论文检索

Zixu Li, Yupeng Hu, Zhiwei Chen, Qinlei Huang, Guozhi Qiu, Zhiheng Fu, Meng Liu

With the rapid growth of video data, Composed Video Retrieval (CVR) has emerged as a novel paradigm in video retrieval and is receiving increasing attention from researchers. Unlike unimodal video retrieval methods, the CVR task takes a multi-modal query consisting of a reference video and a piece of modification text as input. The modification text conveys the user's intended alterations to the reference video. Based on this input, the model aims to retrieve the most relevant target video. In the CVR task, there exists a substantial discrepancy in information density between video and text modalities. Traditional composition methods tend to bias the composed feature toward the reference video, which leads to suboptimal retrieval performance. This limitation is significant due to the presence of three core challenges: (1) modal contribution entanglement, (2) explicit optimization of composed features, and (3) retrieval uncertainty. To address these challenges, we propose the evidence-dRivEn dual-sTream diRectionAl anChor calibration networK (ReTrack). ReTrack is the first CVR framework that improves multi-modal query understanding by calibrating directional bias in composed features. It consists of three key modules: Semantic Contribution Disentanglement, Composition Geometry Calibration, and Reliable Evidence-driven Alignment. Specifically, ReTrack estimates the semantic contribution of each modality to calibrate the directional bias of the composed feature. It then uses the calibrated directional anchors to compute bidirectional evidence that drives reliable composed-to-target similarity estimation. Moreover, ReTrack exhibits strong generalization to the Composed Image Retrieval (CIR) task, achieving SOTA performance across three benchmark datasets in both CVR and CIR scenarios.

Zihan Li, Wei Sun, Jing Hu, Jianhua Yin, Xing Wang, Erwei Yin, Jianlong Wu

While large language-image pre-trained models like CLIP offer powerful generic features for image clustering, existing methods typically freeze the encoder. This creates a fundamental mismatch between the model's task-agnostic representations and the demands of a specific clustering task, imposing a ceiling on performance. To break this ceiling, we propose a self-enhanced framework based on cross-modal semantic consistency for efficient image clustering. Our framework first builds a strong foundation via Cross-Modal Semantic Consistency and then specializes the encoder through Self-Enhancement. In the first stage, we focus on Cross-Modal Semantic Consistency. By mining consistency between generated image-text pairs at the instance, cluster assignment, and cluster center levels, we train lightweight clustering heads to align with the rich semantics of the pre-trained model. This alignment process is bolstered by a novel method for generating higher-quality cluster centers and a dynamic balancing regularizer to ensure well-distributed assignments. In the second stage, we introduce a Self-Enhanced fine-tuning strategy. The well-aligned model from the first stage acts as a reliable pseudo-label generator. These self-generated supervisory signals are then used to feed back the efficient, joint optimization of the vision encoder and clustering heads, unlocking their full potential. Extensive experiments on six mainstream datasets show that our method outperforms existing deep clustering methods by significant margins. Notably, our ViT-B/32 model already matches or even surpasses the accuracy of state-of-the-art methods built upon the far larger ViT-L/14.

Zhuo Li, Gengyu Lyu, Yuena Lin, Ziang Chen, Zhiyuan Ma, Zhen Yang, Zun Li

Hypergraph contrastive learning has emerged as a powerful unsupervised paradigm for hypergraph representation learning. Traditional hypergraph contrastive learning methods typically leverage neighbor aggregation strategy to obtain entity (node and hyperedge) representations within each connected component, and then utilize contrastive losses (e.g., node- or hyperedge-level) to update the encoders. However, since entities are usually focused equally on their respective losses, large connected components with numerous entities tend to provide a dominant contribution to the whole learning process, which inevitably hinders the effective learning of entity representations within small connected components. To address this issue, we propose a novel Connected-Component-Aware Hypergraph Contrastive Learning method (CCAHCL). Different from previous methods that only construct node or hyperedge representations, our method additionally constructs the connected component representations, and accordingly designs a hierarchical contrastive loss to balance the model's focus on different scales of connected components. Specifically, we first use the traditional neighbor aggregation strategy to aggregate and update entity (node and hyperedge) representations. Then, these entity representations are further aggregated to generate the connected component representations, where entity features are incorporated into connected components and their structural information is propagated back to enrich their corresponding entities. Afterwards, we employ node-level and hyperedge-level losses to learn the enriched entity representations, and further propose a novel connected-component-level contrastive loss to balance the model's focus on all different connected components, naturally avoiding the learning bias on large connected components. Extensive experiments on various datasets demonstrate that our proposed model achieves superior performance against other state-of-the-art methods.

