Jian Zhou

Cunhang Fan, Enrui Liu, Jing Zhou et al.

Although artificial neural network (ANN) based speech enhancement (SE) methods demonstrate excellent performance, the high computational complexity and high energy consumption hinder their deployment in practical front-end processing tasks.} Currently, the spiking neural networks (SNNs) have shown potential in reducing power consumption. However, the discrete binary activation and complex spatio-temporal dynamics of SNNs often result in information loss. The current challenge therefore focuses on how to maintain performance and reduce computational complexity. To address this issue, this work propose a Dual-Branch Hybrid Neural (DBHN) Network. 1) In terms of network architecture: A dual-branch network integrating ANN and SNN was designed, where the SNN branch reduces power consumption while the ANN branch addresses information loss; The BandSplit and Time-Frequency (TF) -Mamba modules were developed to simultaneously compress energy consumption and enhance model performance; Spiking Feature Extraction Group (SFEG) and Information Transformation Block (ITB) components were implemented with residual connections to mitigate information loss while further refining feature representations. 2) To facilitate inter-branch information fusion: An Interaction module was designed to promote information exchange at various stages of the dual-branch network; A TF-Cross Attention-Fusion module was designed to perform time-frequency domain fusion of dual-branch information while data-adaptively guiding the SNN branch to retain more critical information. Results show that the proposed model maintains superior performance across three public datasets while achieving an average 7.5 fold reduction in computational complexity compared to baseline models.

Jieneng Chen, Yingda Xia, Jiawen Yao et al.

Human readers or radiologists routinely perform full-body multi-organ multi-disease detection and diagnosis in clinical practice, while most medical AI systems are built to focus on single organs with a narrow list of a few diseases. This might severely limit AI's clinical adoption. A certain number of AI models need to be assembled non-trivially to match the diagnostic process of a human reading a CT scan. In this paper, we construct a Unified Tumor Transformer (CancerUniT) model to jointly detect tumor existence & location and diagnose tumor characteristics for eight major cancers in CT scans. CancerUniT is a query-based Mask Transformer model with the output of multi-tumor prediction. We decouple the object queries into organ queries, tumor detection queries and tumor diagnosis queries, and further establish hierarchical relationships among the three groups. This clinically-inspired architecture effectively assists inter- and intra-organ representation learning of tumors and facilitates the resolution of these complex, anatomically related multi-organ cancer image reading tasks. CancerUniT is trained end-to-end using a curated large-scale CT images of 10,042 patients including eight major types of cancers and occurring non-cancer tumors (all are pathology-confirmed with 3D tumor masks annotated by radiologists). On the test set of 631 patients, CancerUniT has demonstrated strong performance under a set of clinically relevant evaluation metrics, substantially outperforming both multi-disease methods and an assembly of eight single-organ expert models in tumor detection, segmentation, and diagnosis. This moves one step closer towards a universal high performance cancer screening tool.

Ailin Huang, Chengyuan Yao, Chunrui Han et al.

We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal intelligence. STEP3-VL-10B is realized through two strategic shifts: first, a unified, fully unfrozen pre-training strategy on 1.2T multimodal tokens that integrates a language-aligned Perception Encoder with a Qwen3-8B decoder to establish intrinsic vision-language synergy; and second, a scaled post-training pipeline featuring over 1k iterations of reinforcement learning. Crucially, we implement Parallel Coordinated Reasoning (PaCoRe) to scale test-time compute, allocating resources to scalable perceptual reasoning that explores and synthesizes diverse visual hypotheses. Consequently, despite its compact 10B footprint, STEP3-VL-10B rivals or surpasses models 10$\times$-20$\times$ larger (e.g., GLM-4.6V-106B, Qwen3-VL-235B) and top-tier proprietary flagships like Gemini 2.5 Pro and Seed-1.5-VL. Delivering best-in-class performance, it records 92.2% on MMBench and 80.11% on MMMU, while excelling in complex reasoning with 94.43% on AIME2025 and 75.95% on MathVision. We release the full model suite to provide the community with a powerful, efficient, and reproducible baseline.

Jingtao Li, Jian Zhou, Yan Xiong et al.

Sampling is an essential part of raw point cloud data processing such as in the popular PointNet++ scheme. Farthest Point Sampling (FPS), which iteratively samples the farthest point and performs distance updating, is one of the most popular sampling schemes. Unfortunately it suffers from low efficiency and can become the bottleneck of point cloud applications. We propose adjustable FPS (AFPS), parameterized by M, to aggressively reduce the complexity of FPS without compromising on the sampling performance. Specifically, it divides the original point cloud into M small point clouds and samples M points simultaneously. It exploits the dimensional locality of an approximately sorted point cloud data to minimize its performance degradation. AFPS method can achieve 22 to 30x speedup over original FPS. Furthermore, we propose the nearest-point-distance-updating (NPDU) method to limit the number of distance updates to a constant number. The combined NPDU on AFPS method can achieve a 34-280x speedup on a point cloud with 2K-32K points with algorithmic performance that is comparable to the original FPS. For instance, for the ShapeNet part segmentation task, it achieves 0.8490 instance average mIoU (mean Intersection of Union), which is only 0.0035 drop compared to the original FPS.

Hexin Dong, Jiawen Yao, Yuxing Tang et al.

