Institution profile

Jiangsu University of Science and Technology

Academic institutionasia · cn
Official website
Research library10linked papers
Opportunities0open roles
Selected work

Representative Papers

When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learning

Aug 06, 2026

This study investigates whether the effectiveness of frozen vision-language model prompts—such as those from CLIP—remains consistent after visual adaptation to a target domain in unsupervised cross-domain few-shot learning. By evaluating performance shifts of simple class-name templates versus rich semantic descriptions before and after adaptation across multiple medical and remote sensing datasets, and employing LoRA fine-tuning, paired comparisons, semantic shuffling controls, and multi-seed validation, the work uncovers two novel phenomena: “semantic saturation,” where adaptation yields diminishing gains (e.g., EuroSAT, CropDisease), and “semantic emergence,” where only detailed descriptions become effective post-adaptation (e.g., ISIC, ChestX). These findings challenge the prevailing assumption that zero-shot prompt quality reliably predicts its efficacy as a semantic anchor after adaptation, revealing instead a dynamic evolution of semantic utility.

0 citationsRead paper

Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection

Jun 22, 2026

This work addresses key challenges in multispectral object detection—inefficient cross-modal feature alignment, high computational cost of global attention, and the inability of fixed receptive fields to model nonlinear spatial relationships—by proposing the PNAFusion framework. The method introduces Pixel Neighborhood Cross-Attention (PNCA) to eliminate redundant global matching, designs an Adaptive Deformable Alignment (ADA) module to capture nonlinear spatial mappings, and incorporates a progressive feedback mechanism to iteratively refine fusion between visible and thermal infrared features. Integrated into YOLOv5 and Co-DETR, PNAFusion achieves 84.2, 90.5, and 85.5 mAP@0.5 on the FLIR, M3FD, and DroneVehicle datasets, respectively, while reducing GPU memory consumption by 33.0% compared to ICAFusion and lowering theoretical FLOPs from 194.8G to 156.4G.

0 citationsRead paper

LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks

Apr 02, 2026

Quantum machine learning faces two major bottlenecks: barren plateaus and noise sensitivity, compounded by the absence of a unified theoretical framework. This work proposes a novel paradigm based on Lie-algebraic generator dynamics, modeling parameterized quantum circuits as Lie subalgebras of $\mathfrak{u}(2^n)$ and characterizing trainability and expressivity through the induced Riemannian manifold geometry. The key innovation is structured Lie algebra truncation (LieTrunc), which contracts the manifold to circumvent concentration of measure while preserving non-vanishing gradients. We establish the first “geometric capacity–plateau” principle, proving that expressivity is governed by the span of generators rather than parameter count, and identify trainable regions where gradient variance decays polynomially. Experiments on 2–6 qubit systems demonstrate that LieTrunc-QNN maintains stable gradients and high effective dimensionality, fully preserving the Fubini–Study metric rank (rank=16 at $n=6$) and significantly outperforming random truncation, thereby validating the scaling law between gradient variance and effective dimension.

0 citationsRead paper
Recent publications

Latest Papers

When Semantics Saturate or Emerge: Adaptation-Conditional Semantic Utility in Source-Free Cross-Domain Few-Shot Learning

Aug 06, 2026

This study investigates whether the effectiveness of frozen vision-language model prompts—such as those from CLIP—remains consistent after visual adaptation to a target domain in unsupervised cross-domain few-shot learning. By evaluating performance shifts of simple class-name templates versus rich semantic descriptions before and after adaptation across multiple medical and remote sensing datasets, and employing LoRA fine-tuning, paired comparisons, semantic shuffling controls, and multi-seed validation, the work uncovers two novel phenomena: “semantic saturation,” where adaptation yields diminishing gains (e.g., EuroSAT, CropDisease), and “semantic emergence,” where only detailed descriptions become effective post-adaptation (e.g., ISIC, ChestX). These findings challenge the prevailing assumption that zero-shot prompt quality reliably predicts its efficacy as a semantic anchor after adaptation, revealing instead a dynamic evolution of semantic utility.

0 citationsRead paper

Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection

Jun 22, 2026

This work addresses key challenges in multispectral object detection—inefficient cross-modal feature alignment, high computational cost of global attention, and the inability of fixed receptive fields to model nonlinear spatial relationships—by proposing the PNAFusion framework. The method introduces Pixel Neighborhood Cross-Attention (PNCA) to eliminate redundant global matching, designs an Adaptive Deformable Alignment (ADA) module to capture nonlinear spatial mappings, and incorporates a progressive feedback mechanism to iteratively refine fusion between visible and thermal infrared features. Integrated into YOLOv5 and Co-DETR, PNAFusion achieves 84.2, 90.5, and 85.5 mAP@0.5 on the FLIR, M3FD, and DroneVehicle datasets, respectively, while reducing GPU memory consumption by 33.0% compared to ICAFusion and lowering theoretical FLOPs from 194.8G to 156.4G.

0 citationsRead paper

LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks

Apr 02, 2026

Quantum machine learning faces two major bottlenecks: barren plateaus and noise sensitivity, compounded by the absence of a unified theoretical framework. This work proposes a novel paradigm based on Lie-algebraic generator dynamics, modeling parameterized quantum circuits as Lie subalgebras of $\mathfrak{u}(2^n)$ and characterizing trainability and expressivity through the induced Riemannian manifold geometry. The key innovation is structured Lie algebra truncation (LieTrunc), which contracts the manifold to circumvent concentration of measure while preserving non-vanishing gradients. We establish the first “geometric capacity–plateau” principle, proving that expressivity is governed by the span of generators rather than parameter count, and identify trainable regions where gradient variance decays polynomially. Experiments on 2–6 qubit systems demonstrate that LieTrunc-QNN maintains stable gradients and high effective dimensionality, fully preserving the Fubini–Study metric rank (rank=16 at $n=6$) and significantly outperforming random truncation, thereby validating the scaling law between gradient variance and effective dimension.

0 citationsRead paper