Rui Yu

Rui Yu, Dawei Du, Rodney LaLonde et al.

The goal of person search is to localize a target person from a gallery set of scene images, which is extremely challenging due to large scale variations, pose/viewpoint changes, and occlusions. In this paper, we propose the Cascade Occluded Attention Transformer (COAT) for end-to-end person search. Our three-stage cascade design focuses on detecting people in the first stage, while later stages simultaneously and progressively refine the representation for person detection and re-identification. At each stage the occluded attention transformer applies tighter intersection over union thresholds, forcing the network to learn coarse-to-fine pose/scale invariant features. Meanwhile, we calculate each detection's occluded attention to differentiate a person's tokens from other people or the background. In this way, we simulate the effect of other objects occluding a person of interest at the token-level. Through comprehensive experiments, we demonstrate the benefits of our method by achieving state-of-the-art performance on two benchmark datasets.

Rui Yu, Yifeng Li, Wenpeng Lu et al.

In natural language processing (NLP), the context of a word or sentence plays an essential role. Contextual information such as the semantic representation of a passage or historical dialogue forms an essential part of a conversation and a precise understanding of the present phrase or sentence. However, the standard attention mechanisms typically generate weights using query and key but ignore context, forming a Bi-Attention framework, despite their great success in modeling sequence alignment. This Bi-Attention mechanism does not explicitly model the interactions between the contexts, queries and keys of target sequences, missing important contextual information and resulting in poor attention performance. Accordingly, a novel and general triple-attention (Tri-Attention) framework expands the standard Bi-Attention mechanism and explicitly interacts query, key, and context by incorporating context as the third dimension in calculating relevance scores. Four variants of Tri-Attention are generated by expanding the two-dimensional vector-based additive, dot-product, scaled dot-product, and bilinear operations in Bi-Attention to the tensor operations for Tri-Attention. Extensive experiments on three NLP tasks demonstrate that Tri-Attention outperforms about 30 state-of-the-art non-attention, standard Bi-Attention, contextual Bi-Attention approaches and pretrained neural language models1.

Lirong Zheng, Yanshan Li, Rui Yu et al.

Image dehazing is crucial for reliable visual perception, yet it remains highly challenging under real-world non-uniform haze conditions. Although Transformer-based methods excel at capturing global context, their quadratic computational complexity hinders real-time deployment. To address this, we propose Fourier Receptance Weighted Key Value (Fourier-RWKV), a novel dehazing framework based on a Multi-State Perception paradigm. The model achieves comprehensive haze degradation modeling with linear complexity by synergistically integrating three distinct perceptual states: (1) Spatial-form Perception, realized through the Deformable Quad-directional Token Shift (DQ-Shift) operation, which dynamically adjusts receptive fields to accommodate local haze variations; (2) Frequency-domain Perception, implemented within the Fourier Mix block, which extends the core WKV attention mechanism of RWKV from the spatial domain to the Fourier domain, preserving the long-range dependencies essential for global haze estimation while mitigating spatial attenuation; (3) Semantic-relation Perception, facilitated by the Semantic Bridge Module (SBM), which utilizes Dynamic Semantic Kernel Fusion (DSK-Fusion) to precisely align encoder-decoder features and suppress artifacts. Extensive experiments on multiple benchmarks demonstrate that Fourier-RWKV delivers state-of-the-art performance across diverse haze scenarios while significantly reducing computational overhead, establishing a favorable trade-off between restoration quality and practical efficiency. Code is available at: https://github.com/Dilizlr/Fourier-RWKV.

Yuqing Shao, Yuchen Yang, Rui Yu et al.

End-to-end multi-object tracking (MOT) methods have recently achieved remarkable progress by unifying detection and association within a single framework. Despite their strong detection performance, these methods suffer from relatively low association accuracy. Through detailed analysis, we observe that object embeddings produced by the shared DETR architecture display excessively high inter-object similarity, as it emphasizes only category-level discrimination within single frames. In contrast, tracking requires instance-level distinction across frames with spatial and temporal continuity, for which current end-to-end approaches insufficiently optimize object embeddings. To address this, we introduce FDTA (From Detection to Association), an explicit feature refinement framework that enhances object discriminativeness across three complementary perspectives. Specifically, we introduce a Spatial Adapter (SA) to integrate depth-aware cues for spatial continuity, a Temporal Adapter (TA) to aggregate historical information for temporal dependencies, and an Identity Adapter (IA) to leverage quality-aware contrastive learning for instance-level separability. Extensive experiments demonstrate that FDTA achieves state-of-the-art performance on multiple challenging MOT benchmarks, including DanceTrack, SportsMOT, and BFT, highlighting the effectiveness of our proposed discriminative embedding enhancement strategy. The code is available at https://github.com/Spongebobbbbbbbb/FDTA.

Rui Yu, Jiachen Liu, Zihan Zhou et al.

In various applications, such as robotic navigation and remote visual assistance, expanding the field of view (FOV) of the camera proves beneficial for enhancing environmental perception. Unlike image outpainting techniques aimed solely at generating aesthetically pleasing visuals, these applications demand an extended view that faithfully represents the scene. To achieve this, we formulate a new problem of faithful FOV extrapolation that utilizes a set of pre-captured images as prior knowledge of the scene. To address this problem, we present a simple yet effective solution called NeRF-Enhanced Outpainting (NEO) that uses extended-FOV images generated through NeRF to train a scene-specific image outpainting model. To assess the performance of NEO, we conduct comprehensive evaluations on three photorealistic datasets and one real-world dataset. Extensive experiments on the benchmark datasets showcase the robustness and potential of our method in addressing this challenge. We believe our work lays a strong foundation for future exploration within the research community.