Pancreatic ductal adenocarcinoma (PDAC) is a highly lethal cancer in which the tumor-vascular involvement greatly affects the resectability and, thus, overall survival of patients. However, current prognostic prediction methods fail to explicitly and accurately investigate relationships between the tumor and nearby important vessels. This paper proposes a novel learnable neural distance that describes the precise relationship between the tumor and vessels in CT images of different patients, adopting it as a major feature for prognosis prediction. Besides, different from existing models that used CNNs or LSTMs to exploit tumor enhancement patterns on dynamic contrast-enhanced CT imaging, we improved the extraction of dynamic tumor-related texture features in multi-phase contrast-enhanced CT by fusing local and global features using CNN and transformer modules, further enhancing the features extracted across multi-phase CT images. We extensively evaluated and compared the proposed method with existing methods in the multi-center (n=4) dataset with 1,070 patients with PDAC, and statistical analysis confirmed its clinical effectiveness in the external test set consisting of three centers. The developed risk marker was the strongest predictor of overall survival among preoperative factors and it has the potential to be combined with established clinical factors to select patients at higher risk who might benefit from neoadjuvant therapy.

Ziyin Zeng, Qingyong Hu, Zhong Xie et al.

We study the problem of semantic segmentation of large-scale 3D point clouds. In recent years, significant research efforts have been directed toward local feature aggregation, improved loss functions and sampling strategies. While the fundamental framework of point cloud semantic segmentation has been largely overlooked, with most existing approaches rely on the U-Net architecture by default. In this paper, we propose U-Next, a small but mighty framework designed for point cloud semantic segmentation. The key to this framework is to learn multi-scale hierarchical representations from semantically similar feature maps. Specifically, we build our U-Next by stacking multiple U-Net $L^1$ codecs in a nested and densely arranged manner to minimize the semantic gap, while simultaneously fusing the feature maps across scales to effectively recover the fine-grained details. We also devised a multi-level deep supervision mechanism to further smooth gradient propagation and facilitate network optimization. Extensive experiments conducted on three large-scale benchmarks including S3DIS, Toronto3D, and SensatUrban demonstrate the superiority and the effectiveness of the proposed U-Next architecture. Our U-Next architecture shows consistent and visible performance improvements across different tasks and baseline models, indicating its great potential to serve as a general framework for future research.

Sijing Li, Zhongwei Qiu, Jiang Liu et al.

Accurate tumor analysis is central to clinical radiology and precision oncology, where early detection, reliable lesion characterization, and pathology-level risk assessment guide diagnosis and treatment planning. Chain-of-Thought (CoT) reasoning is particularly important in this setting because it enables step-by-step interpretation from imaging findings to clinical impressions and pathology conclusions, improving traceability and reducing diagnostic errors. Here, we target the clinical tumor analysis task and build a large-scale benchmark that operationalizes a multimodal reasoning pipeline, spanning findings, impressions, and pathology predictions. We curate TumorCoT, a large-scale dataset of 1.5M CoT-labeled VQA instructions paired with 3D CT scans, with step-aligned rationales and cross-modal alignments along the trajectory from findings to impression to pathology, enabling evaluation of both answer accuracy and reasoning consistency. We further propose TumorChain, a multimodal interleaved reasoning framework that tightly couples 3D imaging encoders, clinical text understanding, and organ-level vision-language alignment. Through cross-modal alignment and iterative interleaved causal reasoning, TumorChain grounds visual evidence, aggregates conclusions, and issues pathology predictions after multiple rounds of self-refinement, improving traceability and reducing hallucination risk. Experiments show consistent improvements over strong baselines in lesion detection, impression generation, and pathology classification, and demonstrate strong generalization on the DeepTumorVQA benchmark. These results highlight the potential of multimodal reasoning for reliable and interpretable tumor analysis in clinical practice. Detailed information about our project can be found on our project homepage at https://github.com/ZJU4HealthCare/TumorChain.

Ailin Huang, Ang Li, Aobo Kong et al.

We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.

Jiaxiang Fan, Jian Zhou, Xiaoyu Deng et al.

Recognition of facial expression is a challenge when it comes to computer vision. The primary reasons are class imbalance due to data collection and uncertainty due to inherent noise such as fuzzy facial expressions and inconsistent labels. However, current research has focused either on the problem of class imbalance or on the problem of uncertainty, ignoring the intersection of how to address these two problems. Therefore, in this paper, we propose a framework based on Resnet and Attention to solve the above problems. We design weight for each class. Through the penalty mechanism, our model will pay more attention to the learning of small samples during training, and the resulting decrease in model accuracy can be improved by a Convolutional Block Attention Module (CBAM). Meanwhile, our backbone network will also learn an uncertain feature for each sample. By mixing uncertain features between samples, the model can better learn those features that can be used for classification, thus suppressing uncertainty. Experiments show that our method surpasses most basic methods in terms of accuracy on facial expression data sets (e.g., AffectNet, RAF-DB), and it also solves the problem of class imbalance well.

Jiawei Xiong, Olga Fink, Jian Zhou et al.

