Zhu Liu

Jinyuan Liu, Zhu Liu, Guanyao Wu et al.

Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation. Early efforts focus on boosting the performance for only one task, \emph{e.g.,} fusion or segmentation, making it hard to reach~`Best of Both Worlds'. To overcome this issue, in this paper, we propose a \textbf{M}ulti-\textbf{i}nteractive \textbf{F}eature learning architecture for image fusion and \textbf{Seg}mentation, namely SegMiF, and exploit dual-task correlation to promote the performance of both tasks. The SegMiF is of a cascade structure, containing a fusion sub-network and a commonly used segmentation sub-network. By slickly bridging intermediate features between two components, the knowledge learned from the segmentation task can effectively assist the fusion task. Also, the benefited fusion network supports the segmentation one to perform more pretentiously. Besides, a hierarchical interactive attention block is established to ensure fine-grained mapping of all the vital information between two tasks, so that the modality/semantic features can be fully mutual-interactive. In addition, a dynamic weight factor is introduced to automatically adjust the corresponding weights of each task, which can balance the interactive feature correspondence and break through the limitation of laborious tuning. Furthermore, we construct a smart multi-wave binocular imaging system and collect a full-time multi-modality benchmark with 15 annotated pixel-level categories for image fusion and segmentation. Extensive experiments on several public datasets and our benchmark demonstrate that the proposed method outputs visually appealing fused images and perform averagely $7.66\%$ higher segmentation mIoU in the real-world scene than the state-of-the-art approaches. The source code and benchmark are available at \url{https://github.com/JinyuanLiu-CV/SegMiF}.

Zhu Liu, Jinyuan Liu, Benzhuang Zhang et al.

Infrared and visible image fusion is a powerful technique that combines complementary information from different modalities for downstream semantic perception tasks. Existing learning-based methods show remarkable performance, but are suffering from the inherent vulnerability of adversarial attacks, causing a significant decrease in accuracy. In this work, a perception-aware fusion framework is proposed to promote segmentation robustness in adversarial scenes. We first conduct systematic analyses about the components of image fusion, investigating the correlation with segmentation robustness under adversarial perturbations. Based on these analyses, we propose a harmonized architecture search with a decomposition-based structure to balance standard accuracy and robustness. We also propose an adaptive learning strategy to improve the parameter robustness of image fusion, which can learn effective feature extraction under diverse adversarial perturbations. Thus, the goals of image fusion (\textit{i.e.,} extracting complementary features from source modalities and defending attack) can be realized from the perspectives of architectural and learning strategies. Extensive experimental results demonstrate that our scheme substantially enhances the robustness, with gains of 15.3% mIOU of segmentation in the adversarial scene, compared with advanced competitors. The source codes are available at https://github.com/LiuZhu-CV/PAIF.

Yingchi Liu, Zhu Liu, Long Ma et al.

Recently, there has been a growing interest in constructing deep learning schemes for Low-Light Vision (LLV). Existing techniques primarily focus on designing task-specific and data-dependent vision models on the standard RGB domain, which inherently contain latent data associations. In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain. This novel approach connects diverse vision problems by explicitly depicting data generation, which is the first in the field. To precisely characterize the latent correspondence between the generative procedure and the vision task, we establish a bilevel model with the parameters of the generative block defined as the upper level and the parameters of the vision task defined as the lower level. We further develop two types of learning strategies targeting different goals, namely low cost and high accuracy, to acquire a new bilevel generative learning paradigm. The generative blocks embrace a strong generalization ability in other low-light vision tasks through the bilevel optimization on enhancement tasks. Extensive experimental evaluations on three representative low-light vision tasks, namely enhancement, detection, and segmentation, fully demonstrate the superiority of our proposed approach. The code will be available at https://github.com/Yingchi1998/BGL.

Yuhui Wu, Zhu Liu, Jinyuan Liu et al.

Infrared and visible image fusion plays a vital role in the field of computer vision. Previous approaches make efforts to design various fusion rules in the loss functions. However, these experimental designed fusion rules make the methods more and more complex. Besides, most of them only focus on boosting the visual effects, thus showing unsatisfactory performance for the follow-up high-level vision tasks. To address these challenges, in this letter, we develop a semantic-level fusion network to sufficiently utilize the semantic guidance, emancipating the experimental designed fusion rules. In addition, to achieve a better semantic understanding of the feature fusion process, a fusion block based on the transformer is presented in a multi-scale manner. Moreover, we devise a regularization loss function, together with a training strategy, to fully use semantic guidance from the high-level vision tasks. Compared with state-of-the-art methods, our method does not depend on the hand-crafted fusion loss function. Still, it achieves superior performance on visual quality along with the follow-up high-level vision tasks.

Zhu Liu, Yuanhang Yao, Ping Qian et al.

Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution in cluttered, low-contrast infrared imagery and severe sample-distribution imbalance. In this paper, we present a more adaptive and stable framework to address these issues. Leveraging the intrinsic consistency between thermal radiation patterns and heat diffusion, we propose a physics-induced annotation strategy that expands single-point labels into reliable pseudo-masks. To further enhance supervision and alleviate sample imbalance, we develop a bi-level dual-update framework that jointly optimizes detector weights, sample weights, and diffusion parameters. A meta-classifier dynamically predicts sample-wise loss weights, while a differentiable diffusion module refines pseudo-labels with detection feedback, enabling adaptive interaction between training and hyperparameter optimization. Extensive experiments across multiple datasets demonstrate five-fold annotation acceleration, superior detection accuracy, and comparable performance with 30% of the training data, validating the efficiency and practicality of our approach. Our code is available at https://github.com/yuanhang-yao/diffuse-to-detect.

Yaohua Liu, Jiaxin Gao, Xianghao Jiao et al.

