Stay updated with the latest research and technology news
arXiv:2508.13904v3 Announce Type: replace Abstract: Diffusion Q-Learning (DQL) has established diffusion policies as a high-performing paradigm for offline reinforcement learning, but its reliance on multi-step...
arXiv:2508.16815v2 Announce Type: replace Abstract: This paper introduces Uncertainty Propagation Network (UPN), a novel family of neural differential equations that naturally incorporate uncertainty quantification into...
arXiv:2508.17404v3 Announce Type: replace Abstract: Existing video generation models predominantly emphasize appearance fidelity while exhibiting limited ability to synthesize complex human motions, such as whole-body...
arXiv:2508.18632v2 Announce Type: replace Abstract: Cancer survival analysis commonly integrates information across diverse medical modalities to make survival-time predictions. Existing methods primarily focus on extracting...
arXiv:2508.19113v2 Announce Type: replace Abstract: Large reasoning models (LRMs) combined with retrieval-augmented generation (RAG) have enabled deep research agents capable of multi-step reasoning with external...
arXiv:2508.21785v3 Announce Type: replace Abstract: Heart rate prediction is vital for personalized health monitoring and fitness, while it frequently faces a critical challenge in real-world...
arXiv:2509.01856v4 Announce Type: replace Abstract: Navigating unsignalized roundabouts in mixed-autonomy traffic presents significant challenges due to dense vehicle interactions, lane-changing complexities, and behavioral uncertainties of...
arXiv:2509.07411v2 Announce Type: replace Abstract: Modern transportation systems face significant challenges in ensuring road safety, given serious injuries caused by road accidents. The rapid growth...
arXiv:2509.07797v2 Announce Type: replace Abstract: In this paper, we perform a theoretical analysis of the sequential convergence of elementary cellular automata that have at least...
arXiv:2509.08435v2 Announce Type: replace Abstract: Diffusion models offer powerful generative capabilities for robot trajectory planning, yet their practical deployment on robots is hindered by a...
arXiv:2509.08767v3 Announce Type: replace Abstract: Budget aggregation deals with the social choice problem of distributing an exogenously given budget among a set of public projects,...
arXiv:2509.12142v2 Announce Type: replace Abstract: This paper investigates an information-theoretic model of secure semantic-aware communication. For this purpose, we consider the lossy joint source-channel coding...
arXiv:2509.12261v2 Announce Type: replace Abstract: This paper addresses the Longest Filled Common Subsequence (LFCS) problem, a challenging NP-hard problem with applications in bioinformatics, including gene...
arXiv:2509.14297v2 Announce Type: replace Abstract: This study reveals a critical safety blind spot in modern LLMs: learning-style queries, which closely resemble ordinary educational questions, can...
arXiv:2509.15148v3 Announce Type: replace Abstract: Large language models (LLMs) benefit from test-time scaling but are often hampered by high inference latency. Speculative decoding is a...
arXiv:2509.15796v2 Announce Type: replace Abstract: The goal of protein design is to generate amino acid sequences that fold into functional structures with desired properties. Prior...
arXiv:2509.19975v2 Announce Type: replace Abstract: Most state-of-the-art probabilistic time series forecasting models rely on sampling to represent future uncertainty. However, this paradigm suffers from inherent...
arXiv:2509.21825v4 Announce Type: replace Abstract: While large language models (LLMs) have shown promise in automating data science, existing agents often struggle with the complexity of...
arXiv:2509.21895v2 Announce Type: replace Abstract: We derive a new Rademacher complexity bound for deep neural networks using Koopman operators, group representations, and reproducing kernel Hilbert...
arXiv:2509.22566v2 Announce Type: replace Abstract: Despite its recent successes, Deep Reinforcement Learning (DRL) is notoriously sample-inefficient. We argue that this inefficiency stems from the standard...
arXiv:2509.23115v3 Announce Type: replace Abstract: Predicting human mobility is inherently challenging due to complex long-range dependencies and multi-scale periodic behaviors. To address this, we introduce...
arXiv:2509.23513v4 Announce Type: replace Abstract: When one wishes to numerically solve an initial value problem, it is customary to rewrite it as an equivalent first-order...
arXiv:2509.23834v2 Announce Type: replace Abstract: Differential privacy (DP) has become the gold standard for preserving individual privacy in data analysis. However, an implicit yet fundamental...
arXiv:2509.24803v3 Announce Type: replace Abstract: Recent advances in multimodal time series learning underscore a paradigm shift from analytics centered on basic patterns toward advanced time...