Limited availability of representative time-to-failure (TTF) trajectories either limits the performance of deep learning (DL)-based approaches on remaining useful life (RUL) prediction in practice or even precludes their application. Generating synthetic data that is physically plausible is a promising way to tackle this challenge. In this study, a novel hybrid framework combining the controlled physics-informed data generation approach with a deep learning-based prediction model for prognostics is proposed. In the proposed framework, a new controlled physics-informed generative adversarial network (CPI-GAN) is developed to generate synthetic degradation trajectories that are physically interpretable and diverse. Five basic physics constraints are proposed as the controllable settings in the generator. A physics-informed loss function with penalty is designed as the regularization term, which ensures that the changing trend of system health state recorded in the synthetic data is consistent with the underlying physical laws. Then, the generated synthetic data is used as input of the DL-based prediction model to obtain the RUL estimations. The proposed framework is evaluated based on new Commercial Modular Aero-Propulsion System Simulation (N-CMAPSS), a turbofan engine prognostics dataset where a limited avail-ability of TTF trajectories is assumed. The experimental results demonstrate that the proposed framework is able to generate synthetic TTF trajectories that are consistent with underlying degradation trends. The generated trajectories enable to significantly improve the accuracy of RUL predictions.

Guoqing Ma, Haoyang Huang, Kun Yan et al.

We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length. A deep compression Variational Autoencoder, Video-VAE, is designed for video generation tasks, achieving 16x16 spatial and 8x temporal compression ratios, while maintaining exceptional video reconstruction quality. User prompts are encoded using two bilingual text encoders to handle both English and Chinese. A DiT with 3D full attention is trained using Flow Matching and is employed to denoise input noise into latent frames. A video-based DPO approach, Video-DPO, is applied to reduce artifacts and improve the visual quality of the generated videos. We also detail our training strategies and share key observations and insights. Step-Video-T2V's performance is evaluated on a novel video generation benchmark, Step-Video-T2V-Eval, demonstrating its state-of-the-art text-to-video quality when compared with both open-source and commercial engines. Additionally, we discuss the limitations of current diffusion-based model paradigm and outline future directions for video foundation models. We make both Step-Video-T2V and Step-Video-T2V-Eval available at https://github.com/stepfun-ai/Step-Video-T2V. The online version can be accessed from https://yuewen.cn/videos as well. Our goal is to accelerate the innovation of video foundation models and empower video content creators.

Wenxuan Li, Qin Zou, Chi Chen et al.

3D object detection in driving scenarios faces the challenge of complex road environments, which can lead to the loss or incompleteness of key features, thereby affecting perception performance. To address this issue, we propose an advanced detection framework called Co-Fix3D. Co-Fix3D integrates Local and Global Enhancement (LGE) modules to refine Bird's Eye View (BEV) features. The LGE module uses Discrete Wavelet Transform (DWT) for pixel-level local optimization and incorporates an attention mechanism for global optimization. To handle varying detection difficulties, we adopt multi-head LGE modules, enabling each module to focus on targets with different levels of detection complexity, thus further enhancing overall perception capability. Experimental results show that on the nuScenes dataset's LiDAR benchmark, Co-Fix3D achieves 69.4\% mAP and 73.5\% NDS, while on the multimodal benchmark, it achieves 72.3\% mAP and 74.7\% NDS. The source code is publicly available at \href{https://github.com/rubbish001/Co-Fix3d}{https://github.com/rubbish001/Co-Fix3d}.

Wenzhou Lv, Tianyu Wu, Luolin Xiong et al.

Objective: The artificial pancreas (AP) has shown promising potential in achieving closed-loop glucose control for individuals with type 1 diabetes mellitus (T1DM). However, designing an effective control policy for the AP remains challenging due to the complex physiological processes, delayed insulin response, and inaccurate glucose measurements. While model predictive control (MPC) offers safety and stability through the dynamic model and safety constraints, it lacks individualization and is adversely affected by unannounced meals. Conversely, deep reinforcement learning (DRL) provides personalized and adaptive strategies but faces challenges with distribution shifts and substantial data requirements. Methods: We propose a hybrid control policy for the artificial pancreas (HyCPAP) to address the above challenges. HyCPAP combines an MPC policy with an ensemble DRL policy, leveraging the strengths of both policies while compensating for their respective limitations. To facilitate faster deployment of AP systems in real-world settings, we further incorporate meta-learning techniques into HyCPAP, leveraging previous experience and patient-shared knowledge to enable fast adaptation to new patients with limited available data. Results: We conduct extensive experiments using the FDA-accepted UVA/Padova T1DM simulator across three scenarios. Our approaches achieve the highest percentage of time spent in the desired euglycemic range and the lowest occurrences of hypoglycemia. Conclusion: The results clearly demonstrate the superiority of our methods for closed-loop glucose management in individuals with T1DM. Significance: The study presents novel control policies for AP systems, affirming the great potential of proposed methods for efficient closed-loop glucose control.

NextStep Team, Chunrui Han, Guopeng Li et al. · tsinghua

Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.

Jianhui Wu, Jian Zhou, Zhi Zhou et al.

High-quality global illumination (GI) in real-time rendering is commonly achieved using precomputed lighting techniques, with lightmap as the standard choice. To support GI for static objects in dynamic lighting environments, multiple lightmaps at different lighting conditions need to be precomputed, which incurs substantial storage and memory overhead. To overcome this limitation, we propose Neural Dynamic GI (NDGI), a novel compression technique specifically designed for temporal lightmap sets. Our method utilizes multi-dimensional feature maps and lightweight neural networks to integrate the temporal information instead of storing multiple sets explicitly, which significantly reduces the storage size of lightmaps. Additionally, we introduce a block compression (BC) simulation strategy during the training process, which enables BC compression on the final generated feature maps and further improves the compression ratio. To enable efficient real-time decompression, we also integrate a virtual texturing (VT) system with our neural representation. Compared with prior methods, our approach achieves high-quality dynamic GI while maintaining remarkably low storage and memory requirements, with only modest real-time decompression overhead. To facilitate further research in this direction, we will release our temporal lightmap dataset precomputed in multiple scenes featuring diverse temporal variations.