Haoyu Zhao, Wenhui Dong, Rui Yu et al.

The task of single-source domain generalization (SDG) in medical image segmentation is crucial due to frequent domain shifts in clinical image datasets. To address the challenge of poor generalization across different domains, we introduce a Plug-and-Play module for data augmentation called MoreStyle. MoreStyle diversifies image styles by relaxing low-frequency constraints in Fourier space, guiding the image reconstruction network. With the help of adversarial learning, MoreStyle further expands the style range and pinpoints the most intricate style combinations within latent features. To handle significant style variations, we introduce an uncertainty-weighted loss. This loss emphasizes hard-to-classify pixels resulting only from style shifts while mitigating true hard-to-classify pixels in both MoreStyle-generated and original images. Extensive experiments on two widely used benchmarks demonstrate that the proposed MoreStyle effectively helps to achieve good domain generalization ability, and has the potential to further boost the performance of some state-of-the-art SDG methods. Source code is available at https://github.com/zhaohaoyu376/morestyle.

Rui Yu, Runkai Zhao, Jiagen Li et al.

The LiDAR-based 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving and robotic navigation systems. To enhance the accuracy of point cloud detection, integrating global context for visual understanding improves the point clouds ability to grasp overall spatial information. However, many existing LiDAR detection models depend on intricate feature transformation and extraction processes, leading to poor real-time performance and high resource consumption, which limits their practical effectiveness. In this work, we propose a Faster LiDAR 3D object detection framework, called FASD, which implements heterogeneous model distillation by adaptively uniform cross-model voxel features. We aim to distill the transformer's capacity for high-performance sequence modeling into Mamba models with low FLOPs, achieving a significant improvement in accuracy through knowledge transfer. Specifically, Dynamic Voxel Group and Adaptive Attention strategies are integrated into the sparse backbone, creating a robust teacher model with scale-adaptive attention for effective global visual context modeling. Following feature alignment with the Adapter, we transfer knowledge from the Transformer to the Mamba through latent space feature supervision and span-head distillation, resulting in improved performance and an efficient student model. We evaluated the framework on the Waymo and nuScenes datasets, achieving a 4x reduction in resource consumption and a 1-2\% performance improvement over the current SoTA methods.

Jiachen Liu, Rui Yu, Sili Chen et al.

3D plane reconstruction from a single image is a crucial yet challenging topic in 3D computer vision. Previous state-of-the-art (SOTA) methods have focused on training their system on a single dataset from either indoor or outdoor domain, limiting their generalizability across diverse testing data. In this work, we introduce a novel framework dubbed ZeroPlane, a Transformer-based model targeting zero-shot 3D plane detection and reconstruction from a single image, over diverse domains and environments. To enable data-driven models across multiple domains, we have curated a large-scale planar benchmark, comprising over 14 datasets and 560,000 high-resolution, dense planar annotations for diverse indoor and outdoor scenes. To address the challenge of achieving desirable planar geometry on multi-dataset training, we propose to disentangle the representation of plane normal and offset, and employ an exemplar-guided, classification-then-regression paradigm to learn plane and offset respectively. Additionally, we employ advanced backbones as image encoder, and present an effective pixel-geometry-enhanced plane embedding module to further facilitate planar reconstruction. Extensive experiments across multiple zero-shot evaluation datasets have demonstrated that our approach significantly outperforms previous methods on both reconstruction accuracy and generalizability, especially over in-the-wild data. Our code and data are available at: https://github.com/jcliu0428/ZeroPlane.

Rui Yu, Runkai Zhao, Cong Nie et al.

Accurate and robust LiDAR 3D object detection is essential for comprehensive scene understanding in autonomous driving. Despite its importance, LiDAR detection performance is limited by inherent constraints of point cloud data, particularly under conditions of extended distances and occlusions. Recently, temporal aggregation has been proven to significantly enhance detection accuracy by fusing multi-frame viewpoint information and enriching the spatial representation of objects. In this work, we introduce a novel LiDAR 3D object detection framework, namely LiSTM, to facilitate spatial-temporal feature learning with cross-frame motion forecasting information. We aim to improve the spatial-temporal interpretation capabilities of the LiDAR detector by incorporating a dynamic prior, generated from a non-learnable motion estimation model. Specifically, Motion-Guided Feature Aggregation (MGFA) is proposed to utilize the object trajectory from previous and future motion states to model spatial-temporal correlations into gaussian heatmap over a driving sequence. This motion-based heatmap then guides the temporal feature fusion, enriching the proposed object features. Moreover, we design a Dual Correlation Weighting Module (DCWM) that effectively facilitates the interaction between past and prospective frames through scene- and channel-wise feature abstraction. In the end, a cascade cross-attention-based decoder is employed to refine the 3D prediction. We have conducted experiments on the Waymo and nuScenes datasets to demonstrate that the proposed framework achieves superior 3D detection performance with effective spatial-temporal feature learning.

Haoyu Zhao, Yuliang Gu, Zhou Zhao et al.

In clinical examinations and diagnoses, low-dose computed tomography (LDCT) is crucial for minimizing health risks compared with normal-dose computed tomography (NDCT). However, reducing the radiation dose compromises the signal-to-noise ratio, leading to degraded quality of CT images. To address this, we analyze LDCT denoising task based on experimental results from the frequency perspective, and then introduce a novel self-supervised CT image denoising method called WIA-LD2ND, only using NDCT data. The proposed WIA-LD2ND comprises two modules: Wavelet-based Image Alignment (WIA) and Frequency-Aware Multi-scale Loss (FAM). First, WIA is introduced to align NDCT with LDCT by mainly adding noise to the high-frequency components, which is the main difference between LDCT and NDCT. Second, to better capture high-frequency components and detailed information, Frequency-Aware Multi-scale Loss (FAM) is proposed by effectively utilizing multi-scale feature space. Extensive experiments on two public LDCT denoising datasets demonstrate that our WIA-LD2ND, only uses NDCT, outperforms existing several state-of-the-art weakly-supervised and self-supervised methods. Source code is available at https://github.com/zhaohaoyu376/WI-LD2ND.

