Vision-Language Models (VLMs) are widely used in tasks like Open-Vocabulary Object Detection and zero-shot Classification, owing to their powerful generalization. However, recent research reveals that VLMs exhibit significant performance instability when tasked with recognizing concepts at varying granularities (e.g., ``animal'' vs. ``dog''). Prevailing methods inject external knowledge from Large Language Models, but this unconstrained approach distorts the VLM's inherent hierarchical orthogonal geometry, leading to performance collapse on general concepts. To address this, we introduce GeCoin, an innovative Geometrically Constrained framework that safely enhances existing VLMs with external knowledge for improved hierarchical understanding, without additional training. By projecting knowledge into the null-space of a query concept's feature space, GeCoin mathematically guarantees the preservation of general knowledge while integrating specialized information. Extensive experiments across large-scale benchmarks, diverse VLMs, and knowledge from various LLMs (e.g., GPT-3.5, Claude-3, Gemini-Pro) show that GeCoin boosts performance by an average of 3.9% over the strongest baseline—crucially eradicating performance collapse on general concepts.

Defect detection is a fundamental task in industrial image analysis, crucial for identifying and delineating defect regions. However, existing models, often struggle to learn critical features effectively under conditions of noisy interference. In this study, we introduce the Fine-Grained Hierarchical Interaction Learning (FINet) framework, designed to enhance the learning process by harmonizing feature interactions at multiple scales. Specifically, FINet incorporates the Adaptive Tensor Interaction (ATI) to facilitate high-order feature interactions amidst noise in a high-dimensional frequency space. Additionally, the FlexiFocus network is developed to dynamically balance feature focus across scales, further enhancing defect feature visibility and providing an effective trade-off between computational speed and performance. Extensive experiments on the PVEL-AD dataset show FINet’s superior accuracies (90.50% mAP50, 62.80% mAP50:5:95 ), surpassing DDQ-DETR by 8.3% and 3.6%, respectively. The code is available at https://github.com/zhongzee/FINet-master.

Group fairness based on adversarial training has gained significant attention on graph data, which was implemented by masking sensitive attributes to generate fair feature views. However, existing models suffer from training instability due to uncertainty of the generated masks and the trade-off between fairness and utility. In this work, we propose a stable fair Graph Neural Network (SFG) to maintain training stability while preserving accuracy and fairness performance. Specifically, we first theoretically derive a tight upper Lipschitz bound to control the stability of existing adversarial-based models and employ a stochastic projected subgradient algorithm to constrain the bound, which operates in a block-coordinate manner. Additionally, we construct the uncertainty set to train the model, which can prevent unstable training by dropping some overfitting nodes caused by chasing fairness. Extensive experiments conducted on three real-world datasets demonstrate that SFG is stable and outperforms other state-of-the-art adversarial-based methods in terms of both fairness and utility performance. Codes are available at https://github.com/sh-qiangchen/SFG.

Open-vocabulary object detection (OvOD) uses Vision-Language Models (VLMs) to detect arbitrary categories specified by natural language. However, existing methods often struggle with performance instability caused by granularity-induced semantic drift, which arises from misaligned label embeddings across varying levels of specificity. In this paper, we propose GraSecon, a Graph-guided Semantically Consistent representation framework that enhances zero-shot detection robustness without requiring additional training. We construct a hierarchical Fine-grained Semantic Graph enriched with visually grounded attributes from large language models (LLMs). This graph captures hierarchical, sibling and cross-level relations, enabling controlled Laplacian refinement to harmonize the embedding space and improve visual-semantic alignment. To strengthen fine-grained discriminability, we introduce a Key Semantic Node Mining module that identifies and anchors semantically sensitive nodes, ensuring robust feature representation. Furthermore, our Semantic Relevance-Driven Laplacian Propagation adaptively propagates information, promoting coherent and context-aware embedding alignment across granularities. Extensive experiments on the iNatLoc and FSOD datasets demonstrate that GraSecon outperforms prior SOTA methods, achieving average mAP50 improvements of 6.5% and 5.4%. Code is publicly available at: https://github.com/minoslab-csu/GraSecon.

Recent advancements in graph unlearning models have enhanced model utility by preserving the node representation essentially invariant, while using gradient ascent on the forget set to achieve unlearning. However, this approach causes a drastic degradation in model utility during the unlearning process due to the rapid divergence speed of gradient ascent. In this paper, we introduce INPO, an Influence-aware Negative Preference Optimization framework that focuses on slowing the divergence speed and improving the robustness of the model utility to the unlearning process. Specifically, we first analyze that NPO has slower divergence speed and theoretically propose that unlearning high-influence edges can reduce impact of unlearning. We design an influence-aware message function to amplify the influence of unlearned edges and mitigate the tight topological coupling between the forget set and the retain set. The influence of each edge is quickly estimated by a removal-based method. Additionally, we propose a topological entropy loss from the perspective of topology to avoid excessive information loss in the local structure during unlearning. Extensive experiments conducted on five real-world datasets demonstrate that INPO-based model achieves state-of-the-art performance on all forget quality metrics while maintaining the model's utility. Codes are available at https://github.com/sh-qiangchen/INPO.

Medical Visual Question Answering (Med-VQA) interprets complex medical imagery using user instructions for precise diagnostics, yet faces challenges due to diverse, inadequately annotated images. In this paper, we introduce the Universal Instruction-Vision Navigator (Uni-Med) framework for extracting instruction-to-answer relationships, facilitating the understanding of visual evidence behind responses. Specifically, we design the Instruct-to-Answer Clues Interpreter (IAI) to generate visual explanations based on the answers and mark the core part of instructions with "real intent" labels. The IAI-Med VQA dataset, produced using IAI, is now publicly available to advance Med-VQA research. Additionally, our Token-Level Cut-Mix module dynamically aligns visual explanations with image patches, ensuring answers are traceable and learnable. We also implement intention-guided attention to minimize non-core instruction interference, sharpening focus on ’real intent’. Extensive experiments on SLAKE datasets show Uni-Med’s superior accuracies (87.52% closed, 86.12% overall), outperforming MedVInT-PMC-VQA by 1.22% and 0.92%. Code and dataset are available at: https://github.com/zhongzee/Uni-Med-master.

This work follows the 'Discrete Signal Reconstruction from its Spectral Magnitude and Some Samples'[1]. The uniqueness of the discrete signal reconstruction from its autocorrelation function and one sample has been discussed in detail in this paper. Four theorems are presented. In addition, we provide an effective iterative algorithm recovering the discrete signal.

Discrete signal reconstruction from its spectral magnitude and some samples has a variety of potential applications. In this paper, a discrete signal is shown to be uniquely reconstructed by its spectral magnitude and some saples under mild restriction on its original sequence. Three theorems are provided. Several numerical algorithms have been discussed and a new algorithm called three domains iteration method in which the convergence is guaranteed is developed.

In this paper, what can the phass function do in wavelet estimation is mainly concerned, the concept of wave-form unigueness in deconvolution of seismic traces has been discussed. Under this conception, mixed-phase wavelets can be classified into three types. Based on the theorem of uniqueness of a sequence with a phase function by M.H.Hayes et al. and with some extensions, two types of wavelets have been reconstructed from its phase using zero-perturbation relaxed iterative algorithm. A new criterion function Spwhich judges the convergence of iteration and a new criterion of classification are also presented. Several examples of mixed-phase wavelet reconstruction from its phase are provided.