Zhongnian Li, Lan Chen, Yixin Xu, Shi Xu, Xinzheng Xu

Vision-Language Models (VLMs), with their powerful content generation capabilities, have been successfully applied to data annotation processes. However, the VLM-generated labels exhibit dual limitations: low quality (i.e., label noise) and absence of error correction mechanisms. To enhance label quality, we propose Human-Corrected Labels (HCLs), a novel setting that efficient human correction for VLM-generated noisy labels. As shown in Figure 1(b), HCL strategically deploys human correction only for instances with VLM discrepancies, achieving both higher-quality annotations and reduced labor costs. Specifically, we theoretically derive a risk-consistent estimator that incorporates both human-corrected labels and VLM predictions to train classifiers. Besides, we further propose a conditional probability method to estimate the label distribution using a combination of VLM outputs and model predictions. Extensive experiments demonstrate that our approach achieves superior classification performance and is robust to label noise, validating the effectiveness of HCL in practical weak supervision scenarios.

Zhiwei Li, Guodong Long, Jing Jiang, Chengqi Zhang, Qiang Yang

Applying large pre-trained Vision-Language Models to recommendation is a burgeoning field, a direction we term Vision-Language-Recommendation (VLR). Bringing VLR to user-oriented on-device intelligence within a federated learning framework is a crucial step for enhancing user privacy and delivering personalized experiences. This paper introduces FedVLR, a federated VLR framework specially designed for user-specific personalized fusion of vision-language representations. At its core is a novel bi-level fusion mechanism: The server-side multi-view fusion module first generates a diverse set of pre-fused multimodal views. Subsequently, each client employs a user-specific mixture-of-expert mechanism to adaptively integrate these views based on individual user interaction history. This designed lightweight personalized fusion module provides an efficient solution to implement a federated VLR system. The effectiveness of our proposed FedVLR has been validated on seven benchmark datasets.

Zhenpeng Li, Jinshuo Liu, Xinyan Wang, Lina Wang, Jeff Z. Pan

With the growing adoption of Machine-Learning-As-A-Service (MLaaS), Private Inference (PI) has emerged as a promising solution to address its security concerns through cryptographic techniques. However, nonlinear operations in neural networks account for most of the computational and communication overhead in PI. Existing studies mainly focus on optimizing and reducing the number of ReLU activations in neural networks, but traditional pruning methods may mistakenly remove ReLUs that are critical to maintaining model accuracy. To accurately evaluate the importance of ReLUs in the network, we propose ReLUPruner, a method that uses Taylor expansion to quantify the impact on loss before and after ReLU replacement. Furthermore, we establish a hierarchical importance metric to guide layer-wise ReLU budget allocation and adopt a progressive pruning strategy that dynamically adjust the pruning rate of each layer according to training progress. Extensive experiments on various models and datasets show that ReLUPruner achieves a good balance between ReLU budget and model accuracy, yielding improvements of 1.89% (12.9k ReLUs, CIFAR-10), 3.62% (50k ReLUs, CIFAR-100) and 2.66% (30k ReLUs, Tiny-ImageNet) over the previous state-of-the-art.