Adversarial Training (AT), pivotal in fortifying the robustness of deep learning models, is extensively adopted in practical applications. However, prevailing AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. In this context, our work illuminates the potential of leveraging the target model's historical states as a proxy to provide effective initialization and defense prior, which results in a general proxy guided defense framework, `LAST' ({\bf L}earn from the P{\bf ast}). Specifically, LAST derives response of the proxy model as dynamically learned fast weights, which continuously corrects the update direction of the target model. Besides, we introduce a self-distillation regularized defense objective, ingeniously designed to steer the proxy model's update trajectory without resorting to external teacher models, thereby ameliorating the impact of catastrophic overfitting on performance. Extensive experiments and ablation studies showcase the framework's efficacy in markedly improving model robustness (e.g., up to 9.2\% and 20.3\% enhancement in robust accuracy on CIFAR10 and CIFAR100 datasets, respectively) and training stability. These improvements are consistently observed across various model architectures, larger datasets, perturbation sizes, and attack modalities, affirming LAST's ability to consistently refine both single-step and multi-step AT strategies. The code will be available at~\url{https://github.com/callous-youth/LAST}.

Tao Li, Lixing Wang, Zihan Qiu et al.

High temporal resolution CO2 emission data are crucial for understanding the drivers of emission changes, however, current emission dataset is only available on a yearly basis. Here, we extended a global daily CO2 emissions dataset backwards in time to 1970 using machine learning algorithm, which was trained to predict historical daily emissions on national scales based on relationships between daily emission variations and predictors established for the period since 2019. Variation in daily CO2 emissions far exceeded the smoothed seasonal variations. For example, the range of daily CO2 emissions equivalent to 31% of the year average daily emissions in China and 46% of that in India in 2022, respectively. We identified the critical emission-climate temperature (Tc) is 16.5 degree celsius for global average (18.7 degree celsius for China, 14.9 degree celsius for U.S., and 18.4 degree celsius for Japan), in which negative correlation observed between daily CO2 emission and ambient temperature below Tc and a positive correlation above it, demonstrating increased emissions associated with higher ambient temperature. The long-term time series spanning over fifty years of global daily CO2 emissions reveals an increasing trend in emissions due to extreme temperature events, driven by the rising frequency of these occurrences. This work suggests that, due to climate change, greater efforts may be needed to reduce CO2 emissions.

Yuanhang Yao, Ping Qian, Zhu Liu et al.

Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost; however, lightweight CNN detectors often lack sufficient semantics, leading to noisy pseudo-masks and unstable optimization. To address this, we propose a hierarchical VFM-driven knowledge distillation framework that uses a frozen Vision Foundation Model (VFM) during training. We formulate point-supervised learning as a bilevel optimization process: the inner loop adapts a VFM-embedded teacher on reweighted training samples, while the outer loop transfers validation-guided knowledge to a lightweight student to mitigate pseudo-label noise and training-set bias. We further introduce Semantic-Conditioned Affine Modulation (SCAM) to inject VFM semantics into CNN features at multiple layers. In addition, a dynamic collaborative learning strategy with cluster-level sample reweighting enhances robustness to imperfect pseudo-masks. Experiments on diverse challenging cases across multiple ISTD backbones demonstrate consistent improvements in detection accuracy and training stability. Our code is available at https://github.com/yuanhang-yao/semantic-prior.

Teng Wang, Zhu Liu, Feng Zheng et al.

This report describes the details of our approach for the event dense-captioning task in ActivityNet Challenge 2021. We present a semantic-aware pretraining method for dense video captioning, which empowers the learned features to recognize high-level semantic concepts. Diverse video features of different modalities are fed into an event captioning module to generate accurate and meaningful sentences. Our final ensemble model achieves a 10.00 METEOR score on the test set.

Zhu Deng, Jinjie Liu, Biao Luo et al.

The product carbon footprint (PCF) is crucial for decarbonizing the supply chain, as it measures the direct and indirect greenhouse gas emissions caused by all activities during the product's life cycle. However, PCF accounting often requires expert knowledge and significant time to construct life cycle models. In this study, we test and compare the emergent ability of five large language models (LLMs) in modeling the 'cradle-to-gate' life cycles of products and generating the inventory data of inputs and outputs, revealing their limitations as a generalized PCF knowledge database. By utilizing LLMs, we propose an automatic AI-driven PCF accounting framework, called AutoPCF, which also applies deep learning algorithms to automatically match calculation parameters, and ultimately calculate the PCF. The results of estimating the carbon footprint for three case products using the AutoPCF framework demonstrate its potential in achieving automatic modeling and estimation of PCF with a large reduction in modeling time from days to minutes.

Jinyuan Liu, Guanyao Wu, Zhu Liu et al.

Infrared-visible image fusion (IVIF) is a critical task in computer vision, aimed at integrating the unique features of both infrared and visible spectra into a unified representation. Since 2018, the field has entered the deep learning era, with an increasing variety of approaches introducing a range of networks and loss functions to enhance visual performance. However, challenges such as data compatibility, perception accuracy, and efficiency remain. Unfortunately, there is a lack of recent comprehensive surveys that address this rapidly expanding domain. This paper fills that gap by providing a thorough survey covering a broad range of topics. We introduce a multi-dimensional framework to elucidate common learning-based IVIF methods, from visual enhancement strategies to data compatibility and task adaptability. We also present a detailed analysis of these approaches, accompanied by a lookup table clarifying their core ideas. Furthermore, we summarize performance comparisons, both quantitatively and qualitatively, focusing on registration, fusion, and subsequent high-level tasks. Beyond technical analysis, we discuss potential future directions and open issues in this area. For further details, visit our GitHub repository: https://github.com/RollingPlain/IVIF_ZOO.

Zhu Liu, Cunliang Kong, Ying Liu et al.

