shot learning task (SDGZSL), where the visual features of unseen classes are firstly estimated by a conditional VAE and then factorized into semantic-consistent and semantic-unrelated latent vectors. In particular, a total correlation penalty is applied to guarantee the independence between the two factorized representations, and the semantic consistency of which is measured by the derived relation network. Extensive experiments conducted on four GZSL benchmark datasets have evidenced that the semantic-consistent features disentangled by the proposed SDGZSL are more generalizable in tasks of canonical and generalized zero-shot learning. Our source code is available at https://github.com/uqzhichen/SDGZSL.

Yujie Zhong, Linhai Xie, Sen Wang et al.

In this paper, we teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations. Firstly, we define a self-supervised learning framework that captures the cross-modal information. A novel adversarial learning module is then introduced to explicitly handle the noises in the natural videos, where the subtitle sentences are not guaranteed to be strongly corresponded to the video snippets. For training and evaluation, we contribute a new dataset `ApartmenTour' that contains a large number of online videos and subtitles. We carry out experiments on the bidirectional retrieval tasks between sentences and videos, and the results demonstrate that our proposed model achieves the state-of-the-art performance on both retrieval tasks and exceeds several strong baselines. The dataset can be downloaded at https://github.com/zyj-13/WAL.

Xueping Peng, Guodong Long, Tao Shen et al.

Understanding patients' journeys in healthcare system is a fundamental prepositive task for a broad range of AI-based healthcare applications. This task aims to learn an informative representation that can comprehensively encode hidden dependencies among medical events and its inner entities, and then the use of encoding outputs can greatly benefit the downstream application-driven tasks. A patient journey is a sequence of electronic health records (EHRs) over time that is organized at multiple levels: patient, visits and medical codes. The key challenge of patient journey understanding is to design an effective encoding mechanism which can properly tackle the aforementioned multi-level structured patient journey data with temporal sequential visits and a set of medical codes. This paper proposes a novel self-attention mechanism that can simultaneously capture the contextual and temporal relationships hidden in patient journeys. A multi-level self-attention network (MusaNet) is specifically designed to learn the representations of patient journeys that is used to be a long sequence of activities. The MusaNet is trained in end-to-end manner using the training data derived from EHRs. We evaluated the efficacy of our method on two medical application tasks with real-world benchmark datasets. The results have demonstrated the proposed MusaNet produces higher-quality representations than state-of-the-art baseline methods. The source code is available in https://github.com/xueping/MusaNet.