Zekai Li, Ji Liu, Guanchen Li, Yixing Xu, Ziqiong Liu, Xuanwu Yin, Dong Li, Emad Barsoum

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language models (LLMs) in recent years. A promising direction to further improve post-pruning performance is weight permutation, which reorders model weights into patterns more amenable to pruning. However, the exponential growth of the permutation search space with the scale of Transformer architectures forces most methods to rely on greedy or heuristic algorithms, limiting the effectiveness of reordering. In this work, we propose a novel end-to-end learnable permutation framework. Our method introduces a learnable permutation cost matrix to quantify the cost of swapping any two input channels of a given weight matrix, a differentiable bipartite matching solver to obtain the optimal binary permutation matrix given a cost matrix, and a sparsity optimization loss function to directly optimize the permutation operator. We extensively validate our approach on vision and language Transformers, demonstrating that our method achieves state-of-the-art permutation results for structured sparsity.

Yuyuan Li, Junjie Fang, Fengyuan Yu, Xichun Sheng, Tianyu Du, Xuyang Teng, Shaowei Jiang, Linbo Jiang, Jianan Lin, Chaochao Chen

Federated Recommender Systems (FedRecs) leverage federated learning to protect user privacy by retaining data locally. However, user embeddings in FedRecs often encode sensitive attribute information, rendering them vulnerable to attribute inference attacks. Attribute unlearning has emerged as a promising approach to mitigate this issue. In this paper, we focus on user-level FedRecs, which is a more practical yet challenging setting compared to group-level FedRecs. Adversarial training emerges as the most feasible approach within this context. We identify two key challenges in implementing adversarial training-based attribute unlearning for user-level FedRecs: i) mitigating training instability caused by user data heterogeneity, and ii) preventing attribute information leakage through gradients. To address these challenges, we propose FedAU2, an attribute unlearning method for user-level FedRecs. For CH1, we propose a adaptive adversarial training strategy, where the training dynamics are adjusted in response to local optimization behavior. For CH2, we propose a dual-stochastic variational autoencoder to perturb the adversarial model, effectively preventing gradient-based information leakage. Extensive experiments on three real-world datasets demonstrate that our proposed FedAU2 achieves superior performance in unlearning effectiveness and recommendation performance compared to existing baselines.

Yuxuan Li, Yicheng Gao, Ning Yang, Stephen Xia

Episodic tasks in Reinforcement Learning (RL) often pose challenges due to sparse reward signals and high-dimensional state spaces, which hinder efficient learning. Additionally, these tasks often feature hidden “trap states”—irreversible failures that prevent task completion but do not provide explicit negative rewards to guide agents away from repeated errors. To address these issues, we propose Time-Weighted Contrastive Reward Learning (TW-CRL), an Inverse Reinforcement Learning (IRL) framework that leverages both successful and failed demonstrations. By incorporating temporal information, TW-CRL learns a dense reward function that identifies critical states associated with success or failure. This approach not only enables agents to avoid trap states but also encourages meaningful exploration beyond simple imitation of expert trajectories. Empirical evaluations on navigation tasks and robotic manipulation benchmarks demonstrate that TW-CRL surpasses state-of-the-art methods, achieving improved efficiency and robustness.

Yue Li, Weifan Wang, Tai Sing Lee

Recent neurophysiological studies have revealed that the early visual cortex can rapidly learn global image context, as evidenced by a sparsification of population responses and a reduction in mean activity when exposed to familiar versus novel image contexts. This phenomenon has been attributed primarily to local recurrent interactions, rather than changes in feedforward or feedback pathways—supported by both empirical findings and circuit-level modeling. Recurrent neural circuits capable of simulating these effects have been shown to reshape the geometry of neural manifolds, enhancing robustness and invariance to irrelevant variations. In this study, we employ a Vision Transformer (ViT)-based autoencoder to investigate, from a functional perspective, how familiarity training can induce sensitivity to global context in the early layers of a deep neural network. We hypothesize that rapid learning operates via fast weights, which encode transient or short-term memory traces, and we explore the use of Low-Rank Adaptation (LoRA) to implement such fast weights within each Transformer layer. Our results show that: (1) The proposed ViT-based autoencoder's self-attention circuit is performing a manifold transform similar to a neural circuit developed for modeling the familiarity effect. (2) Familiarity training induces alignment of latent representation in early layers with the top layer that contains global context information. (3) Familiarity training makes self-attention pay attention to a broader scope details in the remembered image context, rather than just the critical features for object recognition. (4) These effects are significantly amplified by the incorporation of LoRA-based fast weights. Together, these findings suggest that familiarity training can introduce global sensitivity to earlier layers in a hierarchical network, and that a hybrid fast-and-slow weight architecture may provide a viable computational model for studying the functional consequences of rapid global context learning in the brain.