Large language models have achieved remarkable success in general language understanding tasks. However, as a family of generative methods with the objective of next token prediction, the semantic evolution with the depth of these models are not fully explored, unlike their predecessors, such as BERT-like architectures. In this paper, we specifically investigate the bottom-up evolution of lexical semantics for a popular LLM, namely Llama2, by probing its hidden states at the end of each layer using a contextualized word identification task. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics. The conclusion is further supported by the monotonic increase in performance via the hidden states for the last meaningless symbols, such as punctuation, in the prompting strategy. Our codes are available at https://github.com/RyanLiut/LLM_LexSem.

Zhisheng Zheng, Puyuan Peng, Anuj Diwan et al.

We introduce VoiceCraft-X, an autoregressive neural codec language model which unifies multilingual speech editing and zero-shot Text-to-Speech (TTS) synthesis across 11 languages: English, Mandarin, Korean, Japanese, Spanish, French, German, Dutch, Italian, Portuguese, and Polish. VoiceCraft-X utilizes the Qwen3 large language model for phoneme-free cross-lingual text processing and a novel token reordering mechanism with time-aligned text and speech tokens to handle both tasks as a single sequence generation problem. The model generates high-quality, natural-sounding speech, seamlessly creating new audio or editing existing recordings within one framework. VoiceCraft-X shows robust performance in diverse linguistic settings, even with limited per-language data, underscoring the power of unified autoregressive approaches for advancing complex, real-world multilingual speech applications. Audio samples are available at https://zhishengzheng.com/voicecraft-x/.

Ping Guo, Chengzhou Li, Guanchen Meng et al.

As one of the most important underwater sensing technologies, forward-looking sonar exhibits unique imaging characteristics. Sonar images are often affected by severe speckle noise, low texture contrast, acoustic shadows, and geometric distortions. These factors make it difficult for traditional teacher-student frameworks to achieve satisfactory performance in sonar semantic segmentation tasks under extremely limited labeled data conditions. To address this issue, we propose a Collaborative Teacher Semantic Segmentation Framework for forward-looking sonar images. This framework introduces a multi-teacher collaborative mechanism composed of one general teacher and multiple sonar-specific teachers. By adopting a multi-teacher alternating guidance strategy, the student model can learn general semantic representations while simultaneously capturing the unique characteristics of sonar images, thereby achieving more comprehensive and robust feature modeling. Considering the challenges of sonar images, which can lead teachers to generate a large number of noisy pseudo-labels, we further design a cross-teacher reliability assessment mechanism. This mechanism dynamically quantifies the reliability of pseudo-labels by evaluating the consistency and stability of predictions across multiple views and multiple teachers, thereby mitigating the negative impact caused by noisy pseudo-labels. Notably, on the FLSMD dataset, when only 2% of the data is labeled, our method achieves a 5.08% improvement in mIoU compared to other state-of-the-art approaches.

Zhu Liu, Zijun Wang, Jinyuan Liu et al.

Thermal imaging is often compromised by dynamic, complex degradations caused by hardware limitations and unpredictable environmental factors. The scarcity of high-quality infrared data, coupled with the challenges of dynamic, intricate degradations, makes it difficult to recover details using existing methods. In this paper, we introduce thermal degradation simulation integrated into the training process via a mini-max optimization, by modeling these degraded factors as adversarial attacks on thermal images. The simulation is dynamic to maximize objective functions, thus capturing a broad spectrum of degraded data distributions. This approach enables training with limited data, thereby improving model performance.Additionally, we introduce a dual-interaction network that combines the benefits of spiking neural networks with scale transformation to capture degraded features with sharp spike signal intensities. This architecture ensures compact model parameters while preserving efficient feature representation. Extensive experiments demonstrate that our method not only achieves superior visual quality under diverse single and composited degradation, but also delivers a significant reduction in processing when trained on only fifty clear images, outperforming existing techniques in efficiency and accuracy. The source code will be available at https://github.com/LiuZhu-CV/DEAL.

Weichao Shen, Yuan Dong, Zonghao Chen et al.

In this paper, we propose PanoViT, a panorama vision transformer to estimate the room layout from a single panoramic image. Compared to CNN models, our PanoViT is more proficient in learning global information from the panoramic image for the estimation of complex room layouts. Considering the difference between a perspective image and an equirectangular image, we design a novel recurrent position embedding and a patch sampling method for the processing of panoramic images. In addition to extracting global information, PanoViT also includes a frequency-domain edge enhancement module and a 3D loss to extract local geometric features in a panoramic image. Experimental results on several datasets demonstrate that our method outperforms state-of-the-art solutions in room layout prediction accuracy.

Zhu Liu, Zhen Hu, Ying Liu

We present the results of our system for the CoMeDi Shared Task, which predicts majority votes (Subtask 1) and annotator disagreements (Subtask 2). Our approach combines model ensemble strategies with MLP-based and threshold-based methods trained on pretrained language models. Treating individual models as virtual annotators, we simulate the annotation process by designing aggregation measures that incorporate continuous relatedness scores and discrete classification labels to capture both majority and disagreement. Additionally, we employ anisotropy removal techniques to enhance performance. Experimental results demonstrate the effectiveness of our methods, particularly for Subtask 2. Notably, we find that standard deviation on continuous relatedness scores among different model manipulations correlates with human disagreement annotations compared to metrics on aggregated discrete labels. The code will be published at https://github.com/RyanLiut/CoMeDi_Solution.

Guofeng Cui, Yang Liu, Pichao Wang et al.

