The paper introduces an adaptive feature-optimized vision front end that intelligently selects and budgets visual features for 3D reconstruction, significantly improving reconstruction quality and com…

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

This paper systematically explores the convex polygon reconstruction problem with specified sets of features, contributing new testing algorithms and hardness results.

The paper proposes a unified framework to systematically redefine instance matching for Panoptic Quality evaluation, moving beyond the standard One-to-One matching to accommodate complex scenarios lik…

The paper identifies a fundamental mismatch between standard pairwise ranking metrics (like AP and FPR-95) and the true assignment objective in multi-view object association, proposing a Sinkhorn-base…

This paper formalizes the binding problem using information theory and develops a probing method to measure binding information in deep learning representations, demonstrating that binding is crucial…

This paper proves that single-vector embeddings require a larger representation size than multi-vector embeddings to approximate certain similarities.

This paper investigates the use of spectral filtering for continuous subgraph matching over dynamic graphs and presents three key findings.

This paper investigates the application of Parameter-Efficient Fine-Tuning (PEFT) methods, specifically adapters and LoRA, to large pretrained models for instance segmentation, demonstrating that thes…

Low-Pass Flow Matching introduces a spectral bias into the flow matching process, allowing it to better model natural data by transitioning from a standard source spectrum to a frequency-decaying bias…

The paper argues that the standard FID metric is unreliable because its performance depends significantly on the geometric structure and density of the reference dataset, not just the sample quality.

This paper proposes a hybrid feature fusion and voting-based approach for automated malware detection and classification into specific malware families, achieving high performance metrics like an AUC…

This paper proposes Point Cloud Upsampling through Patch-based Frequency Superposition (PUtPFS), an optimization-based approach for uniform point cloud upsampling without data dependency or training.

This paper derives deterministic limits for transfer learning performance of linear discriminant analysis in high-dimensional two-class classification under spiked covariance models.