Yu-sheng Li, Xincen Duan, Beili Wang, Wei Guo, Han-jia Ye

Accurate medical diagnosis often relies on both textual self-reported symptoms and structured medical examination results of patients. However, these examinations vary significantly in cost—measured in time, money, or patient discomfort---creating a challenging trade-off between diagnostic accuracy and resource efficiency. To address this issue, we propose a dynamic diagnostic framework that incrementally selects medical examinations based on individual characteristics of each patient. Starting with textual self-reported symptoms and basic demographic, the system determines follow-up examinations step-by-step, improving accuracy while minimizing additional costs. Specifically, we introduce Dynamic feature selection with Instance-Specific Cost sensitivity (DISC). DISC treats each examination as a feature and learns to acquire them sequentially to optimize predictive performance under personalized cost constraints. To support richer clinical understanding, we further develop a multimodal framework that integrates unstructured self-reported symptom text with structured medical examination data. We conduct experiments on 680,000 patients with 43 million medical examination records, demonstrating that DISC high diagnostic accuracy even when accounting for examination costs. Our work provides substantial momentum for the advancement of AI in healthcare, offering both methodological and practical foundations that can significantly accelerate the deployment of intelligent, cost-aware diagnostic systems in real-world clinical settings.

You Li, Guannan Zhao, Yuhao Ju, Yunqi He, Jie Gu, Hai Zhou

We introduce LLA, an effective intellectual property (IP) protection scheme for generative AI models. LLA leverages the synergy between hardware and software to defend against various supply chain threats, including model theft, model corruption, and information leakage. On the software side, it embeds key bits into neurons that can trigger outliers to degrade performance and applies invariance transformations to obscure the key values. On the hardware side, it integrates a lightweight locking module into the AI accelerator while maintaining compatibility with various dataflow patterns and toolchains. An accelerator with a pre-stored secret key acts as a license to access the model services provided by the IP owner. The evaluation results show that LLA can withstand a broad range of oracle-guided key optimization attacks, while incurring a minimal computational overhead of less than 0.1% for 7,168 key bits.

Yongguang Li, Jindong Li, Qi Wang, QianLi Xing, Runliang Niu, Shengsheng Wang, Menglin Yang

Vision-language models (VLMs) have gained widespread attention for their strong zero-shot capabilities across numerous downstream tasks. However, these models assume that each test image’s class label is drawn from a predefined label set and lack a reliable mechanism to reject samples from emerging unknown classes when only unlabeled data are available. To address this gap, open-set domain adaptation methods retrain models to push potential unknowns away from known clusters. Yet, some unknown samples remain stably anchored to specific known classes in the VLM feature space due to semantic relevance, which is termed as Semantic Affinity Anchoring (SAA). Forcibly repelling these samples unavoidably distorts the native geometry of VLMs and degrades performance. Meanwhile, existing score‑based unknown detectors use simplistic thresholds and suffer from threshold sensitivity, resulting in sub‑optimal performance. To address aforementioned issues, we propose VLM-OpenXpert, which comprises two training‑free, plug‑and‑play inference modules. SUFF performs SVD on high-confidence unknowns to extract a low-rank "unknown subspace". Each sample’s projection onto this subspace is weighted and softly removed from its feature, suppressing unknown components while preserving semantics. BGAT corrects score skewness via a Box–Cox transform, then fits a bimodal Gaussian mixture to adaptively estimate the optimal threshold balancing known-class recognition and unknown-class rejection. Experiments on 9 benchmarks and three backbones (CLIP, SigLIP, ALIGN) under Source-Free OSDA settings show that our training-free pipeline matches or outperforms retraining-heavy state-of-the-art methods, establishing a powerful lightweight inference calibration paradigm for open-set VLM deployment.