Batch active learning (BAL) is a crucial technique for reducing labeling costs and improving data efficiency in training large-scale deep learning models. Traditional BAL methods often rely on metrics like Mahalanobis Distance to balance uncertainty and diversity when selecting data for annotation. However, these methods predominantly focus on the distribution of unlabeled data and fail to leverage feedback from labeled data or the model's performance. To address these limitations, we introduce TrustSet, a novel approach that selects the most informative data from the labeled dataset, ensuring a balanced class distribution to mitigate the long-tail problem. Unlike CoreSet, which focuses on maintaining the overall data distribution, TrustSet optimizes the model's performance by pruning redundant data and using label information to refine the selection process. To extend the benefits of TrustSet to the unlabeled pool, we propose a reinforcement learning (RL)-based sampling policy that approximates the selection of high-quality TrustSet candidates from the unlabeled data. Combining TrustSet and RL, we introduce the Batch Reinforcement Active Learning with TrustSet (BRAL-T) framework. BRAL-T achieves state-of-the-art results across 10 image classification benchmarks and 2 active fine-tuning tasks, demonstrating its effectiveness and efficiency in various domains.

Jinyuan Liu, Zihang Chen, Zhu Liu et al.

We engage in the relatively underexplored task named thermal infrared image enhancement. Existing infrared image enhancement methods primarily focus on tackling individual degradations, such as noise, contrast, and blurring, making it difficult to handle coupled degradations. Meanwhile, all-in-one enhancement methods, commonly applied to RGB sensors, often demonstrate limited effectiveness due to the significant differences in imaging models. In sight of this, we first revisit the imaging mechanism and introduce a Progressive Prompt Fusion Network (PPFN). Specifically, the PPFN initially establishes prompt pairs based on the thermal imaging process. For each type of degradation, we fuse the corresponding prompt pairs to modulate the model's features, providing adaptive guidance that enables the model to better address specific degradations under single or multiple conditions. In addition, a Selective Progressive Training (SPT) mechanism is introduced to gradually refine the model's handling of composite cases to align the enhancement process, which not only allows the model to remove camera noise and retain key structural details, but also enhancing the overall contrast of the thermal image. Furthermore, we introduce the most high-quality, multi-scenarios infrared benchmark covering a wide range of scenarios. Extensive experiments substantiate that our approach not only delivers promising visual results under specific degradation but also significantly improves performance on complex degradation scenes, achieving a notable 8.76\% improvement. Code is available at https://github.com/Zihang-Chen/HM-TIR.

Zhu Liu, Cunliang Kong, Ying Liu et al.

Semantic map models (SMMs) construct a network-like conceptual space from cross-linguistic instances or forms, based on the connectivity hypothesis. This approach has been widely used to represent similarity and entailment relationships in cross-linguistic concept comparisons. However, most SMMs are manually built by human experts using bottom-up procedures, which are often labor-intensive and time-consuming. In this paper, we propose a novel graph-based algorithm that automatically generates conceptual spaces and SMMs in a top-down manner. The algorithm begins by creating a dense graph, which is subsequently pruned into maximum spanning trees, selected according to metrics we propose. These evaluation metrics include both intrinsic and extrinsic measures, considering factors such as network structure and the trade-off between precision and coverage. A case study on cross-linguistic supplementary adverbs demonstrates the effectiveness and efficiency of our model compared to human annotations and other automated methods. The tool is available at https://github.com/RyanLiut/SemanticMapModel.

Zhu Liu, Zihang Chen, Jinyuan Liu et al.

The detection of small infrared targets against blurred and cluttered backgrounds has remained an enduring challenge. In recent years, learning-based schemes have become the mainstream methodology to establish the mapping directly. However, these methods are susceptible to the inherent complexities of changing backgrounds and real-world disturbances, leading to unreliable and compromised target estimations. In this work, we propose a bi-level adversarial framework to promote the robustness of detection in the presence of distinct corruptions. We first propose a bi-level optimization formulation to introduce dynamic adversarial learning. Specifically, it is composited by the learnable generation of corruptions to maximize the losses as the lower-level objective and the robustness promotion of detectors as the upper-level one. We also provide a hierarchical reinforced learning strategy to discover the most detrimental corruptions and balance the performance between robustness and accuracy. To better disentangle the corruptions from salient features, we also propose a spatial-frequency interaction network for target detection. Extensive experiments demonstrate our scheme remarkably improves 21.96% IOU across a wide array of corruptions and notably promotes 4.97% IOU on the general benchmark. The source codes are available at https://github.com/LiuZhu-CV/BALISTD.

Risheng Liu, Zhu Liu, Jinyuan Liu et al.

Image fusion plays a key role in a variety of multi-sensor-based vision systems, especially for enhancing visual quality and/or extracting aggregated features for perception. However, most existing methods just consider image fusion as an individual task, thus ignoring its underlying relationship with these downstream vision problems. Furthermore, designing proper fusion architectures often requires huge engineering labor. It also lacks mechanisms to improve the flexibility and generalization ability of current fusion approaches. To mitigate these issues, we establish a Task-guided, Implicit-searched and Meta-initialized (TIM) deep model to address the image fusion problem in a challenging real-world scenario. Specifically, we first propose a constrained strategy to incorporate information from downstream tasks to guide the unsupervised learning process of image fusion. Within this framework, we then design an implicit search scheme to automatically discover compact architectures for our fusion model with high efficiency. In addition, a pretext meta initialization technique is introduced to leverage divergence fusion data to support fast adaptation for different kinds of image fusion tasks. Qualitative and quantitative experimental results on different categories of image fusion problems and related downstream tasks (e.g., visual enhancement and semantic understanding) substantiate the flexibility and effectiveness of our TIM. The source code will be available at https://github.com/LiuZhu-CV/TIMFusion.

