Related papers: ProBA: Probabilistic Bundle Adjustment with the Bh…
Mixture-of-Experts (MoE) embedding models combine expert outputs using weighted linear summation, implicitly assuming a linear subspace structure in the embedding space. This assumption is shown to be inconsistent with the geometry of…
Bayesian inference allows expressing the uncertainty of posterior belief under a probabilistic model given prior information and the likelihood of the evidence. Predominantly, the likelihood function is only implicitly established by a…
Two-view structure-from-motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM. Existing deep learning-based approaches formulate the problem by either recovering absolute pose scales from two consecutive frames or predicting…
Multi-modal fusion is crucial for Internet of Things (IoT) perception, widely deployed in smart homes, intelligent transport, industrial automation, and healthcare. However, existing systems often face challenges: high model complexity…
Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt positive data…
Achieving both high accuracy and topological continuity in road segmentation from satellite imagery is a critical goal for applications ranging from urban planning to disaster response. State-of-the-art methods often rely on Vision…
We show that two widely accepted model reduction techniques, Balanced Truncation and Balanced Singular Perturbation Approximation, can be derived as limiting approximations of a carefully constructed parameterization of Linear Time…
Existing score-based methods for inverse problems often resort to approximate minimization of the KL divergence between the inversion distribution and the Bayesian posterior. Such an approximation leads to severe mode collapse and…
Modern robotics often involves multiple embodied agents operating within a shared environment. Path planning in these cases is considerably more challenging than in single-agent scenarios. Although standard Sampling-based Algorithms (SBAs)…
Stochastic approximation (SA) is a classical approach for stochastic convex optimization. Previous studies have demonstrated that the convergence rate of SA can be improved by introducing either smoothness or strong convexity condition. In…
Multimodal Sentiment Analysis (MSA) requires integrating language, acoustic, and visual signals without sacrificing modality-specific sentiment evidence. Existing methods mainly improve either shared-private decomposition or cross-modal…
Protein-ligand binding affinity (PLBA) prediction is the fundamental task in drug discovery. Recently, various deep learning-based models predict binding affinity by incorporating the three-dimensional structure of protein-ligand complexes…
We further develop the numerical algorithm for computing the gauge connection of slope-stable holomorphic vector bundles on Calabi-Yau manifolds. In particular, recent work on the generalized Donaldson algorithm is extended to bundles with…
Structure from motion using uncalibrated multi-camera systems is a challenging task. This paper proposes a bundle adjustment solution that implements a baseline constraint respecting that these cameras are static to each other. We assume…
A restricted Boltzmann machine (RBM) is a two-layer neural network with shared weights and has been extensively studied for dimensionality reduction, data representation and recommendation systems in the literature. The traditional RBM…
We propose a novel semi-direct approach for monocular simultaneous localization and mapping (SLAM) that combines the complementary strengths of direct and feature-based methods. The proposed pipeline loosely couples direct odometry and…
Thresholding iterative methods are recently successfully applied to image deblurring problems. In this paper, we investigate the modified linearized Bregman algorithm (MLBA) used in image deblurring problems, with a proper treatment of the…
We propose a new formulation for the bundle adjustment problem which relies on nullspace marginalization of landmark variables by QR decomposition. Our approach, which we call square root bundle adjustment, is algebraically equivalent to…
Federated fine-tuning of large language models (LLMs) over bandwidth-limited 6G links must meet strict round-time and energy budgets. Analog over-the-air (OTA) aggregation reduces uplink cost but is sensitive to fading and interference,…
In dynamical systems saddle points partition the domain into basins of attractions of the remaining locally stable equilibria. This problem is rather common especially in population dynamics models. Precisely, a particular solution of a…