Stay updated with the latest research and technology news
arXiv:2510.02180v2 Announce Type: replace Abstract: Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult...
arXiv:2510.04480v2 Announce Type: replace Abstract: The Constraint-satisfaction problem (CSP) is fundamental in mathematics, physics, and theoretical computer science. Continuous local search (CLS) solvers, as recent...
arXiv:2510.05580v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models show promise in embodied reasoning, yet remain far from true generalists-they often require task-specific fine-tuning, incur high...
arXiv:2510.06165v2 Announce Type: replace Abstract: Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an...
arXiv:2510.07118v2 Announce Type: replace Abstract: Instruction tuning is essential for aligning large language models (LLMs) to downstream tasks and commonly relies on large, diverse corpora....
arXiv:2510.07922v3 Announce Type: replace Abstract: Decentralized Federated Learning enables privacy-preserving collaborative training without centralized servers but remains vulnerable to Byzantine attacks. Existing defenses require exchanging...
arXiv:2510.09695v2 Announce Type: replace Abstract: Logical fallacies are common in public communication and can mislead audiences; fallacious arguments may still appear convincing despite lacking soundness,...
arXiv:2510.09718v2 Announce Type: replace Abstract: We study federated clustering, where interconnected devices collaboratively cluster the data points of private local datasets. Focusing on hard clustering...
arXiv:2510.09885v3 Announce Type: replace Abstract: Large language models (LLMs) are often used in environments where facts evolve, yet factual knowledge updates via fine-tuning on unstructured...
arXiv:2510.10631v2 Announce Type: replace Abstract: Linear attention mechanisms have emerged as efficient alternatives to full self-attention in Graph Transformers, offering linear time complexity. However, existing...
arXiv:2510.12312v2 Announce Type: replace Abstract: Safe policy improvement (SPI) offers theoretical control over policy updates, yet existing guarantees largely concern offline, tabular reinforcement learning (RL)....
arXiv:2510.12414v2 Announce Type: replace Abstract: Steganographic schemes dedicated to generated images modify the seed vector in the latent space to embed a message. Whereas most...
arXiv:2510.12603v2 Announce Type: replace Abstract: Multimodal reasoning aims to enhance the capabilities of MLLMs by incorporating intermediate reasoning steps before reaching the final answer. It...
arXiv:2510.12605v2 Announce Type: replace Abstract: Underwater Salient Object Detection (USOD) faces significant challenges, including underwater image quality degradation and domain gaps. Existing methods tend to...
arXiv:2510.13907v2 Announce Type: replace Abstract: Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization (APO) methods assume access to ground-truth...
arXiv:2510.14398v3 Announce Type: replace Abstract: Large language models (LLMs) trained for general \textit{next-token prediction} often fail to generate responses that reflect how specific individuals communicate....
arXiv:2510.18439v2 Announce Type: replace Abstract: Hallucination, where models generate fluent text unsupported by visual evidence, remains a major flaw in vision-language models and is particularly...
arXiv:2510.18714v2 Announce Type: replace Abstract: This paper addresses metric 3D reconstruction of indoor scenes by exploiting their inherent geometric regularities with compact representations. Using planar...
arXiv:2510.20518v2 Announce Type: replace Abstract: AI-based sensing at wireless edge devices has the potential to significantly enhance Artificial Intelligence (AI) applications, particularly for vision and...
arXiv:2510.20707v2 Announce Type: replace Abstract: Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion...
arXiv:2510.22848v2 Announce Type: replace Abstract: Self-induced stochastic resonance (SISR) is the emergence of coherent oscillations in slow-fast excitable systems driven solely by noise, without external...
arXiv:2510.23530v2 Announce Type: replace Abstract: Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or...
arXiv:2510.24810v2 Announce Type: replace Abstract: Fact-checking on major platforms, such as X, Meta, and TikTok, is shifting from expert-driven verification to a community-based setup, where...
arXiv:2510.26844v2 Announce Type: replace Abstract: Existing semantic communication schemes primarily focus on single-hop scenarios, overlooking the challenges of multi-hop wireless image transmission. As semantic communication...