Zhu Liu, Ying Liu

Word sense disambiguation (WSD), which aims to determine an appropriate sense for a target word given its context, is crucial for natural language understanding. Existing supervised methods treat WSD as a classification task and have achieved remarkable performance. However, they ignore uncertainty estimation (UE) in the real-world setting, where the data is always noisy and out of distribution. This paper extensively studies UE on the benchmark designed for WSD. Specifically, we first compare four uncertainty scores for a state-of-the-art WSD model and verify that the conventional predictive probabilities obtained at the end of the model are inadequate to quantify uncertainty. Then, we examine the capability of capturing data and model uncertainties by the model with the selected UE score on well-designed test scenarios and discover that the model reflects data uncertainty satisfactorily but underestimates model uncertainty. Furthermore, we explore numerous lexical properties that intrinsically affect data uncertainty and provide a detailed analysis of four critical aspects: the syntactic category, morphology, sense granularity, and semantic relations. The code is available at https://github.com/RyanLiut/WSD-UE.

Zhu Liu, Jinyuan Liu, Guanyao Wu et al.

In recent years, learning-based methods have achieved significant advancements in multi-exposure image fusion. However, two major stumbling blocks hinder the development, including pixel misalignment and inefficient inference. Reliance on aligned image pairs in existing methods causes susceptibility to artifacts due to device motion. Additionally, existing techniques often rely on handcrafted architectures with huge network engineering, resulting in redundant parameters, adversely impacting inference efficiency and flexibility. To mitigate these limitations, this study introduces an architecture search-based paradigm incorporating self-alignment and detail repletion modules for robust multi-exposure image fusion. Specifically, targeting the extreme discrepancy of exposure, we propose the self-alignment module, leveraging scene relighting to constrain the illumination degree for following alignment and feature extraction. Detail repletion is proposed to enhance the texture details of scenes. Additionally, incorporating a hardware-sensitive constraint, we present the fusion-oriented architecture search to explore compact and efficient networks for fusion. The proposed method outperforms various competitive schemes, achieving a noteworthy 3.19\% improvement in PSNR for general scenarios and an impressive 23.5\% enhancement in misaligned scenarios. Moreover, it significantly reduces inference time by 69.1\%. The code will be available at https://github.com/LiuZhu-CV/CRMEF.

Pan Mu, Zhu Liu, Yaohua Liu et al.

Video deraining is an important issue for outdoor vision systems and has been investigated extensively. However, designing optimal architectures by the aggregating model formation and data distribution is a challenging task for video deraining. In this paper, we develop a model-guided triple-level optimization framework to deduce network architecture with cooperating optimization and auto-searching mechanism, named Triple-level Model Inferred Cooperating Searching (TMICS), for dealing with various video rain circumstances. In particular, to mitigate the problem that existing methods cannot cover various rain streaks distribution, we first design a hyper-parameter optimization model about task variable and hyper-parameter. Based on the proposed optimization model, we design a collaborative structure for video deraining. This structure includes Dominant Network Architecture (DNA) and Companionate Network Architecture (CNA) that is cooperated by introducing an Attention-based Averaging Scheme (AAS). To better explore inter-frame information from videos, we introduce a macroscopic structure searching scheme that searches from Optical Flow Module (OFM) and Temporal Grouping Module (TGM) to help restore latent frame. In addition, we apply the differentiable neural architecture searching from a compact candidate set of task-specific operations to discover desirable rain streaks removal architectures automatically. Extensive experiments on various datasets demonstrate that our model shows significant improvements in fidelity and temporal consistency over the state-of-the-art works. Source code is available at https://github.com/vis-opt-group/TMICS.

Risheng Liu, Zhu Liu, Pan Mu et al.

In recent years, there has been a growing interest in combining learnable modules with numerical optimization to solve low-level vision tasks. However, most existing approaches focus on designing specialized schemes to generate image/feature propagation. There is a lack of unified consideration to construct propagative modules, provide theoretical analysis tools, and design effective learning mechanisms. To mitigate the above issues, this paper proposes a unified optimization-inspired learning framework to aggregate Generative, Discriminative, and Corrective (GDC for short) principles with strong generalization for diverse optimization models. Specifically, by introducing a general energy minimization model and formulating its descent direction from different viewpoints (i.e., in a generative manner, based on the discriminative metric and with optimality-based correction), we construct three propagative modules to effectively solve the optimization models with flexible combinations. We design two control mechanisms that provide the non-trivial theoretical guarantees for both fully- and partially-defined optimization formulations. Under the support of theoretical guarantees, we can introduce diverse architecture augmentation strategies such as normalization and search to ensure stable propagation with convergence and seamlessly integrate the suitable modules into the propagation respectively. Extensive experiments across varied low-level vision tasks validate the efficacy and adaptability of GDC. The codes are available at https://github.com/LiuZhu-CV/GDC-OptimizationLearning

Yifei Cao, Yu Liu, Guolong Wang et al.

Egocentric visual query localization is vital for embodied AI and VR/AR, yet remains challenging due to camera motion, viewpoint changes, and appearance variations. We present EAGLE, a novel framework that leverages episodic appearance- and geometry-aware memory to achieve unified 2D-3D visual query localization in egocentric vision. Inspired by avian memory consolidation, EAGLE synergistically integrates segmentation guided by an appearance-aware meta-learning memory (AMM), with tracking driven by a geometry-aware localization memory (GLM). This memory consolidation mechanism, through structured appearance and geometry memory banks, stores high-confidence retrieval samples, effectively supporting both long- and short-term modeling of target appearance variations. This enables precise contour delineation with robust spatial discrimination, leading to significantly improved retrieval accuracy. Furthermore, by integrating the VQL-2D output with a visual geometry grounded Transformer (VGGT), we achieve a efficient unification of 2D and 3D tasks, enabling rapid and accurate back-projection into 3D space. Our method achieves state-ofthe-art performance on the Ego4D-VQ benchmark.

Risheng Liu, Zhu Liu, Wei Yao et al.