Yucen Wang, Rui Yu, Fengming Zhang et al.

Post-training Vision-Language-Action (VLA) models via reinforcement learning (RL) in learned world models has emerged as an effective strategy to adapt to new tasks without costly real-world interactions. However, while using imagined trajectories reduces the sample complexity of policy training, existing methods still heavily rely on task-specific data to fine-tune both the world and reward models, fundamentally limiting their scalability to unseen tasks. To overcome this, we argue that world and reward models should capture transferable physical priors that enable zero-shot inference. We propose RAW-Dream (Reinforcing VLAs in task-Agnostic World Dreams), a new paradigm that completely disentangles world model learning from downstream task dependencies. RAW-Dream utilizes a world model pre-trained on diverse task-free behaviors for predicting future rollouts, and an off-the-shelf Vision-Language Model (VLM) for reward generation. Because both components are task-agnostic, VLAs can be readily finetuned for any new task entirely within this zero-shot imagination. Furthermore, to mitigate world model hallucinations, we introduce a dual-noise verification mechanism to filter out unreliable rollouts. Extensive experiments across simulation and real-world settings demonstrate consistent performance gains, proving that generalized physical priors can effectively substitute for costly task-dependent data, offering a highly scalable roadmap for VLA adaptation.

Zhipeng Yao, Rui Yu, Guisong Chang et al.

Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fixed momentum coefficients inherently distort the balance between bias and variance, leading to skewed or suboptimal parameter updates. To address this, we propose SGDF (SGD with Filter), an optimizer inspired by the principles of Optimal Linear Filtering. SGDF computes an online, time-varying gain to dynamically refine gradient estimation by minimizing the mean-squared error, thereby achieving an optimal trade-off between noise suppression and signal preservation. Furthermore, our approach could extend to other optimizers, showcasing its broad applicability to optimization frameworks. Extensive experiments across diverse architectures and benchmarks demonstrate SGDF surpasses conventional momentum methods and achieves performance on par with or surpassing state-of-the-art optimizers.

Zhipeng Yao, Dazhou Li, Zitong Zhang et al.

Diffusion models have achieved remarkable success, yet their training remains inefficient due to a severe optimization bottleneck, which we term Representation Degradation. As noise levels increase, the outputs of the trained model exhibit progressive structural distortion, which can destabilize training and impair generation quality. Our analysis suggests that this instability is driven by mismatched target recoverability, which is associated with Neural Tangent Kernel (NTK) spectral weakening and effective low-rank behavior. To address this, we propose Elucidated Representation Diffusion (ERD), a plug-and-play framework that dynamically reallocates optimization effort according to effective recoverability. By stabilizing representation learning without external supervision, ERD accelerates convergence and achieves strong empirical performance across diffusion backbones.

Zhipeng Yao, Rui Yu, Guisong Chang et al.

In deep learning, stochastic gradient descent (SGD) and its momentum-based variants are widely used for optimization. However, the internal dynamics of these methods remain underexplored. In this paper, we analyze gradient behavior through a signal processing lens, isolating key factors that influence gradient updates and revealing a critical limitation: momentum techniques lack the flexibility to adequately balance bias and variance components in gradients, resulting in gradient estimation inaccuracies. To address this issue, we introduce a novel method SGDF (SGD with Filter) based on Wiener Filter principles, which derives an optimal time-varying gain to refine gradient updates by minimizing the mean square error in gradient estimation. This method yields an optimal first-order gradient estimate, effectively balancing noise reduction and signal preservation. Furthermore, our approach could extend to adaptive optimizers, enhancing their generalization potential. Empirical results show that SGDF achieves superior convergence and generalization compared to traditional momentum methods, and performs competitively with state-of-the-art optimizers.

Rui Yu, Xianghang Zhang, Runkai Zhao et al.

End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive focus on ego-vehicle status as their sole learning objectives and lacks of planning-oriented understanding, which limits the robustness of the overall decision-making prcocess. In this work, we introduce DistillDrive, an end-to-end knowledge distillation-based autonomous driving model that leverages diversified instance imitation to enhance multi-mode motion feature learning. Specifically, we employ a planning model based on structured scene representations as the teacher model, leveraging its diversified planning instances as multi-objective learning targets for the end-to-end model. Moreover, we incorporate reinforcement learning to enhance the optimization of state-to-decision mappings, while utilizing generative modeling to construct planning-oriented instances, fostering intricate interactions within the latent space. We validate our model on the nuScenes and NAVSIM datasets, achieving a 50\% reduction in collision rate and a 3-point improvement in closed-loop performance compared to the baseline model. Code and model are publicly available at https://github.com/YuruiAI/DistillDrive

Lirong Zheng, Yanshan Li, Rui Yu et al.