Yichen Li, Hang Su, Huifa Li, Haolin Yang, Xinlin Zhuang, Haochen Xue, Haozhao Wang, Imran Razzak

Knowledge Distillation (KD) serves as an effective approach to addressing heterogeneity issues in Federated Learning (FL), leveraging additional datasets to align local and global models better. There are two primary distillation paradigms: feature-based distillation, which utilizes intermediate-layer features of the network, and logit-based distillation, which employs the final layer's logit outputs. However, existing studies often select distillation methods based on intuitive and empirical evidence when facing different heterogeneous settings, neglecting the intrinsic relationship between distillation paradigms and heterogeneity. This oversight may result in suboptimal federated knowledge distillation performance under heterogeneous conditions. In this paper, we propose the Consolidated Distillation for Heterogeneous Federated Learning - FedCD that balances knowledge representations from both feature-based and logit-based distillation to enhance performance. Specifically, to address the misalignment between knowledge conveyed by features and logits, we aggregate features from different layers via cross-layer attention to preserve semantic knowledge, followed by distribution modeling using Gaussian Mixture Models. This process strengthens knowledge distillation by constraining the transformation of different network layers' features under a consolidated distribution, thereby mitigating impacts from both data and model heterogeneity. Extensive experiments demonstrate that FedCD outperforms state-of-the-art methods by over 10.72% and validate the effectiveness of our approach.

Yanmin Li, Lihua Liu, Xin Wang, Zhilong Mao, Jibing Wu, Weidong Bao

Learning decision policies from confounded observational data is a challenging task in causal inference, as unobserved confounders can lead to biased or suboptimal actions when relying solely on machine learning models. A synergistic approach is learning to defer, which decides when to act itself and when to defer to a human expert with access to unobserved information. However, constructing the learning target, which defines the probability of choosing each action or deferral, remains a core challenge. To address this, we propose causal-target-based learning to defer (CTLD) framework, where the causal target is constructed from sharp bounds on potential outcomes. Specifically, the degree of overlap between these bounds determines the probability of deferral, while their relative positions and widths define the probabilities over actions. CTLD aligns model predictions with this causal target to make probabilistic decisions over actions and deferral. We present comprehensive theoretical guarantees for the learned policy and demonstrate the effectiveness of CTLD on synthetic and semi-synthetic datasets.

Xinyao Li, Yinjie Min, Hongbo Chen, Zhekai Du, Fengling Li, Jingjing Li

Fine-tuning large pretrained vision-language models (VLMs) has emerged as a prevalent paradigm for downstream adaptation, yet it faces a critical trade-off between domain specificity and domain generalization (DG) ability. Current methods typically fine-tune a universal model on the entire dataset, which potentially compromises the ability to generalize to unseen domains. To fill this gap, we provide a theoretical understanding of the generalization ability for VLM fine-tuning, which reveals that training multiple parameter-efficient expert models on partitioned source domains leads to better generalization than fine-tuning a universal model. Inspired by this finding, we propose a two-step domain-expert-Guided DG (GuiDG) framework. GuiDG first employs prompt tuning to obtain source domain experts, then introduces a Cross-Modal Attention module to guide the fine-tuning of the vision encoder via adaptive expert integration. To better evaluate few-shot DG, we construct ImageNet-DG from ImageNet and its variants. Extensive experiments on standard DG benchmarks and ImageNet-DG demonstrate that GuiDG improves upon state-of-the-art fine-tuning methods while maintaining efficiency.