This work focuses on addressing two major challenges in the context of large-scale nonconvex Bi-Level Optimization (BLO) problems, which are increasingly applied in machine learning due to their ability to model nested structures. These challenges involve ensuring computational efficiency and providing theoretical guarantees. While recent advances in scalable BLO algorithms have primarily relied on lower-level convexity simplification, our work specifically tackles large-scale BLO problems involving nonconvexity in both the upper and lower levels. We simultaneously address computational and theoretical challenges by introducing an innovative single-loop gradient-based algorithm, utilizing the Moreau envelope-based reformulation, and providing non-asymptotic convergence analysis for general nonconvex BLO problems. Notably, our algorithm relies solely on first-order gradient information, enhancing its practicality and efficiency, especially for large-scale BLO learning tasks. We validate our approach's effectiveness through experiments on various synthetic problems, two typical hyper-parameter learning tasks, and a real-world neural architecture search application, collectively demonstrating its superior performance.

Kangyang Luo, Yuzhuo Bai, Cheng Gao et al.

Knowledge Graph Completion (KGC), which aims to infer missing or incomplete facts, is a crucial task for KGs. However, integrating the vital structural information of KGs into Large Language Models (LLMs) and outputting predictions deterministically remains challenging. To address this, we propose a new method called GLTW, which encodes the structural information of KGs and merges it with LLMs to enhance KGC performance. Specifically, we introduce an improved Graph Transformer (iGT) that effectively encodes subgraphs with both local and global structural information and inherits the characteristics of language model, bypassing training from scratch. Also, we develop a subgraph-based multi-classification training objective, using all entities within KG as classification objects, to boost learning efficiency.Importantly, we combine iGT with an LLM that takes KG language prompts as input.Our extensive experiments on various KG datasets show that GLTW achieves significant performance gains compared to SOTA baselines.

Guofeng Cui, Pichao Wang, Yang Liu et al.

Large language models (LLMs) have shown great potential in natural language processing tasks, but their application to machine translation (MT) remains challenging due to pretraining on English-centric data and the complexity of reinforcement learning from human feedback (RLHF). Direct Preference Optimization (DPO) has emerged as a simpler and more efficient alternative, but its performance depends heavily on the quality of preference data. To address this, we propose Confidence-Reward driven Preference Optimization (CRPO), a novel method that combines reward scores with model confidence to improve data selection for fine-tuning. CRPO selects challenging sentence pairs where the model is uncertain or underperforms, leading to more effective learning. While primarily designed for LLMs, CRPO also generalizes to encoder-decoder models like NLLB, demonstrating its versatility. Empirical results show that CRPO outperforms existing methods such as RS-DPO, RSO and MBR score in both translation accuracy and data efficiency.

Chengzhou Li, Ping Guo, Guanchen Meng et al.

Object detection in sonar images is a key technology in underwater detection systems. Compared to natural images, sonar images contain fewer texture details and are more susceptible to noise, making it difficult for non-experts to distinguish subtle differences between classes. This leads to their inability to provide precise annotation data for sonar images. Therefore, designing effective object detection methods for sonar images with extremely limited labels is particularly important. To address this, we propose a teacher-student framework called RSOD, which aims to fully learn the characteristics of sonar images and develop a pseudo-label strategy suitable for these images to mitigate the impact of limited labels. First, RSOD calculates a reliability score by assessing the consistency of the teacher's predictions across different views. To leverage this score, we introduce an object mixed pseudo-label method to tackle the shortage of labeled data in sonar images. Finally, we optimize the performance of the student by implementing a reliability-guided adaptive constraint. By taking full advantage of unlabeled data, the student can perform well even in situations with extremely limited labels. Notably, on the UATD dataset, our method, using only 5% of labeled data, achieves results that can compete against those of our baseline algorithm trained on 100% labeled data. We also collected a new dataset to provide more valuable data for research in the field of sonar.

Zhisheng Zheng, Xiaohang Sun, Tuan Dinh et al.

End-to-end speech-to-speech translation (S2ST) systems typically struggle with a critical data bottleneck: the scarcity of parallel speech-to-speech corpora. To overcome this, we introduce RosettaSpeech, a novel zero-shot framework trained exclusively on monolingual speech-text data augmented by machine translation supervision. Unlike prior works that rely on complex cascaded pseudo-labeling, our approach strategically utilizes text as a semantic bridge during training to synthesize translation targets, thereby eliminating the need for parallel speech pairs while maintaining a direct, end-to-end inference pipeline. Empirical evaluations on the CVSS-C benchmark demonstrate that RosettaSpeech achieves state-of-the-art zero-shot performance, surpassing leading baselines by significant margins - achieving ASR-BLEU scores of 25.17 for German-to-English (+27% relative gain) and 29.86 for Spanish-to-English (+14%). Crucially, our model effectively preserves the source speaker's voice without ever seeing paired speech data. We further analyze the impact of data scaling and demonstrate the model's capability in many-to-one translation, offering a scalable solution for extending high-quality S2ST to "text-rich, speech-poor" languages.

Kangyang Luo, Yuzhuo Bai, Shuzheng Si et al. · tsinghua

Coreference Resolution (CR) is a critical task in Natural Language Processing (NLP). Current research faces a key dilemma: whether to further explore the potential of supervised neural methods based on small language models, whose detect-then-cluster pipeline still delivers top performance, or embrace the powerful capabilities of Large Language Models (LLMs). However, effectively combining their strengths remains underexplored. To this end, we propose \textbf{ImCoref-CeS}, a novel framework that integrates an enhanced supervised model with LLM-based reasoning. First, we present an improved CR method (\textbf{ImCoref}) to push the performance boundaries of the supervised neural method by introducing a lightweight bridging module to enhance long-text encoding capability, devising a biaffine scorer to comprehensively capture positional information, and invoking a hybrid mention regularization to improve training efficiency. Importantly, we employ an LLM acting as a multi-role Checker-Splitter agent to validate candidate mentions (filtering out invalid ones) and coreference results (splitting erroneous clusters) predicted by ImCoref. Extensive experiments demonstrate the effectiveness of ImCoref-CeS, which achieves superior performance compared to existing state-of-the-art (SOTA) methods.