Jian Zhou, Sihao Lin, Shuai Fu et al.

Behavior Cloning (BC) is a data-driven supervised learning approach that has gained increasing attention with the success of scaling laws in language and vision domains. Among its implementations in robotic manipulation, Diffusion Policy (DP), with its two variants DP-CNN (DP-C) and DP-Transformer (DP-T), is one of the most effective and widely adopted models, demonstrating the advantages of predicting continuous action sequences. However, both DP and other BC methods remain constrained by the scarcity of paired training data, and the internal mechanisms underlying DP's effectiveness remain insufficiently understood, leading to limited generalization and a lack of principled design in model development. In this work, we propose a decoupled training recipe that leverages nearly cost-free kinematics-generated trajectories as observation-free data to pretrain a general action head (action generator). The pretrained action head is then frozen and adapted to novel tasks through feature modulation. Our experiments demonstrate the feasibility of this approach in both in-distribution and out-of-distribution scenarios. As an additional benefit, decoupling improves training efficiency; for instance, DP-C achieves up to a 41% speedup. Furthermore, the confinement of task-specific knowledge to the conditioning components under decoupling, combined with the near-identical performance of DP-C in both normal and decoupled training, indicates that the action generation backbone plays a limited role in robotic manipulation. Motivated by this observation, we introduce DP-MLP, which replaces the 244M-parameter U-Net backbone of DP-C with only 4M parameters of simple MLP blocks, achieving a 83.9% faster training speed under normal training and 89.1% under decoupling.

Yuemei Xu, Kexin Xu, Jian Zhou et al.

The current Large Language Models (LLMs) face significant challenges in improving their performance on low-resource languages and urgently need data-efficient methods without costly fine-tuning. From the perspective of language-bridge, we propose a simple yet effective method, namely BridgeX-ICL, to improve the zero-shot Cross-lingual In-Context Learning (X-ICL) for low-resource languages. Unlike existing works focusing on language-specific neurons, BridgeX-ICL explores whether sharing neurons can improve cross-lingual performance in LLMs. We construct neuron probe data from the ground-truth MUSE bilingual dictionaries, and define a subset of language overlap neurons accordingly to ensure full activation of these anchored neurons. Subsequently, we propose an HSIC-based metric to quantify LLMs' internal linguistic spectrum based on overlapping neurons, guiding optimal bridge selection. The experiments conducted on 4 cross-lingual tasks and 15 language pairs from 7 diverse families, covering both high-low and moderate-low pairs, validate the effectiveness of BridgeX-ICL and offer empirical insights into the underlying multilingual mechanisms of LLMs. The code is publicly available at https://github.com/xuyuemei/BridgeX-ICL.

Haiyan Wu, Yanyun Qu, Shaohui Lin et al.

Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images as positive samples to guide the training of dehazing network while negative information is unexploited. Moreover, most of them focus on strengthening the dehazing network with an increase of depth and width, leading to a significant requirement of computation and memory. In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively. CR ensures that the restored image is pulled to closer to the clear image and pushed to far away from the hazy image in the representation space. Furthermore, considering trade-off between performance and memory storage, we develop a compact dehazing network based on autoencoder-like (AE) framework. It involves an adaptive mixup operation and a dynamic feature enhancement module, which can benefit from preserving information flow adaptively and expanding the receptive field to improve the network's transformation capability, respectively. We term our dehazing network with autoencoder and contrastive regularization as AECR-Net. The extensive experiments on synthetic and real-world datasets demonstrate that our AECR-Net surpass the state-of-the-art approaches. The code is released in https://github.com/GlassyWu/AECR-Net.

StepFun, Bin Wang, Bojun Wang et al.

Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hardware-aware model-system co-design optimized for minimizing decoding costs. Step-3 innovates in two key dimensions: (1) A novel Multi-Matrix Factorization Attention (MFA) mechanism that significantly reduces both KV cache size and computation while maintaining high attention expressiveness, and (2) Attention-FFN Disaggregation (AFD), a distributed inference system that decouples attention and Feed-Forward Network (FFN) layers into specialized subsystems. This co-design achieves unprecedented cost efficiency: Step-3 significantly reduces theoretical decoding costs compared with models like DeepSeek-V3 and Qwen3 MoE 235B, with the gains widening at longer context. Step-3 achieves low cost while activating 38B parameters per token (more than DeepSeek-V3 and Qwen3 MoE 235B), demonstrating that hardware-aligned attention arithmetic intensity, MoE sparsity, and AFD are critical to cost-effectiveness. We perform a head-to-head comparison with DeepSeek-V3 in its favorable scenarios. Our implementation on Hopper GPUs achieves a decoding throughput of up to 4,039 tokens per second per GPU under 50ms TPOT SLA (4K context, FP8, no MTP). It is higher than DeepSeek-V3's 2,324 in the same setup and sets a new Pareto frontier for LLM decoding.

Anqing Jiang, Jinhao Chai, Yu Gao et al.