Transformer-based models exhibit strong global modeling capabilities in single-image dehazing, but their high computational cost limits real-time applicability. Existing methods predominantly rely on spatial-domain features to capture long-range dependencies, which are computationally expensive and often inadequate under complex haze conditions. While some approaches introduce frequency-domain cues, the weak coupling between spatial and frequency branches limits the overall performance. To overcome these limitations, we propose the Dark Channel Guided Frequency-aware Dehazing Network (DGFDNet), a novel dual-domain framework that performs physically guided degradation alignment across spatial and frequency domains. At its core, the DGFDBlock comprises two key modules: 1) the Haze-Aware Frequency Modulator (HAFM), which generates a pixel-level haze confidence map from dark channel priors to adaptively enhance haze-relevant frequency components, thereby achieving global degradation-aware spectral modulation; 2) the Multi-level Gating Aggregation Module (MGAM), which fuses multi-scale features through diverse convolutional kernels and hybrid gating mechanisms to recover fine structural details. Additionally, a Prior Correction Guidance Branch (PCGB) incorporates a closed-loop feedback mechanism, enabling iterative refinement of the prior by intermediate dehazed features and significantly improving haze localization accuracy, especially in challenging outdoor scenes. Extensive experiments on four benchmark haze datasets demonstrate that DGFDNet achieves state-of-the-art performance with superior robustness and real-time efficiency. Code is available at: https://github.com/Dilizlr/DGFDNet.

Rui Yu, Tianyi Wang, Ruixia Liu et al.

Efficient question-answering (QA) over extensive scientific literature is essential for evidence-based engineering decision-making. Retrieval-augmented generation (RAG) is increasingly applied to question-answering over long academic papers, where accurate evidence allocation under a fixed token budget is critical. However, existing approaches flatten papers into unstructured chunks, destroying the native hierarchical structure and forcing retrieval to operate in a disordered space. This produces fragmented contexts, misallocates tokens to non-evidential regions, and increases the reasoning burden for downstream language models.To address these issues, we propose SF-RAG, an RAG framework that treats the native hierarchical structure of academic papers as a low-entropy retrieval prior.SF-RAG first inherits the native hierarchy to construct a structure-fidelity index, which prevents entropy increase at the source.It then designs a path-guided retrieval mechanism that aligns query semantics to relevant sections and selects high relevance root-to-leaf paths under a fixed token budget, yielding compact, coherent, and low-entropy retrieval contexts.In contrast to existing RAG approaches, SF-RAG avoids entropy increase caused by destructive preprocessing and provides a native low-entropy structural basis for subsequent retrieval. We further introduce entropy-based structural diagnostics to quantify retrieval fragmentation and evidence allocation accuracy.Evaluations across three QA benchmarks show that SF-RAG significantly reduces retrieval fragmentation and improves evidence allocation. These structural benefits drive superior answer quality, establishing a scalable foundation for intelligent engineering document systems and future applications in technical specifications.

Baiting Chen, Tong Zhu, Rui Yu et al.

Aligning large language models (LLMs) with human preferences is inherently multi-objective: different users and evaluation criteria impose heterogeneous and often conflicting requirements on model outputs. We propose CAGE (Common-Agency Games for Alignment), a training-free, game-theoretic framework for multi-objective test-time alignment. CAGE models alignment objectives as strategic principals that allocate token-level incentives to a shared LLM, inducing an equilibrium policy that captures the joint effect of competing objectives. We develop an efficient algorithm based on equilibrium problems with equilibrium constraints (EPEC) to compute this equilibrium, and establish theoretical guarantees including existence and uniqueness of the equilibrium policy, convergence and stability of the algorithm, and no-regret learning dynamics. Empirically, CAGE enables flexible and fine-grained trade-offs across objectives at inference time, consistently outperforming existing test-time alignment methods while requiring no retraining. It further supports weak-to-strong generalization, making multi-objective alignment practical in resource-constrained settings.

Bing Han, Chen Zhu, Dong Han et al.

Vision-driven field monitoring is central to digital agriculture, yet models built on general-domain pretrained backbones often fail to generalize across tasks, owing to the interaction of fine, variable canopy structures with fluctuating field conditions. We present FoMo4Wheat, one of the first crop-domain vision foundation model pretrained with self-supervision on ImAg4Wheat, the largest and most diverse wheat image dataset to date (2.5 million high-resolution images collected over a decade at 30 global sites, spanning >2,000 genotypes and >500 environmental conditions). This wheat-specific pretraining yields representations that are robust for wheat and transferable to other crops and weeds. Across ten in-field vision tasks at canopy and organ levels, FoMo4Wheat models consistently outperform state-of-the-art models pretrained on general-domain dataset. These results demonstrate the value of crop-specific foundation models for reliable in-field perception and chart a path toward a universal crop foundation model with cross-species and cross-task capabilities. FoMo4Wheat models and the ImAg4Wheat dataset are publicly available online: https://github.com/PheniX-Lab/FoMo4Wheat and https://huggingface.co/PheniX-Lab/FoMo4Wheat. The demonstration website is: https://fomo4wheat.phenix-lab.com/.

Zhichuan Wang, Yang Zhou, Zhe Liu et al.

Open-set 3D object retrieval (3DOR) is an emerging task aiming to retrieve 3D objects of unseen categories beyond the training set. Existing methods typically utilize all modalities (i.e., voxels, point clouds, multi-view images) and train specific backbones before fusion. However, they still struggle to produce generalized representations due to insufficient 3D training data. Being contrastively pre-trained on web-scale image-text pairs, CLIP inherently produces generalized representations for a wide range of downstream tasks. Building upon it, we present a simple yet effective framework named Describe, Adapt and Combine (DAC) by taking only multi-view images for open-set 3DOR. DAC innovatively synergizes a CLIP model with a multi-modal large language model (MLLM) to learn generalized 3D representations, where the MLLM is used for dual purposes. First, it describes the seen category information to align with CLIP's training objective for adaptation during training. Second, it provides external hints about unknown objects complementary to visual cues during inference. To improve the synergy, we introduce an Additive-Bias Low-Rank adaptation (AB-LoRA), which alleviates overfitting and further enhances the generalization to unseen categories. With only multi-view images, DAC significantly surpasses prior arts by an average of +10.01\% mAP on four open-set 3DOR datasets. Moreover, its generalization is also validated on image-based and cross-dataset setups. Code is available at https://github.com/wangzhichuan123/DAC.

