Stay updated with the latest research and technology news
arXiv:2511.16943v2 Announce Type: replace Abstract: Generative recommendation systems typically leverage Semantic Identifiers (SIDs), which represent each item as a sequence of tokens that encode semantic...
arXiv:2511.17044v2 Announce Type: replace Abstract: Parametric Retrieval-Augmented Generation (PRAG) is a RAG approach that integrates external knowledge directly into model parameters using a LoRA adapter,...
arXiv:2511.18247v2 Announce Type: replace Abstract: We derive instance-dependent tail bounds for the regret of optimism-based reinforcement learning in finite-horizon tabular Markov decision processes with unknown...
arXiv:2511.18267v2 Announce Type: replace Abstract: Residential buildings are increasingly integrating large devices that run natively on direct current (DC), such as solar photovoltaics, electric vehicles,...
arXiv:2511.18413v3 Announce Type: replace Abstract: Agentic recommendations cast recommenders as large language model (LLM) agents that can plan, reason, use tools, and interact with users...
arXiv:2511.18894v3 Announce Type: replace Abstract: Medical image segmentation is crucial for clinical applications, but it is frequently disrupted by noisy annotations and ambiguous anatomical boundaries,...
arXiv:2511.19233v2 Announce Type: replace Abstract: Localization is increasingly becoming an integral component of wireless cellular networks. The advent of artificial intelligence (AI) and machine learning...
arXiv:2511.21448v3 Announce Type: replace Abstract: Phishing and spam emails remain a major cybersecurity threat, with attackers increasingly leveraging Large Language Models (LLMs) to craft highly...
arXiv:2511.22690v2 Announce Type: replace Abstract: Despite recent advances in text-to-image generation, existing models consistently fail to produce reliable multi-human scenes, often duplicating faces, merging identities,...
arXiv:2512.01556v2 Announce Type: replace Abstract: Foundation models often generate unreliable answers, while heuristic uncertainty estimators fail to fully distinguish correct from incorrect outputs, causing users...
arXiv:2512.01557v2 Announce Type: replace Abstract: This study examines the digital representation of African languages and the challenges this presents for current language detection tools. We...
arXiv:2512.01628v2 Announce Type: replace Abstract: Existing two-stage fourth-order (TSFO) methods are confined to explicit frameworks and can only be applied to homogeneous hydrodynamic problems describing...
arXiv:2512.03470v4 Announce Type: replace Abstract: Infrared small target detection (ISTD) faces two major challenges: a lack of discernible target texture and severe background clutter, which...
arXiv:2512.04552v2 Announce Type: replace Abstract: Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward...
arXiv:2512.05742v2 Announce Type: replace Abstract: This memorandum analyzes and stress-tests arguments in favor and against the inclusion of internal deployment within the scope of the...
arXiv:2512.05790v3 Announce Type: replace Abstract: We develop a theoretical framework that explains how gating mechanisms determine the learnability window $\mathcal{H}_N$ of recurrent neural networks, defined...
arXiv:2512.07076v3 Announce Type: replace Abstract: Camouflage is primarily context-dependent yet current metrics for camouflaged scenarios overlook this critical factor. Instead, these metrics are originally designed...
arXiv:2512.09101v2 Announce Type: replace Abstract: We present Masked Generative Policy (MGP), a novel framework for visuomotor imitation learning. We represent actions as discrete tokens, and...
arXiv:2512.10046v3 Announce Type: replace Abstract: Recent advances in foundation models have shown promising results in developing generalist robotics that can perform diverse tasks in open-ended...
arXiv:2512.10408v2 Announce Type: replace Abstract: The rapid growth of video content on platforms such as TikTok and YouTube has intensified the spread of multimodal hate...
arXiv:2512.10481v2 Announce Type: replace Abstract: Contact-rich manipulation is difficult for robots to execute and requires accurate perception of the environment. In some scenarios, vision is...
arXiv:2512.11654v2 Announce Type: replace Abstract: The acquisition cost for large, annotated motion datasets remains a critical bottleneck for skeletal-based Human Activity Recognition (HAR). Although Text-to-Motion...
arXiv:2512.11908v2 Announce Type: replace Abstract: Contact-rich tasks pose significant challenges for robotic systems due to inherent uncertainty, complex dynamics, and the high risk of damage...
arXiv:2512.12210v2 Announce Type: replace Abstract: Large-scale EEG foundation models have shown strong generalization across a range of downstream tasks, but their training remains resource-intensive due...