Recent advancements in high-definition \emph{HD} map construction have demonstrated the effectiveness of dense representations, which heavily rely on computationally intensive bird's-eye view \emph{BEV} features. While sparse representations offer a more efficient alternative by avoiding dense BEV processing, existing methods often lag behind due to the lack of tailored designs. These limitations have hindered the competitiveness of sparse representations in online HD map construction. In this work, we systematically revisit and enhance sparse representation techniques, identifying key architectural and algorithmic improvements that bridge the gap with--and ultimately surpass--dense approaches. We introduce a dedicated network architecture optimized for sparse map feature extraction, a sparse-dense segmentation auxiliary task to better leverage geometric and semantic cues, and a denoising module guided by physical priors to refine predictions. Through these enhancements, our method achieves state-of-the-art performance on the nuScenes dataset, significantly advancing HD map construction and centerline detection. Specifically, SparseMeXt-Tiny reaches a mean average precision \emph{mAP} of 55.5% at 32 frames per second \emph{fps}, while SparseMeXt-Base attains 65.2% mAP. Scaling the backbone and decoder further, SparseMeXt-Large achieves an mAP of 68.9% at over 20 fps, establishing a new benchmark for sparse representations in HD map construction. These results underscore the untapped potential of sparse methods, challenging the conventional reliance on dense representations and redefining efficiency-performance trade-offs in the field.

Guangyu Guo, Jiawen Yao, Yingda Xia et al.

The absence of adequately sufficient expert-level tumor annotations hinders the effectiveness of supervised learning based opportunistic cancer screening on medical imaging. Clinical reports (that are rich in descriptive textual details) can offer a "free lunch'' supervision information and provide tumor location as a type of weak label to cope with screening tasks, thus saving human labeling workloads, if properly leveraged. However, predicting cancer only using such weak labels can be very changeling since tumors are usually presented in small anatomical regions compared to the whole 3D medical scans. Weakly semi-supervised learning (WSSL) utilizes a limited set of voxel-level tumor annotations and incorporates alongside a substantial number of medical images that have only off-the-shelf clinical reports, which may strike a good balance between minimizing expert annotation workload and optimizing screening efficacy. In this paper, we propose a novel text-guided learning method to achieve highly accurate cancer detection results. Through integrating diagnostic and tumor location text prompts into the text encoder of a vision-language model (VLM), optimization of weakly supervised learning can be effectively performed in the latent space of VLM, thereby enhancing the stability of training. Our approach can leverage clinical knowledge by large-scale pre-trained VLM to enhance generalization ability, and produce reliable pseudo tumor masks to improve cancer detection. Our extensive quantitative experimental results on a large-scale cancer dataset, including 1,651 unique patients, validate that our approach can reduce human annotation efforts by at least 70% while maintaining comparable cancer detection accuracy to competing fully supervised methods (AUC value 0.961 versus 0.966).

Haifeng Wang, Hao Xu, Jun Wang et al.

Recognizing various surgical tools, actions and phases from surgery videos is an important problem in computer vision with exciting clinical applications. Existing deep-learning-based methods for this problem either process each surgical video as a series of independent images without considering their dependence, or rely on complicated deep learning models to count for dependence of video frames. In this study, we revealed from exploratory data analysis that surgical videos enjoy relatively simple semantic structure, where the presence of surgical phases and tools can be well modeled by a compact hidden Markov model (HMM). Based on this observation, we propose an HMM-stabilized deep learning method for tool presence detection. A wide range of experiments confirm that the proposed approaches achieve better performance with lower training and running costs, and support more flexible ways to construct and utilize training data in scenarios where not all surgery videos of interest are extensively labelled. These results suggest that popular deep learning approaches with over-complicated model structures may suffer from inefficient utilization of data, and integrating ingredients of deep learning and statistical learning wisely may lead to more powerful algorithms that enjoy competitive performance, transparent interpretation and convenient model training simultaneously.

Siming Zhang, Zhehui Shen, Shijie Chen et al.

NBA franchise management is not a sequence of independent tasks, but a single dynamic control problem in which roster construction, cash-flow discipline, media strategy, external market shocks, and player-health uncertainty interact over time. Using the New York Knicks as a case study, this paper develops a unified decision architecture for franchise management under competitive, financial, and regulatory constraints. The core layer is formulated as a rolling-horizon stochastic mixed-integer program augmented with distributionally robust optimization and conditional value-at-risk constraints, so that long-run franchise value can be optimized while downside exposure remains explicitly controlled. On top of this core layer, we construct coordinated modules for transaction execution, league-expansion shock transmission, media-rights regime transition, and injury-triggered re-optimization. This integrated design reframes multiple managerial mechanisms inside one research problem: how should an NBA franchise allocate resources and update decisions when performance objectives and commercial objectives are jointly determined under uncertainty? The manuscript is organized around problem formulation, model architecture, empirical validation, robustness analysis, and managerial interpretation.

Junchi Zhou, Haozhou Wang, Yoichiro Kato et al.