Tingfeng Huang, Weijia Kong, Yuxuan Cheng et al.

In unsupervised image anomaly detection, reconstruction methods aim to train models to capture normal patterns comprehensively for normal data reconstruction. Yet, these models sometimes retain unintended reconstruction capacity for anomalous regions during inference, leading to missed detections. To mitigate this issue, existing works perturb normal samples in a sample-agnostic manner, uniformly adding noise across spatial locations before reconstructing the original. Despite promising results, they disregard the fact that foreground locations are inherently more critical for robust reconstruction. Motivated by this, we present a novel reconstruction framework named Attention-Guided Perturbation Network (AGPNet) for industrial anomaly detection. Its core idea is to add perturbations guided by a sample-aware attention mask to improve the learning of invariant normal patterns at important locations. AGPNet consists of two branches, \ie, a reconstruction branch and an auxiliary attention-based perturbation one. The reconstruction branch learns to reconstruct normal samples, while the auxiliary one aims to produce attention masks to guide the noise perturbation process for normal samples. By perturbing more aggressively at those important regions, we encourage the reconstruction branch to learn inherent normal patterns both comprehensively and robustly. Extensive experiments are conducted on several popular benchmarks covering MVTec-AD, VisA, and MVTec-3D, and show that AGPNet consistently obtains leading anomaly detection performance across a variety of setups, including few-shot, one-class, and multi-class ones.

Bin Tan, Rui Yu, Yujun Shen et al.

This paper presents PlanarSplatting, an ultra-fast and accurate surface reconstruction approach for multiview indoor images. We take the 3D planes as the main objective due to their compactness and structural expressiveness in indoor scenes, and develop an explicit optimization framework that learns to fit the expected surface of indoor scenes by splatting the 3D planes into 2.5D depth and normal maps. As our PlanarSplatting operates directly on the 3D plane primitives, it eliminates the dependencies on 2D/3D plane detection and plane matching and tracking for planar surface reconstruction. Furthermore, the essential merits of plane-based representation plus CUDA-based implementation of planar splatting functions, PlanarSplatting reconstructs an indoor scene in 3 minutes while having significantly better geometric accuracy. Thanks to our ultra-fast reconstruction speed, the largest quantitative evaluation on the ScanNet and ScanNet++ datasets over hundreds of scenes clearly demonstrated the advantages of our method. We believe that our accurate and ultrafast planar surface reconstruction method will be applied in the structured data curation for surface reconstruction in the future. The code of our CUDA implementation will be publicly available. Project page: https://icetttb.github.io/PlanarSplatting/

Yucen Wang, Rui Yu, Shenghua Wan et al.

Foundation Models (FMs) and World Models (WMs) offer complementary strengths in task generalization at different levels. In this work, we propose FOUNDER, a framework that integrates the generalizable knowledge embedded in FMs with the dynamic modeling capabilities of WMs to enable open-ended task solving in embodied environments in a reward-free manner. We learn a mapping function that grounds FM representations in the WM state space, effectively inferring the agent's physical states in the world simulator from external observations. This mapping enables the learning of a goal-conditioned policy through imagination during behavior learning, with the mapped task serving as the goal state. Our method leverages the predicted temporal distance to the goal state as an informative reward signal. FOUNDER demonstrates superior performance on various multi-task offline visual control benchmarks, excelling in capturing the deep-level semantics of tasks specified by text or videos, particularly in scenarios involving complex observations or domain gaps where prior methods struggle. The consistency of our learned reward function with the ground-truth reward is also empirically validated. Our project website is https://sites.google.com/view/founder-rl.

Rui Yu, Shenghua Wan, Yucen Wang et al.

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when the agent maximizes the accumulated reward, it also fulfills the task designer's intentions. Recently, significant attention from both academic and industrial researchers has focused on developing reward models that not only align closely with the true objectives but also facilitate policy optimization. In this survey, we provide a comprehensive review of reward modeling techniques within the deep RL literature. We begin by outlining the background and preliminaries in reward modeling. Next, we present an overview of recent reward modeling approaches, categorizing them based on the source, the mechanism, and the learning paradigm. Building on this understanding, we discuss various applications of these reward modeling techniques and review methods for evaluating reward models. Finally, we conclude by highlighting promising research directions in reward modeling. Altogether, this survey includes both established and emerging methods, filling the vacancy of a systematic review of reward models in current literature.

Zerui Zhang, Zhichao Sun, Zelong Liu et al.

Medical anomaly detection is a critical research area aimed at recognizing abnormal images to aid in diagnosis.Most existing methods adopt synthetic anomalies and image restoration on normal samples to detect anomaly. The unlabeled data consisting of both normal and abnormal data is not well explored. We introduce a novel Spatial-aware Attention Generative Adversarial Network (SAGAN) for one-class semi-supervised generation of health images.Our core insight is the utilization of position encoding and attention to accurately focus on restoring abnormal regions and preserving normal regions. To fully utilize the unlabelled data, SAGAN relaxes the cyclic consistency requirement of the existing unpaired image-to-image conversion methods, and generates high-quality health images corresponding to unlabeled data, guided by the reconstruction of normal images and restoration of pseudo-anomaly images.Subsequently, the discrepancy between the generated healthy image and the original image is utilized as an anomaly score.Extensive experiments on three medical datasets demonstrate that the proposed SAGAN outperforms the state-of-the-art methods.

Jiagen Li, Rui Yu, Huihao Huang et al.

