arXiv:2510.03217v2 Announce Type: replace-cross Abstract: Agentic Automated Program Repair (APR) is increasingly tackling complex, repository-level bugs in industry, but ultimately these patches still need to be reviewed by a human before committing them to ensure they address the bug. Showing patches unlikely to be accepted can lead to substantial noise, wasting valuable developer time and […]
Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models
arXiv:2512.00590v2 Announce Type: replace-cross Abstract: Knowledge graphs (KGs) provide structured, verifiable grounding for large language models (LLMs), but current LLM-based systems commonly use KGs as auxiliary structures for text retrieval, leaving their intrinsic quality underexplored. In this work, we propose Wikontic, a multi-stage pipeline that constructs KGs from open-domain text by extracting candidate triplets with […]
SDFLoRA: Selective Decoupled Federated LoRA for Privacy-preserving Fine-tuning with Heterogeneous Clients
arXiv:2601.11219v2 Announce Type: replace-cross Abstract: Federated learning (FL) for large language models (LLMs) has attracted increasing attention as a privacy-preserving approach for adapting models over distributed data, where parameter-efficient methods such as Low-Rank Adaptation (LoRA) are widely adopted to reduce communication and memory costs. However, practical deployments often exhibit rank and data heterogeneity: clients operate […]
NeuraLSP: An Efficient and Rigorous Neural Left Singular Subspace Preconditioner for Conjugate Gradient Methods
arXiv:2601.20174v2 Announce Type: replace-cross Abstract: Numerical techniques for solving partial differential equations (PDEs) are integral for many fields across science and engineering. Such techniques usually involve solving large, sparse linear systems, where preconditioning methods are critical. In recent years, neural methods, particularly graph neural networks (GNNs), have demonstrated their potential through accelerated convergence. Nonetheless, to […]
ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
arXiv:2601.21947v1 Announce Type: new Abstract: Prevalent retrieval-based tool-use pipelines struggle with a dual semantic challenge: their retrievers often employ encoders that fail to capture complex semantics, while the Large Language Model (LLM) itself lacks intrinsic tool knowledge from its natural language pretraining. Generative methods offer a powerful alternative by unifying selection and execution, tasking the […]
CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty
arXiv:2601.22027v1 Announce Type: new Abstract: Existing benchmarks for Large Language Model (LLM) agents focus on task completion under idealistic settings but overlook reliability in real-world, user-facing applications. In domains, such as in-car voice assistants, users often issue incomplete or ambiguous requests, creating intrinsic uncertainty that agents must manage through dialogue, tool use, and policy adherence. […]
Heterogeneous Vertiport Selection Optimization for On-Demand Air Taxi Services: A Deep Reinforcement Learning Approach
arXiv:2601.21316v1 Announce Type: cross Abstract: Urban Air Mobility (UAM) has emerged as a transformative solution to alleviate urban congestion by utilizing low-altitude airspace, thereby reducing pressure on ground transportation networks. To enable truly efficient and seamless door-to-door travel experiences, UAM requires close integration with existing ground transportation infrastructure. However, current research on optimal integrated routing […]
L$^3$: Large Lookup Layers
arXiv:2601.21461v1 Announce Type: cross Abstract: Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP “experts.” However, dynamic hard routing has a number of drawbacks, such as potentially poor hardware efficiency and needing auxiliary losses for stable training. In contrast, the tokenizer embedding table, which is natively […]
Can Neural Networks Learn Small Algebraic Worlds? An Investigation Into the Group-theoretic Structures Learned By Narrow Models Trained To Predict Group Operations
arXiv:2601.21150v1 Announce Type: cross Abstract: While a real-world research program in mathematics may be guided by a motivating question, the process of mathematical discovery is typically open-ended. Ideally, exploration needed to answer the original question will reveal new structures, patterns, and insights that are valuable in their own right. This contrasts with the exam-style paradigm […]
Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks
arXiv:2601.21242v1 Announce Type: cross Abstract: Motivated by challenges in conditional generative modeling, where the target conditional density takes the form of a ratio f1 over f2, this paper develops a theoretical framework for approximating such ratio-type functionals. Here, f1 and f2 are kernel-based marginal densities that capture structured interactions, a setting central to diffusion-based generative […]
SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Model
arXiv:2601.21031v1 Announce Type: cross Abstract: Current foundation model for photoplethysmography (PPG) signals is challenged by the intrinsic redundancy and noise of the signal. Standard masked modeling often yields trivial solutions while contrastive methods lack morphological precision. To address these limitations, we propose a Statistical-prior Informed Generative Masking Architecture (SIGMA-PPG), a generative foundation model featuring a […]
LSR-Net: A Lightweight and Strong Robustness Network for Bearing Fault Diagnosis in Noise Environment
arXiv:2601.10761v1 Announce Type: cross Abstract: Rotating bearings play an important role in modern industries, but have a high probability of occurrence of defects because they operate at high speed, high load, and poor operating environments. Therefore, if a delay time occurs when a bearing is diagnosed with a defect, this may cause economic loss and […]