Mingyu Liu, Zian Mao, Zhu Liu et al.

Automated experimentation with real time data analysis in scanning transmission electron microscopy (STEM) often require end-to-end framework. The four-dimensional scanning transmission electron microscopy (4D-STEM) with high-throughput data acquisition has been constrained by the critical bottleneck results from data preprocessing. Pervasive noise, beam center drift, and elliptical distortions during high-throughput acquisition inevitably corrupt diffraction patterns, systematically biasing quantitative measurements. Yet, conventional correction algorithms are often material-specific and fail to provide a robust, generalizable solution. In this work, we present 4D-PreNet, an end-to-end deep-learning pipeline that integrates attention-enhanced U-Net and ResNet architectures to simultaneously perform denoising, center correction, and elliptical distortion calibration. The network is trained on large, simulated datasets encompassing a wide range of noise levels, drift magnitudes, and distortion types, enabling it to generalize effectively to experimental data acquired under varying conditions. Quantitative evaluations demonstrate that our pipeline reduces mean squared error by up to 50% during denoising and achieves sub-pixel center localization in the center detection task, with average errors below 0.04 pixels. The outputs are bench-marked against traditional algorithms, highlighting improvements in both noise suppression and restoration of diffraction patterns, thereby facilitating high-throughput, reliable 4D-STEM real-time analysis for automated characterization.

Zhu Liu, Zhen Hu, Lei Dai et al.

Semantic map models represent meanings or functions as nodes in a graph constrained by the local connectivity hypothesis, with edges indicating their associations. Widely used in typological linguistics, these models compare interrelated meanings across languages. Traditionally built manually in a bottom-up manner, they are inefficient for large datasets and lack visualization and evaluation tools. This paper introduces XISM, an interactive tool based on our prior algorithm, which constructs semantic maps from user data via a top-down approach, displays candidate maps, and evaluates them using multiple metrics. Users can refine maps by editing edges, combining data-driven efficiency with expert knowledge. This human-in-the-loop design benefits both typologists and computational linguists. The system https://770103knev48.vicp.fun/ and a demonstration video https://youtu.be/S-wsVDF2HSI?si=1OrcF41tRznaifhZ are publicly available.

Xiang Fan, Xiaohang Sun, Kushan Thakkar et al.

Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectively capture the temporal dependencies and redundancies inherent in videos. To address this limitation, we introduce RefTok, a novel reference-based tokenization method capable of capturing complex temporal dynamics and contextual information. Our method encodes and decodes sets of frames conditioned on an unquantized reference frame. When decoded, RefTok preserves the continuity of motion and the appearance of objects across frames. For example, RefTok retains facial details despite head motion, reconstructs text correctly, preserves small patterns, and maintains the legibility of handwriting from the context. Across 4 video datasets (K600, UCF-101, BAIR Robot Pushing, and DAVIS), RefTok significantly outperforms current state-of-the-art tokenizers (Cosmos and MAGVIT) and improves all evaluated metrics (PSNR, SSIM, LPIPS) by an average of 36.7% at the same or higher compression ratios. When a video generation model is trained using RefTok's latents on the BAIR Robot Pushing task, the generations not only outperform MAGVIT-B but the larger MAGVIT-L, which has 4x more parameters, across all generation metrics by an average of 27.9%.

Zhu Liu, Ying Liu, KangYang Luo et al.

Lexico-semantic networks represent words as nodes and their semantic relatedness as edges. While such networks are traditionally constructed using embeddings from encoder-based models or static vectors, embeddings from decoder-only large language models (LLMs) remain underexplored. Unlike encoder models, LLMs are trained with a next-token prediction objective, which does not directly encode the meaning of the current token. In this paper, we construct lexico-semantic networks from the input embeddings of LLMs with varying parameter scales and conduct a comparative analysis of their global and local structures. Our results show that these networks exhibit small-world properties, characterized by high clustering and short path lengths. Moreover, larger LLMs yield more intricate networks with less small-world effects and longer paths, reflecting richer semantic structures and relations. We further validate our approach through analyses of common conceptual pairs, structured lexical relations derived from WordNet, and a cross-lingual semantic network for qualitative words.

Zhu Liu

Modern neural networks (NNs), trained on extensive raw sentence data, construct distributed representations by compressing individual words into dense, continuous, high-dimensional vectors. These representations are expected to capture multi-level lexical meaning. In this thesis, our objective is to examine the efficacy of distributed representations from NNs in encoding lexical meaning. Initially, we identify and formalize three levels of lexical semantics: \textit{local}, \textit{global}, and \textit{mixed} levels. Then, for each level, we evaluate language models by collecting or constructing multilingual datasets, leveraging various language models, and employing linguistic analysis theories. This thesis builds a bridge between computational models and lexical semantics, aiming to complement each other.

Zhu Liu, Jinyuan Liu, Guanyao Wu et al.

Recently, multi-modality scene perception tasks, e.g., image fusion and scene understanding, have attracted widespread attention for intelligent vision systems. However, early efforts always consider boosting a single task unilaterally and neglecting others, seldom investigating their underlying connections for joint promotion. To overcome these limitations, we establish the hierarchical dual tasks-driven deep model to bridge these tasks. Concretely, we firstly construct an image fusion module to fuse complementary characteristics and cascade dual task-related modules, including a discriminator for visual effects and a semantic network for feature measurement. We provide a bi-level perspective to formulate image fusion and follow-up downstream tasks. To incorporate distinct task-related responses for image fusion, we consider image fusion as a primary goal and dual modules as learnable constraints. Furthermore, we develop an efficient first-order approximation to compute corresponding gradients and present dynamic weighted aggregation to balance the gradients for fusion learning. Extensive experiments demonstrate the superiority of our method, which not only produces visually pleasant fused results but also realizes significant promotion for detection and segmentation than the state-of-the-art approaches.

