Stay updated with the latest research and technology news
arXiv:2504.18913v2 Announce Type: replace Abstract: A common approach to approximating quadratic forms of matrix functions is to use a quadrature rule derived from the Lanczos...
arXiv:2505.00554v4 Announce Type: replace Abstract: Two candidate approaches for univariate sumcheck over roots of unity are presented. The first takes the form of a multilinear...
arXiv:2505.00570v3 Announce Type: replace Abstract: Existing key-value (KV) cache compression methods for large language models (LLMs) often rely on token eviction, which risks losing critical...
arXiv:2505.03797v2 Announce Type: replace Abstract: Partial Bayesian neural networks (pBNNs) have been shown to perform competitively with fully Bayesian neural networks while only having a...
arXiv:2505.05029v3 Announce Type: replace Abstract: Cooperation has long been a fundamental topic in both human society and AI systems. However, recent studies indicate that the...
arXiv:2505.05428v3 Announce Type: replace Abstract: Agentic systems, in which diverse agents cooperate to tackle challenging problems, are exploding in popularity in the AI community. However,...
arXiv:2505.07789v2 Announce Type: replace Abstract: We develop dualities for complete perfect distributive quasi relation algebras and complete perfect distributive involutive FL-algebras. The duals are partially...
arXiv:2505.09857v4 Announce Type: replace Abstract: This work introduces the High-Order Hermite Optimization (HOHO) method, an open-loop discrete adjoint method for quantum optimal control. Our method...
arXiv:2505.11766v3 Announce Type: replace Abstract: Neural Operators (NOs) have emerged as powerful tools for learning mappings between function spaces. Among them, the kernel integral operator...
arXiv:2505.12129v2 Announce Type: replace Abstract: We introduce the first graph kernels for metric graphs via tropical algebraic geometry. In contrast to conventional graph kernels based...
arXiv:2505.13140v2 Announce Type: replace Abstract: Many density estimation techniques for 3D human motion prediction require a significant amount of inference time, often exceeding the duration...
arXiv:2505.13258v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) delivers substantial value in knowledge-intensive applications. However, its generated responses often lack transparent reasoning paths that trace...
arXiv:2505.13357v2 Announce Type: replace Abstract: Accelerating Machine Learning (ML) workloads requires efficient methods due to their large optimization space. Autotuning has emerged as an effective...
arXiv:2505.15183v2 Announce Type: replace Abstract: Inspired by a proposal made almost ten years ago, this paper presents a model for classifying per-sonal data for research...
arXiv:2505.15255v5 Announce Type: replace Abstract: Mental manipulation on social media poses a covert yet serious threat to individuals' psychological well-being and the integrity of online...
arXiv:2505.15998v3 Announce Type: replace Abstract: We present a method for the automated discovery of system-level dynamics in Flow-Lenia--a continuous cellular automaton (CA) with mass conservation...
arXiv:2505.17799v2 Announce Type: replace Abstract: Coreset selection targets the challenge of finding a small, representative subset of a large dataset that preserves essential patterns for...
arXiv:2505.18269v4 Announce Type: replace Abstract: We study the problem of selecting a subset from a large action space shared by a family of bandits, with...
arXiv:2505.18760v3 Announce Type: replace Abstract: Many critical information technology and cyber-physical systems rely on a supply chain of open-source software projects. OSS project maintainers often...
arXiv:2505.19236v2 Announce Type: replace Abstract: Creativity evaluation remains a challenging frontier for large language models (LLMs). Current evaluations heavily rely on inefficient and costly human...
arXiv:2505.19439v4 Announce Type: replace Abstract: Large Language Models have achieved remarkable success in natural language processing tasks, with Reinforcement Learning playing a key role in...
arXiv:2505.19497v2 Announce Type: replace Abstract: We introduce DyCO-GNN, a novel unsupervised learning framework for Dynamic Combinatorial Optimization that requires no training data beyond the problem...
arXiv:2505.19616v4 Announce Type: replace Abstract: Multimodal Large Language Models demonstrate strong performance on multimodal benchmarks, yet often exhibit poor robustness when exposed to spurious modality...
arXiv:2505.20623v2 Announce Type: replace Abstract: This study examines the discursive construction of algorithms and its role in labor management in Chinese live-streaming industry by focusing...