Developing computer vision-based rice phenotyping techniques is crucial for precision field management and accelerating breeding, thereby continuously advancing rice production. Among phenotyping tasks, distinguishing image components is a key prerequisite for characterizing plant growth and development at the organ scale, enabling deeper insights into eco-physiological processes. However, due to the fine structure of rice organs and complex illumination within the canopy, this task remains highly challenging, underscoring the need for a high-quality training dataset. Such datasets are scarce, both due to a lack of large, representative collections of rice field images and the time-intensive nature of annotation. To address this gap, we established the first comprehensive multi-class rice semantic segmentation dataset, RiceSEG. We gathered nearly 50,000 high-resolution, ground-based images from five major rice-growing countries (China, Japan, India, the Philippines, and Tanzania), encompassing over 6,000 genotypes across all growth stages. From these original images, 3,078 representative samples were selected and annotated with six classes (background, green vegetation, senescent vegetation, panicle, weeds, and duckweed) to form the RiceSEG dataset. Notably, the sub-dataset from China spans all major genotypes and rice-growing environments from the northeast to the south. Both state-of-the-art convolutional neural networks and transformer-based semantic segmentation models were used as baselines. While these models perform reasonably well in segmenting background and green vegetation, they face difficulties during the reproductive stage, when canopy structures are more complex and multiple classes are involved. These findings highlight the importance of our dataset for developing specialized segmentation models for rice and other crops.

Yanmeng Wang, Wenkai Ji, Jian Zhou et al.

Federated learning (FL) has emerged as a promising distributed learning paradigm for training deep neural networks (DNNs) at the wireless edge, but its performance can be severely hindered by unreliable wireless transmission and inherent data heterogeneity among clients. Existing solutions primarily address these challenges by incorporating wireless resource optimization strategies, often focusing on uplink resource allocation across clients under the assumption of homogeneous client-server network standards. However, these approaches overlooked the fact that mobile clients may connect to the server via diverse network standards (e.g., 4G, 5G, Wi-Fi) with customized configurations, limiting the flexibility of server-side modifications and restricting applicability in real-world commercial networks. This paper presents a novel theoretical analysis about how transmission failures in unreliable networks distort the effective label distributions of local samples, causing deviations from the global data distribution and introducing convergence bias in FL. Our analysis reveals that a carefully designed client selection strategy can mitigate biases induced by network unreliability and data heterogeneity. Motivated by this insight, we propose FedCote, a client selection approach that optimizes client selection probabilities without relying on wireless resource scheduling. Experimental results demonstrate the robustness of FedCote in DNN-based classification tasks under unreliable networks with frequent transmission failures.

Yuchen Zhang, Jian Zhou

Inverse generation problems, such as denoising without ground truth observations, is a critical challenge in many scientific inquiries and real-world applications. While recent advances in generative models like diffusion models, conditional flow matching, and consistency models achieved impressive results by casting generation as denoising problems, they cannot be directly used for inverse generation without access to clean data. Here we introduce Inverse Flow (IF), a novel framework that enables using these generative models for inverse generation problems including denoising without ground truth. Inverse Flow can be flexibly applied to nearly any continuous noise distribution and allows complex dependencies. We propose two algorithms for learning Inverse Flows, Inverse Flow Matching (IFM) and Inverse Consistency Model (ICM). Notably, to derive the computationally efficient, simulation-free inverse consistency model objective, we generalized consistency training to any forward diffusion processes or conditional flows, which have applications beyond denoising. We demonstrate the effectiveness of IF on synthetic and real datasets, outperforming prior approaches while enabling noise distributions that previous methods cannot support. Finally, we showcase applications of our techniques to fluorescence microscopy and single-cell genomics data, highlighting IF's utility in scientific problems. Overall, this work expands the applications of powerful generative models to inversion generation problems.

Yulin Chen, Guoheng Huang, Kai Huang et al.

Accurate segmentation of lesion regions is crucial for clinical diagnosis and treatment across various diseases. While deep convolutional networks have achieved satisfactory results in medical image segmentation, they face challenges such as loss of lesion shape information due to continuous convolution and downsampling, as well as the high cost of manually labeling lesions with varying shapes and sizes. To address these issues, we propose a novel medical visual prompting (MVP) framework that leverages pre-training and prompting concepts from natural language processing (NLP). The framework utilizes three key components: Super-Pixel Guided Prompting (SPGP) for superpixelating the input image, Image Embedding Guided Prompting (IEGP) for freezing patch embedding and merging with superpixels to provide visual prompts, and Adaptive Attention Mechanism Guided Prompting (AAGP) for pinpointing prompt content and efficiently adapting all layers. By integrating SPGP, IEGP, and AAGP, the MVP enables the segmentation network to better learn shape prompting information and facilitates mutual learning across different tasks. Extensive experiments conducted on five datasets demonstrate superior performance of this method in various challenging medical image tasks, while simplifying single-task medical segmentation models. This novel framework offers improved performance with fewer parameters and holds significant potential for accurate segmentation of lesion regions in various medical tasks, making it clinically valuable.

Jian Zhou

We present a large-scale computational study combining arbitrary-precision arithmetic, sequence acceleration, and the PSLQ integer relation algorithm to discover exact closed-form expressions for fundamental constants arising in asymptotic analysis. We compute the Stokes multipliers C_M of the one-dimensional anharmonic oscillators H = p^2/2 + x^2/2 + g x^{2M} for M = 2, 3, ..., 11, extracting 17-30 significant digits from up to 1200 perturbation coefficients computed at 300-digit working precision. The computational pipeline consists of three stages: (i) Rayleigh-Schrodinger recursion in the harmonic oscillator basis, (ii) Richardson extrapolation of order 40-100 to accelerate convergence of ratio sequences, and (iii) PSLQ searches over bases of Gamma-function values and algebraic numbers. This pipeline discovers three new exact identities: C_3^2 pi^4 = 32, C_5^4 Gamma(1/4)^4 pi^5 = 2^{12} 3^2, and C_7^6 Gamma(1/3)^9 pi^6 = 2^{20} 3^3, in addition to confirming the known C_2^2 pi^3 = 6. Equally significant is a negative result: exhaustive PSLQ searches at 30-digit precision with coefficient bounds up to 2000 find no closed form for C_4, strongly suggesting the x^8 case introduces a genuinely new transcendental number. A number-theoretic pattern emerges: closed-form existence correlates with Euler's totient function phi(M-1)/2, which counts algebraically independent Gamma-function transcendentals at denominator M-1. We formulate conjectures connecting computational constant recognition to classical number theory, and provide all code and data for full reproducibility.