Multimodal Emotion Recognition in Conversations (MERC) identifies emotional states across text, audio and video, which is essential for intelligent dialogue systems and opinion analysis. Existing methods emphasize heterogeneous modal fusion directly for cross-modal integration, but often suffer from disorientation in multimodal learning due to modal heterogeneity and lack of instructive guidance. In this work, we propose SUMMER, a novel heterogeneous multimodal integration framework leveraging Mixture of Experts with Hierarchical Cross-modal Fusion and Interactive Knowledge Distillation. Key components include a Sparse Dynamic Mixture of Experts (SDMoE) for capturing dynamic token-wise interactions, a Hierarchical Cross-Modal Fusion (HCMF) for effective fusion of heterogeneous modalities, and Interactive Knowledge Distillation (IKD), which uses a pre-trained unimodal teacher to guide multimodal fusion in latent and logit spaces. Experiments on IEMOCAP and MELD show SUMMER outperforms state-of-the-art methods, particularly in recognizing minority and semantically similar emotions.

Jiachen Liu, Yuan Xue, Haomiao Ni et al.

Generating realistic building layouts for automatic building design has been studied in both the computer vision and architecture domains. Traditional approaches from the architecture domain, which are based on optimization techniques or heuristic design guidelines, can synthesize desirable layouts, but usually require post-processing and involve human interaction in the design pipeline, making them costly and timeconsuming. The advent of deep generative models has significantly improved the fidelity and diversity of the generated architecture layouts, reducing the workload by designers and making the process much more efficient. In this paper, we conduct a comprehensive review of three major research topics of architecture layout design and generation: floorplan layout generation, scene layout synthesis, and generation of some other formats of building layouts. For each topic, we present an overview of the leading paradigms, categorized either by research domains (architecture or machine learning) or by user input conditions or constraints. We then introduce the commonly-adopted benchmark datasets that are used to verify the effectiveness of the methods, as well as the corresponding evaluation metrics. Finally, we identify the well-solved problems and limitations of existing approaches, then propose new perspectives as promising directions for future research in this important research area. A project associated with this survey to maintain the resources is available at awesome-building-layout-generation.

Qiming Zhu, Shunian Chen, Rui Yu et al.

Long-horizon agents often compress interaction histories into write-time summaries. This creates a fundamental write-before-query barrier: compression decisions are made before the system knows what a future query will hinge on. As a result, summaries can cause unverifiable omissions -- decisive constraints (e.g., allergies) may be dropped, leaving the agent unable to justify an answer with traceable evidence. Retaining raw logs restores an authoritative source of truth, but grounding on raw logs by default is expensive: many queries are answerable from summaries, yet raw grounding still requires processing far longer contexts, inflating token consumption and latency. We propose TierMem, a provenance-linked framework that casts retrieval as an inference-time evidence allocation problem. TierMem uses a two-tier memory hierarchy to answer with the cheapest sufficient evidence: it queries a fast summary index by default, and a runtime sufficiency router Escalates to an immutable raw-log store only when summary evidence is insufficient. TierMem then writes back verified findings as new summary units linked to their raw sources. On LoCoMo, TierMem achieves 0.851 accuracy (vs.0.873 raw-only) while reducing input tokens by 54.1\% and latency by 60.7%.

Zichong Wang, Zhipeng Yin, Liping Yang et al.

Ensuring fairness in Graph Neural Networks is fundamental to promoting trustworthy and socially responsible machine learning systems. In response, numerous fair graph learning methods have been proposed in recent years. However, most of them assume full access to demographic information, a requirement rarely met in practice due to privacy, legal, or regulatory restrictions. To this end, this paper introduces a novel fair graph learning framework that mitigates bias in graph learning under limited demographic information. Specifically, we propose a mechanism guided by partial demographic data to generate proxies for demographic information and design a strategy that enforces consistent node embeddings across demographic groups. In addition, we develop an adaptive confidence strategy that dynamically adjusts each node's contribution to fairness and utility based on prediction confidence. We further provide theoretical analysis demonstrating that our framework, FairGLite, achieves provable upper bounds on group fairness metrics, offering formal guarantees for bias mitigation. Through extensive experiments on multiple datasets and fair graph learning frameworks, we demonstrate the framework's effectiveness in both mitigating bias and maintaining model utility.

Jie Hao, Rui Yu, Wei Zhang et al.

Effective data selection is essential for pretraining large language models (LLMs), enhancing efficiency and improving generalization to downstream tasks. However, existing approaches often require leveraging external pretrained models, making it difficult to disentangle the effects of data selection from those of the external pretrained models. In addition, they often overlook the long-term impact of selected data if the model is trained to convergence, primarily due to the prohibitive cost of full-scale LLM pretraining. In this paper, we introduce BLISS (\textbf{B}ileve\textbf{L} \textbf{I}nfluence \textbf{S}coring method for data \textbf{S}election): a lightweight data selection method that operates entirely \emph{from scratch}, without relying on any external pretrained oracle models, while explicitly accounting for the long-term impact of selected data. BLISS leverages a small proxy model as a surrogate for the LLM and employs a score model to estimate the long-term influence of training samples if the proxy model is trained to convergence. We formulate data selection as a bilevel optimization problem, where the upper-level objective optimizes the score model to assign importance weights to training samples, ensuring that minimizing the lower-level objective (i.e., training the proxy model over the weighted training loss until convergence) leads to best validation performance. Once optimized, the trained score model predicts influence scores for the dataset, enabling efficient selection of high-quality samples for LLM pretraining. We validate BLISS by pretraining 410M/1B/2.8B Pythia and LLaMA-0.5B models on selected subsets of the C4 dataset. Notably, under the 1B model setting, BLISS achieves $1.7\times$ speedup in reaching the same performance as the state-of-the-art method, demonstrating superior performance across multiple downstream tasks.