Isabella Liu, Edward Yang, Jianyu Tao et al.

Traditional depth sensors generate accurate real world depth estimates that surpass even the most advanced learning approaches trained only on simulation domains. Since ground truth depth is readily available in the simulation domain but quite difficult to obtain in the real domain, we propose a method that leverages the best of both worlds. In this paper we present a new framework, ActiveZero, which is a mixed domain learning solution for active stereovision systems that requires no real world depth annotation. First, we demonstrate the transferability of our method to out-of-distribution real data by using a mixed domain learning strategy. In the simulation domain, we use a combination of supervised disparity loss and self-supervised losses on a shape primitives dataset. By contrast, in the real domain, we only use self-supervised losses on a dataset that is out-of-distribution from either training simulation data or test real data. Second, our method introduces a novel self-supervised loss called temporal IR reprojection to increase the robustness and accuracy of our reprojections in hard-to-perceive regions. Finally, we show how the method can be trained end-to-end and that each module is important for attaining the end result. Extensive qualitative and quantitative evaluations on real data demonstrate state of the art results that can even beat a commercial depth sensor.

Xinyu Dou, Cuijuan Liao, Hengqi Wang et al.

Nitrogen dioxide (NO2) is one of the most important atmospheric pollutants. However, current ground-level NO2 concentration data are lack of either high-resolution coverage or full coverage national wide, due to the poor quality of source data and the computing power of the models. To our knowledge, this study is the first to estimate the ground-level NO2 concentration in China with national coverage as well as relatively high spatiotemporal resolution (0.25 degree; daily intervals) over the newest past 6 years (2013-2018). We advanced a Random Forest model integrated K-means (RF-K) for the estimates with multi-source parameters. Besides meteorological parameters, satellite retrievals parameters, we also, for the first time, introduce socio-economic parameters to assess the impact by human activities. The results show that: (1) the RF-K model we developed shows better prediction performance than other models, with cross-validation R2 = 0.64 (MAPE = 34.78%). (2) The annual average concentration of NO2 in China showed a weak increasing trend . While in the economic zones such as Beijing-Tianjin-Hebei region, Yangtze River Delta, and Pearl River Delta, the NO2 concentration there even decreased or remained unchanged, especially in spring. Our dataset has verified that pollutant controlling targets have been achieved in these areas. With mapping daily nationwide ground-level NO2 concentrations, this study provides timely data with high quality for air quality management for China. We provide a universal model framework to quickly generate a timely national atmospheric pollutants concentration map with a high spatial-temporal resolution, based on improved machine learning methods.

Shervin Minaee, Zhu Liu

Automatic question-answering is a classical problem in natural language processing, which aims at designing systems that can automatically answer a question, in the same way as human does. In this work, we propose a deep learning based model for automatic question-answering. First the questions and answers are embedded using neural probabilistic modeling. Then a deep similarity neural network is trained to find the similarity score of a pair of answer and question. Then for each question, the best answer is found as the one with the highest similarity score. We first train this model on a large-scale public question-answering database, and then fine-tune it to transfer to the customer-care chat data. We have also tested our framework on a public question-answering database and achieved very good performance.

Yadong Mu, Zhu Liu

Similarity-based image hashing represents crucial technique for visual data storage reduction and expedited image search. Conventional hashing schemes typically feed hand-crafted features into hash functions, which separates the procedures of feature extraction and hash function learning. In this paper, we propose a novel algorithm that concurrently performs feature engineering and non-linear supervised hashing function learning. Our technical contributions in this paper are two-folds: 1) deep network optimization is often achieved by gradient propagation, which critically requires a smooth objective function. The discrete nature of hash codes makes them not amenable for gradient-based optimization. To address this issue, we propose an exponentiated hashing loss function and its bilinear smooth approximation. Effective gradient calculation and propagation are thereby enabled; 2) pre-training is an important trick in supervised deep learning. The impact of pre-training on the hash code quality has never been discussed in current deep hashing literature. We propose a pre-training scheme inspired by recent advance in deep network based image classification, and experimentally demonstrate its effectiveness. Comprehensive quantitative evaluations are conducted on several widely-used image benchmarks. On all benchmarks, our proposed deep hashing algorithm outperforms all state-of-the-art competitors by significant margins. In particular, our algorithm achieves a near-perfect 0.99 in terms of Hamming ranking accuracy with only 12 bits on MNIST, and a new record of 0.74 on the CIFAR10 dataset. In comparison, the best accuracies obtained on CIFAR10 by existing hashing algorithms without or with deep networks are known to be 0.36 and 0.58 respectively.

Marie-Jose Montpetit, Pablo Cesar, Maja Matijasevic et al.

The TV is dead motto of just a few years ago has been replaced by the prospect of Internet Protocol (IP) television experiences over converged networks to become one of the great technology opportunities in the next few years. As an introduction to the Special Issue on Smart, Social and Converged Television, this extended editorial intends to review the current IP television landscape in its many realizations: operator-based, over-the-top, and user generated. We will address new services like social TV and recommendation engines, dissemination including new paradigms built on peer to peer and content centric networks, as well as the all important quality of experience that challenges services and networks alike. But we intend to go further than just review the existing work by proposing areas for the future of television research. These include strategies to provide services that are more efficient in network and energy usage while being socially engaging, novel services that will provide consumers with a broader choice of content and devices, and metrics that will enable operators and users alike to define the level of service they require or that they are ready to provide. These topics are addressed in this survey paper that attempts to create a unifying framework to link them all together. Not only is television not dead, it is well alive, thriving and fostering innovation and this paper will hopefully prove it.