Lijun Shang, Yadong Yu, Wenqiang Kang et al.

Two-dimensional (2D) materials have showed widespread applications in energy storage and conversion owning to their unique physicochemical, and electronic properties. Most of the valuable information for the materials, such as their properties and preparation methods, is included in the published research papers. However, due to the dispersion of synthe

Shuai Fu, Jian Zhou, Qi Chen et al.

Diffusion probabilistic models (DPMs) have demonstrated remarkable progress in generative tasks, such as image and video synthesis. However, they still often produce hallucinated samples (hallucinations) that conflict with real-world knowledge, such as generating an implausible duplicate cup floating beside another cup. Despite their prevalence, the lack of feasible methodologies for systematically quantifying such hallucinations hinders progress in addressing this challenge and obscures potential pathways for designing next-generation generative models under factual constraints. In this work, we bridge this gap by focusing on a specific form of hallucination, which we term counting hallucination, referring to the generation of an incorrect number of instances or structured objects, such as a hand image with six fingers, despite such patterns being absent from the training data. To this end, we construct a dataset suite CountHalluSet, with well-defined counting criteria, comprising ToyShape, SimObject, and RealHand. Using these datasets, we develop a standardized evaluation protocol for quantifying counting hallucinations, and systematically examine how different sampling conditions in DPMs, including solver type, ODE solver order, sampling steps, and initial noise, affect counting hallucination levels. Furthermore, we analyze their correlation with common evaluation metrics such as FID, revealing that this widely used image quality metric fails to capture counting hallucinations consistently. This work aims to take the first step toward systematically quantifying hallucinations in diffusion models and offer new insights into the investigation of hallucination phenomena in image generation.

Jian Zhou, Jiazheng Li, Sirui Zhuge et al.

This paper proposed an approach to automatically discovering subject dimension, action dimension, object dimension and adverbial dimension from texts to efficiently operate texts and support query in natural language. The high quality of trees guarantees that all subjects, actions, objects and adverbials and their subclass relations within texts can be represented. The independency of trees ensures that there is no redundant representation between trees. The expressiveness of trees ensures that the majority of sentences can be accessed from each tree and the rest of sentences can be accessed from at least one tree so that the tree-based search mechanism can support querying in natural language. Experiments show that the average precision, recall and F1-score of the abstraction trees constructed by the subclass relations of subject, action, object and adverbial are all greater than 80%. The application of the proposed approach to supporting query in natural language demonstrates that different types of question patterns for querying subject or object have high coverage of texts, and searching multiple trees on subject, action, object and adverbial according to the question pattern can quickly reduce search space to locate target sentences, which can support precise operation on texts.

Pavel Avdeyev, Chenlai Shi, Yuhao Tan et al.

Designing biological sequences is an important challenge that requires satisfying complex constraints and thus is a natural problem to address with deep generative modeling. Diffusion generative models have achieved considerable success in many applications. Score-based generative stochastic differential equations (SDE) model is a continuous-time diffusion model framework that enjoys many benefits, but the originally proposed SDEs are not naturally designed for modeling discrete data. To develop generative SDE models for discrete data such as biological sequences, here we introduce a diffusion process defined in the probability simplex space with stationary distribution being the Dirichlet distribution. This makes diffusion in continuous space natural for modeling discrete data. We refer to this approach as Dirchlet diffusion score model. We demonstrate that this technique can generate samples that satisfy hard constraints using a Sudoku generation task. This generative model can also solve Sudoku, including hard puzzles, without additional training. Finally, we applied this approach to develop the first human promoter DNA sequence design model and showed that designed sequences share similar properties with natural promoter sequences.

Qing Pan, Teng Gao, Jian Zhou et al.

Compared with air-conducted speech, bone-conducted speech has the unique advantage of shielding background noise. Enhancement of bone-conducted speech helps to improve its quality and intelligibility. In this paper, a novel CycleGAN with dual adversarial loss (CycleGAN-DAL) is proposed for bone-conducted speech enhancement. The proposed method uses an adversarial loss and a cycle-consistent loss simultaneously to learn forward and cyclic mapping, in which the adversarial loss is replaced with the classification adversarial loss and the defect adversarial loss to consolidate the forward mapping. Compared with conventional baseline methods, it can learn feature mapping between bone-conducted speech and target speech without additional air-conducted speech assistance. Moreover, the proposed method also avoids the oversmooth problem which is occurred commonly in conventional statistical based models. Experimental results show that the proposed method outperforms baseline methods such as CycleGAN, GMM, and BLSTM. Keywords: Bone-conducted speech enhancement, dual adversarial loss, Parallel CycleGAN, high frequency speech reconstruction

Teng Gao, Jian Zhou, Huabin Wang et al.