Zitong Zhang, Suranjan Gautam, Rui Yu

Generating immersive 360° indoor panoramas from 2D top-down views has applications in virtual reality, interior design, real estate, and robotics. This task is challenging due to the lack of explicit 3D structure and the need for geometric consistency and photorealism. We propose Top2Pano, an end-to-end model for synthesizing realistic indoor panoramas from top-down views. Our method estimates volumetric occupancy to infer 3D structures, then uses volumetric rendering to generate coarse color and depth panoramas. These guide a diffusion-based refinement stage using ControlNet, enhancing realism and structural fidelity. Evaluations on two datasets show Top2Pano outperforms baselines, effectively reconstructing geometry, occlusions, and spatial arrangements. It also generalizes well, producing high-quality panoramas from schematic floorplans. Our results highlight Top2Pano's potential in bridging top-down views with immersive indoor synthesis.

Jiaxin Song, Yixu Wang, Jie Li et al.

Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them increasingly susceptible to jailbreak attacks. However, lacking well-defined attack objectives, existing jailbreak methods often struggle with gradient-based strategies prone to local optima and lacking precise directional guidance, and typically decouple visual and textual modalities, thereby limiting their effectiveness by neglecting crucial cross-modal interactions. Inspired by the Eliciting Latent Knowledge (ELK) framework, we posit that VLMs encode safety-relevant information within their internal fusion-layer representations, revealing an implicit safety decision boundary in the latent space. This motivates exploiting boundary to steer model behavior. Accordingly, we propose JailBound, a novel latent space jailbreak framework comprising two stages: (1) Safety Boundary Probing, which addresses the guidance issue by approximating decision boundary within fusion layer's latent space, thereby identifying optimal perturbation directions towards the target region; and (2) Safety Boundary Crossing, which overcomes the limitations of decoupled approaches by jointly optimizing adversarial perturbations across both image and text inputs. This latter stage employs an innovative mechanism to steer the model's internal state towards policy-violating outputs while maintaining cross-modal semantic consistency. Extensive experiments on six diverse VLMs demonstrate JailBound's efficacy, achieves 94.32% white-box and 67.28% black-box attack success averagely, which are 6.17% and 21.13% higher than SOTA methods, respectively. Our findings expose a overlooked safety risk in VLMs and highlight the urgent need for more robust defenses. Warning: This paper contains potentially sensitive, harmful and offensive content.

Yu Zhang, Rui Yu, Zhipeng Yao et al.

The Mean Square Error (MSE) is commonly utilized to estimate the solution of the optimal value function in the vast majority of offline reinforcement learning (RL) models and has achieved outstanding performance. However, we find that its principle can lead to overestimation phenomenon for the value function. In this paper, we first theoretically analyze overestimation phenomenon led by MSE and provide the theoretical upper bound of the overestimated error. Furthermore, to address it, we propose a novel Bellman underestimated operator to counteract overestimation phenomenon and then prove its contraction characteristics. At last, we propose the offline RL algorithm based on underestimated operator and diffusion policy model. Extensive experimental results on D4RL tasks show that our method can outperform state-of-the-art offline RL algorithms, which demonstrates that our theoretical analysis and underestimation way are effective for offline RL tasks.

Kaiqun Wu, Xiaoling Jiang, Rui Yu et al.

Image compression has been applied in the fields of image storage and video broadcasting. However, it's formidably tough to distinguish the subtle quality differences between those distorted images generated by different algorithms. In this paper, we propose a new image quality assessment framework to decide which image is better in an image group. To capture the subtle differences, a fine-grained network is adopted to acquire multi-scale features. Subsequently, we design a cross subtract block for separating and gathering the information within positive and negative image pairs. Enabling image comparison in feature space. After that, a progressive feature fusion block is designed, which fuses multi-scale features in a novel progressive way. Hierarchical spatial 2D features can thus be processed gradually. Experimental results show that compared with the current mainstream image quality assessment methods, the proposed network can achieve more accurate image quality assessment and ranks second in the benchmark of CLIC in the image perceptual model track.

Jingyi Xie, Rui Yu, Sooyeon Lee et al.

Remote sighted assistance (RSA) has emerged as a conversational assistive technology, where remote sighted workers, i.e., agents, provide real-time assistance to users with vision impairments via video-chat-like communication. Researchers found that agents' lack of environmental knowledge, the difficulty of orienting users in their surroundings, and the inability to estimate distances from users' camera feeds are key challenges to sighted agents. To address these challenges, researchers have suggested assisting agents with computer vision technologies, especially 3D reconstruction. This paper presents a high-fidelity prototype of such an RSA, where agents use interactive 3D maps with localization capability. We conducted a walkthrough study with thirteen agents and one user with simulated vision impairment using this prototype. The study revealed that, compared to baseline RSA, the agents were significantly faster in providing navigational assistance to users, and their mental workload was significantly reduced -- all indicate the feasibility and prospect of 3D maps in RSA.

Rui Yu, Zihan Zhou

Human trajectory prediction has received increased attention lately due to its importance in applications such as autonomous vehicles and indoor robots. However, most existing methods make predictions based on human-labeled trajectories and ignore the errors and noises in detection and tracking. In this paper, we study the problem of human trajectory forecasting in raw videos, and show that the prediction accuracy can be severely affected by various types of tracking errors. Accordingly, we propose a simple yet effective strategy to correct the tracking failures by enforcing prediction consistency over time. The proposed "re-tracking" algorithm can be applied to any existing tracking and prediction pipelines. Experiments on public benchmark datasets demonstrate that the proposed method can improve both tracking and prediction performance in challenging real-world scenarios. The code and data are available at https://git.io/retracking-prediction.

