arXiv preprints from January 1, 2026 through September 27, 2026 — 22:09:59 EST
Large Language Models have revolutionized information processing, yet their reliability is severely compromised by faithfulness hallucinations. While current approaches attempt to mitigate this issue through node-level adjustments or coarse suppression, they often overlook the distributed nature of neural information, leading to...
Current evaluations of mathematical reasoning in large language models (LLMs) are dominated by static benchmarks, either derived from competition-style problems or curated through costly expert effort, resulting in limited coverage of research-level mathematics and rapid performance saturation. We propose a fully automated,...
3D Gaussian Splatting (3DGS) has emerged as a novel paradigm for 3D reconstruction from satellite imagery. However, in multi-temporal satellite images, prevalent shadows exhibit significant inconsistencies due to varying illumination conditions. To address this, we propose ShadowGS, a novel framework based on 3DGS. It leverages a...
This paper presents the development and evaluation of a custom Convolutional Neural Network (CustomCNN) created to study how architectural design choices affect multi-domain image classification tasks. The network uses residual connections, Squeeze-and-Excitation attention mechanisms, progressive channel scaling, and Kaiming...
Existing fraud detection methods predominantly rely on transcribed text, suffering from ASR errors and missing crucial acoustic cues like vocal tone and environmental context. This limits their effectiveness against complex deceptive strategies. To address these challenges, we first propose \textbf{SAFE-QAQ}, an end-to-end...
We reexamine the classical subset sum problem: given a set $X$ of $n$ positive integers and a number $t$, decide whether there exists a subset of $X$ that sums to $t$; or more generally, compute the set $\mbox{out}$ of all numbers $y\in\{0,\ldots,t\}$ for which there exists a subset of $X$ that sums to $y$. Standard dynamic...
Approximate Graph Pattern Mining (AGPM) is essential for analyzing large-scale graphs where exact counting is computationally prohibitive. While there exist numerous sampling-based AGPM systems, they all rely on uniform sampling and overlook the underlying probability distribution. This limitation restricts their scalability to a...
Developing deep learning models with strong adaptability to topological variations is of great practical significance for power flow analysis. To enhance model performance under variable system scales and improve robustness in branch power prediction, this paper proposes a Scale-adaptive Multi-task Power Flow Analysis (SaMPFA)...
Parking is a critical task for autonomous driving systems (ADS), with unique challenges in crowded parking slots and GPS-denied environments. However, existing works focus on 2D parking slot perception, mapping, and localization, 3D reconstruction remains underexplored, which is crucial for capturing complex spatial geometry in...
Deep learning models are widely used across computer vision and other domains. When working on the model induction, selecting the right architecture for a given dataset often relies on repetitive trial-and-error procedures. This procedure is time-consuming, resource-intensive, and difficult to automate. While previous work has...
Small language models (SLMs) are increasingly used for financial classification due to their fast inference and local deployability. However, compared with large language models, SLMs are more prone to factual hallucinations in reasoning and exhibit weaker classification performance. This raises a natural question: Can mitigating...
Motivated by a historical combinatorial problem that resembles the well-known Josephus problem, we investigate circular partition algorithms and formulate problems in deterministic finite automata with practical algorithms. The historical problem involves arranging individuals on a circle and eliminating every k-th person until a...
The development of audio foundation models has accelerated rapidly since the emergence of GPT-4o. However, the lack of comprehensive evaluation has become a critical bottleneck for further progress in the field, particularly in audio generation. Current audio evaluation faces three major challenges: (1) audio evaluation lacks a...
In this paper, we propose a probabilistic algorithm suitable for any linear code $C$ to determine whether a given vector $\mathbf{x}$ belongs to $ C$. The algorithm achieves $O(n\log n)$ time complexity, $ O(n^2)$ space complexity and with an error probability less than $1/\mathrm{poly}(n)$ in the asymptotic sense.
Causal discovery from data with unmeasured confounding factors is a challenging problem. This paper proposes an approach based on the f-GAN framework, learning the binary causal structure independent of specific weight values. We reformulate the structure learning problem as minimizing Bayesian free energy and prove that this problem...
With the rapid adoption of multimodal large language models (MLMs) in autonomous agents, cross-platform task execution capabilities in educational settings have garnered significant attention. However, existing benchmark frameworks still exhibit notable deficiencies in supporting cross-platform tasks in educational contexts,...
Cryo-electron tomography (cryo-ET) provides direct 3D visualization of macromolecules inside the cell, enabling analysis of their in situ morphology. This morphology can be regarded as an SE(3)-invariant, denoised volumetric representation of subvolumes extracted from tomograms. Inferring morphology is therefore an inverse problem of...
Scientific discovery increasingly relies on integrating heterogeneous, high-dimensional data across disciplines nowadays. While AI models have achieved notable success across various scientific domains, they typically remain domain-specific or lack the capability of simultaneously understanding and generating multimodal scientific...
Ensuring that deep learning models are well-calibrated in terms of their predictive uncertainty is essential in maintaining their trustworthiness and reliability, yet despite increasing advances in foundation model research, the relationship between such large language models (LLMs) and their calibration remains an open area of...
Large-scale time series visualization often suffers from excessive visual clutter and redundant patterns, making it difficult for users to understand the main temporal trends. To address this challenge, we present VARTS, an interactive visual analytics tool for representative time series selection and visualization. Building upon our...
Solving increasingly complex problems with large language models (LLMs) necessitates a move beyond individual models and towards multi-model systems that can effectively collaborate. While text has traditionally served as the medium for inter-model communication, a richer and more efficient exchange is possible if models can access...
Wearable inertial motion capture (MoCap) provides a portable, occlusion-free, and privacy-preserving alternative to camera-based systems, but its accuracy depends on tightly attached sensors - an intrusive and uncomfortable requirement for daily use. Embedding IMUs into loose-fitting garments is a desirable alternative, yet...
The rapid evolution of large language models (LLMs) is transforming artificial intelligence into autonomous research partners, yet a critical gap persists in complex scientific domains such as combustion modeling. Here, practical AI assistance requires the seamless integration of domain literature knowledge with robust execution...
Person re-identification (ReID) plays a critical role in intelligent surveillance systems by linking identities across multiple cameras in complex environments. However, ReID faces significant challenges such as appearance variations, domain shifts, and limited labeled data. This dissertation proposes three advanced approaches to...
Visual reinforcement learning (RL) suffers from poor sample efficiency due to high-dimensional observations in complex tasks. While existing works have shown that vision-language models (VLMs) can assist RL, they often focus on knowledge distillation from the VLM to RL, overlooking the potential of RL-generated interaction data to...