Whispered speech is a special way of pronunciation without using vocal cord vibration. A whispered speech does not contain a fundamental frequency, and its energy is about 20dB lower than that of a normal speech. Converting a whispered speech into a normal speech can improve speech quality and intelligibility. In this paper, a novel attention-guided generative adversarial network model incorporating an autoencoder, a Siamese neural network, and an identity mapping loss function for whisper to normal speech conversion (AGAN-W2SC) is proposed. The proposed method avoids the challenge of estimating the fundamental frequency of the normal voiced speech converted from a whispered speech. Specifically, the proposed model is more amendable to practical applications because it does not need to align speech features for training. Experimental results demonstrate that the proposed AGAN-W2SC can obtain improved speech quality and intelligibility compared with dynamic-time-warping-based methods.

Chengwei Chen, Yuan Xie, Shaohui Lin et al.

Novelty detection is the process of determining whether a query example differs from the learned training distribution. Previous methods attempt to learn the representation of the normal samples via generative adversarial networks (GANs). However, they will suffer from instability training, mode dropping, and low discriminative ability. Recently, various pretext tasks (e.g. rotation prediction and clustering) have been proposed for self-supervised learning in novelty detection. However, the learned latent features are still low discriminative. We overcome such problems by introducing a novel decoder-encoder framework. Firstly, a generative network (a.k.a. decoder) learns the representation by mapping the initialized latent vector to an image. In particular, this vector is initialized by considering the entire distribution of training data to avoid the problem of mode-dropping. Secondly, a contrastive network (a.k.a. encoder) aims to ``learn to compare'' through mutual information estimation, which directly helps the generative network to obtain a more discriminative representation by using a negative data augmentation strategy. Extensive experiments show that our model has significant superiority over cutting-edge novelty detectors and achieves new state-of-the-art results on some novelty detection benchmarks, e.g. CIFAR10 and DCASE. Moreover, our model is more stable for training in a non-adversarial manner, compared to other adversarial based novelty detection methods.

Huabin Wang, Rui Cheng, Jian Zhou et al.

An ability to generalize unconstrained conditions such as severe occlusions and large pose variations remains a challenging goal to achieve in face alignment. In this paper, a multistage model based on deep neural networks is proposed which takes advantage of spatial transformer networks, hourglass networks and exemplar-based shape constraints. First, a spatial transformer - generative adversarial network which consists of convolutional layers and residual units is utilized to solve the initialization issues caused by face detectors, such as rotation and scale variations, to obtain improved face bounding boxes for face alignment. Then, stacked hourglass network is employed to obtain preliminary locations of landmarks as well as their corresponding scores. In addition, an exemplar-based shape dictionary is designed to determine landmarks with low scores based on those with high scores. By incorporating face shape constraints, misaligned landmarks caused by occlusions or cluttered backgrounds can be considerably improved. Extensive experiments based on challenging benchmark datasets are performed to demonstrate the superior performance of the proposed method over other state-of-the-art methods.

Shenglan Liu, Xiang Liu, Yang Liu et al.

Supervised learning methods are widely used in machine learning. However, the lack of labels in existing data limits the application of these technologies. Visual interactive learning (VIL) compared with computers can avoid semantic gap, and solve the labeling problem of small label quantity (SLQ) samples in a groundbreaking way. In order to fully understand the importance of VIL to the interaction process, we re-summarize the interactive learning related algorithms (e.g. clustering, classification, retrieval etc.) from the perspective of VIL. Note that, perception and cognition are two main visual processes of VIL. On this basis, we propose a perceptual visual interactive learning (PVIL) framework, which adopts gestalt principle to design interaction strategy and multi-dimensionality reduction (MDR) to optimize the process of visualization. The advantage of PVIL framework is that it combines computer's sensitivity of detailed features and human's overall understanding of global tasks. Experimental results validate that the framework is superior to traditional computer labeling methods (such as label propagation) in both accuracy and efficiency, which achieves significant classification results on dense distribution and sparse classes dataset.

Huazhong Shu, Jian Zhou, Guo-Niu Han et al.

A set of orthonormal polynomials is proposed for image reconstruction from projection data. The relationship between the projection moments and image moments is discussed in detail, and some interesting properties are demonstrated. Simulation results are provided to validate the method and to compare its performance with previous works.

Jian Zhou, Olga G. Troyanskaya

Predicting protein secondary structure is a fundamental problem in protein structure prediction. Here we present a new supervised generative stochastic network (GSN) based method to predict local secondary structure with deep hierarchical representations. GSN is a recently proposed deep learning technique (Bengio & Thibodeau-Laufer, 2013) to globally train deep generative model. We present the supervised extension of GSN, which learns a Markov chain to sample from a conditional distribution, and applied it to protein structure prediction. To scale the model to full-sized, high-dimensional data, like protein sequences with hundreds of amino acids, we introduce a convolutional architecture, which allows efficient learning across multiple layers of hierarchical representations. Our architecture uniquely focuses on predicting structured low-level labels informed with both low and high-level representations learned by the model. In our application this corresponds to labeling the secondary structure state of each amino-acid residue. We trained and tested the model on separate sets of non-homologous proteins sharing less than 30% sequence identity. Our model achieves 66.4% Q8 accuracy on the CB513 dataset, better than the previously reported best performance 64.9% (Wang et al., 2011) for this challenging secondary structure prediction problem.