Rui Yu, Zhenyuan Yuan, Minghui Zhu et al.

Nowadays, the prevalence of sensor networks has enabled tracking of the states of dynamic objects for a wide spectrum of applications from autonomous driving to environmental monitoring and urban planning. However, tracking real-world objects often faces two key challenges: First, due to the limitation of individual sensors, state estimation needs to be solved in a collaborative and distributed manner. Second, the objects' movement behavior is unknown, and needs to be learned using sensor observations. In this work, for the first time, we formally formulate the problem of simultaneous state estimation and behavior learning in a sensor network. We then propose a simple yet effective solution to this new problem by extending the Gaussian process-based Bayes filters (GP-BayesFilters) to an online, distributed setting. The effectiveness of the proposed method is evaluated on tracking objects with unknown movement behaviors using both synthetic data and data collected from a multi-robot platform.

Rui Yu, Zhiyong Dou, Song Bai et al.

Person re-identification (re-ID) is a highly challenging task due to large variations of pose, viewpoint, illumination, and occlusion. Deep metric learning provides a satisfactory solution to person re-ID by training a deep network under supervision of metric loss, e.g., triplet loss. However, the performance of deep metric learning is greatly limited by traditional sampling methods. To solve this problem, we propose a Hard-Aware Point-to-Set (HAP2S) loss with a soft hard-mining scheme. Based on the point-to-set triplet loss framework, the HAP2S loss adaptively assigns greater weights to harder samples. Several advantageous properties are observed when compared with other state-of-the-art loss functions: 1) Accuracy: HAP2S loss consistently achieves higher re-ID accuracies than other alternatives on three large-scale benchmark datasets; 2) Robustness: HAP2S loss is more robust to outliers than other losses; 3) Flexibility: HAP2S loss does not rely on a specific weight function, i.e., different instantiations of HAP2S loss are equally effective. 4) Generality: In addition to person re-ID, we apply the proposed method to generic deep metric learning benchmarks including CUB-200-2011 and Cars196, and also achieve state-of-the-art results.

Xiang Bai, Mingkun Yang, Tengteng Huang et al.

Recently, many methods of person re-identification (Re-ID) rely on part-based feature representation to learn a discriminative pedestrian descriptor. However, the spatial context between these parts is ignored for the independent extractor to each separate part. In this paper, we propose to apply Long Short-Term Memory (LSTM) in an end-to-end way to model the pedestrian, seen as a sequence of body parts from head to foot. Integrating the contextual information strengthens the discriminative ability of local representation. We also leverage the complementary information between local and global feature. Furthermore, we integrate both identification task and ranking task in one network, where a discriminative embedding and a similarity measurement are learned concurrently. This results in a novel three-branch framework named Deep-Person, which learns highly discriminative features for person Re-ID. Experimental results demonstrate that Deep-Person outperforms the state-of-the-art methods by a large margin on three challenging datasets including Market-1501, CUHK03, and DukeMTMC-reID. Specifically, combining with a re-ranking approach, we achieve a 90.84% mAP on Market-1501 under single query setting.

Rui Yu, Zhichao Zhou, Song Bai et al.

As re-ranking is a necessary procedure to boost person re-identification (re-ID) performance on large-scale datasets, the diversity of feature becomes crucial to person reID for its importance both on designing pedestrian descriptions and re-ranking based on feature fusion. However, in many circumstances, only one type of pedestrian feature is available. In this paper, we propose a "Divide and use" re-ranking framework for person re-ID. It exploits the diversity from different parts of a high-dimensional feature vector for fusion-based re-ranking, while no other features are accessible. Specifically, given an image, the extracted feature is divided into sub-features. Then the contextual information of each sub-feature is iteratively encoded into a new feature. Finally, the new features from the same image are fused into one vector for re-ranking. Experimental results on two person re-ID benchmarks demonstrate the effectiveness of the proposed framework. Especially, our method outperforms the state-of-the-art on the Market-1501 dataset.

Qi Liu-Yin, Rui Yu, Lourdes Agapito et al.

We demonstrate the use of shape-from-shading (SfS) to improve both the quality and the robustness of 3D reconstruction of dynamic objects captured by a single camera. Unlike previous approaches that made use of SfS as a post-processing step, we offer a principled integrated approach that solves dynamic object tracking and reconstruction and SfS as a single unified cost function. Moving beyond Lambertian S f S , we propose a general approach that models both specularities and shading while simultaneously tracking and reconstructing general dynamic objects. Solving these problems jointly prevents the kinds of tracking failures which can not be recovered from by pipeline approaches. We show state-of-the-art results both qualitatively and quantitatively.

Rui Yu, Chris Russell, Lourdes Agapito

We propose a novel Linear Program (LP) based formula- tion for solving jigsaw puzzles. We formulate jigsaw solving as a set of successive global convex relaxations of the stan- dard NP-hard formulation, that can describe both jigsaws with pieces of unknown position and puzzles of unknown po- sition and orientation. The main contribution and strength of our approach comes from the LP assembly strategy. In contrast to existing greedy methods, our LP solver exploits all the pairwise matches simultaneously, and computes the position of each piece/component globally. The main ad- vantages of our LP approach include: (i) a reduced sensi- tivity to local minima compared to greedy approaches, since our successive approximations are global and convex and (ii) an increased robustness to the presence of mismatches in the pairwise matches due to the use of a weighted L1 penalty. To demonstrate the effectiveness of our approach, we test our algorithm on public jigsaw datasets and show that it outperforms state-of-the-art methods.