Xintong Li, Haoran Zhang, Xiao Zhou

The abundance of fine-grained spatio-temporal data, such as traffic sensor networks, offers vast opportunities for scientific discovery. However, inferring causal relationships from such observational data remains challenging, particularly due to unobserved confounders that are specific to units (e.g., geographical locations) yet influence outcomes over time. Most existing methods for spatio-temporal causal inference assume that all confounders are observed, an assumption that is often violated in practice. In this paper, we introduce Spatio-Temporal Hierarchical Causal Models (ST-HCMs), a novel graphical framework that extends hierarchical causal modeling to the spatio-temporal domain. At the core of our approach is the Spatio-Temporal Collapse Theorem, which shows that a complex ST-HCM converges to a simpler flat causal model as the amount of subunit data increases. This theoretical result enables a general procedure for causal identification, allowing ST-HCMs to recover causal effects even in the presence of unobserved, time-invariant unit-level confounders, a scenario where standard non-hierarchical models fail. We validate the effectiveness of our framework on both synthetic and real-world datasets, demonstrating its potential for robust causal inference in complex dynamic systems.

Xinpeng Li, Kai Ming Ting

The proliferation of complex, black-box AI models has intensified the need for techniques that can explain their decisions. Feature attribution methods have become a popular solution for providing post-hoc explanations, yet the field has historically lacked a formal problem definition. This paper addresses this gap by introducing a formal definition for the problem of feature attribution, which stipulates that explanations be supported by an underlying probability distribution represented by the given dataset. Our analysis reveals that many existing model-agnostic methods fail to meet this criterion, while even those that do often possess other limitations. To overcome these challenges, we propose Distributional Feature Attribution eXplanations (DFAX), a novel, model-agnostic method for feature attribution. DFAX is the first feature attribution method to explain classifier predictions directly based on the data distribution. We show through extensive experiments that DFAX is more effective and efficient than state-of-the-art baselines.

Xingyao Li, Fengzhuo Zhang, Cunxiao Du, Hui Ji

Despite significant progress in auto-regressive image generation, inference remains slow due to the sequential nature of AR models and the ambiguity of image tokens, even when using speculative decoding. Recent works attempt to address this with relaxed speculative decoding but lack theoretical grounding. In this paper, we establish the theoretical basis of relaxed SD and propose COOL-SD, an annealed relaxation of speculative decoding built on two key insights. The first analyzes the total variation (TV) distance between the target model and relaxed speculative decoding and yields an optimal resampling distribution that minimizes an upper bound of the distance. The second uses perturbation analysis to reveal an annealing behaviour in relaxed speculative decoding, motivating our annealed design. Together, these insights enable COOL-SD to generate images faster with comparable quality, or achieve better quality at similar latency. Experiments validate the effectiveness of COOL-SD, showing consistent improvements over prior methods in speed-quality trade-offs.

Xingwang Li, Fei Teng, Xin Wu, Qiang Duan

Hidden degenerations in industrial time series often precede observable failures, they remain undetected by standard monitoring systems until anomalies become apparent. This gap between microscopic degradation and macroscopic observation renders conventional predictors inherently reactive, as they rely on correlations in sensor data rather than uncovering the underlying, physics‑consistent degradation states. Crucially, the microscopic mechanisms governing system evolution depend on macroscopic state variables—whose measurements are expectations over microscopic probability distributions—so purely data‑driven “top‑down” or purely physics‑guided “bottom‑up” approaches cannot forecast degeneration‑entangled industrial faults. To address these challenges, we propose a Physics-Guided Bidirectional Inference Framework that represents hidden microscopic states from macroscopic measurements. Our approach uniquely combines: (1) bottom-up physics-based simulation using Continuum Damage Mechanics to model micro-scale damage evolution under environmental stressors, and (2) top-down probabilistic inference via maximum entropy formalism to estimate latent microstate distributions from sparse sensor data. This bidirectional mechanism enables early failure prediction by bridging observable measurements with unobservable degeneration. Validation on real-world railway infrastruc datasets demonstrates significant improvements in early fault prediction compared to state-of-the-art baselines. Our method establishes a new paradigm for safety-critical industrial applications requiring reliable prediction of hidden degeneration processes.