Stay updated with the latest research and technology news
arXiv:2503.03505v2 Announce Type: replace Abstract: Recent advancements in Large Language Model~(LLM)-based Multi-Agent Systems (MAS) have demonstrated remarkable potential for tackling complex decision-making tasks. However, existing...
arXiv:2503.09820v2 Announce Type: replace Abstract: We introduce ViLAM, a novel method for distilling vision-language reasoning from large Vision-Language Models (VLMs) into spatial attention maps for...
arXiv:2503.10110v3 Announce Type: replace Abstract: Motion planning involves determining a sequence of robot configurations to reach a desired pose, subject to movement and safety constraints....
arXiv:2503.10336v2 Announce Type: replace Abstract: Characterizing the long term behavior of dynamical systems given limited measurements is a common challenge throughout the physical and biological...
arXiv:2503.11126v3 Announce Type: replace Abstract: The problem of relevant and diverse subset selection has a wide range of applications, including recommender systems and retrieval-augmented generation...
arXiv:2503.11978v2 Announce Type: replace Abstract: Despite the increasing popularity of avatar systems such as Snapchat Bitmojis, existing production avatar platforms face several limitations, such as...
arXiv:2503.14488v3 Announce Type: replace Abstract: Engineering information systems for scientific data analysis presents significant challenges: complex workflows requiring exploration of large solution spaces, close collaboration...
arXiv:2503.14756v3 Announce Type: replace Abstract: Despite recent advances in text-conditioned 3D indoor scene generation, there remain gaps in the evaluation of these methods. Existing metrics...
arXiv:2503.14824v2 Announce Type: replace Abstract: The traditional paradigm to update retrieval models requires re-computing the embeddings of the gallery data, a time-consuming and computationally intensive...
arXiv:2503.15904v4 Announce Type: replace Abstract: Large Language Models (LLMs) have revolutionized natural language processing, yet concerns persist regarding their tendency to reflect or amplify social...
arXiv:2503.17788v3 Announce Type: replace Abstract: Two-hand reconstruction from monocular images is hampered by complex poses and severe occlusions, which often cause interaction misalignment and two-hand...
arXiv:2503.21210v3 Announce Type: replace Abstract: Accurate and interpretable detection of AI-generated images is essential for mitigating risks associated with AI misuse. However, the substantial domain...
arXiv:2503.21361v2 Announce Type: replace Abstract: This paper considers the problem of detecting adjoint mismatch for two linear maps. To clarify, this means that we aim...
arXiv:2503.22233v4 Announce Type: replace Abstract: We introduce the Entropy-Driven Uncertainty Process Reward Model (EDU-PRM), a novel entropy-driven training framework for process reward modeling that enables...
arXiv:2503.22769v2 Announce Type: replace Abstract: Artificial Intelligence (AI) has been advancing rapidly and with the advent of large language models (LLMs) in late 2022, numerous...
arXiv:2504.02637v3 Announce Type: replace Abstract: Medium access in 5G systems was tailored to accommodate diverse traffic classes through network resource slicing. 6G wireless systems are...
arXiv:2504.04700v2 Announce Type: replace Abstract: Recent advancements in large language models (LLMs) have significantly enhanced the performance of conversational AI systems. To extend their capabilities...
arXiv:2504.05089v3 Announce Type: replace Abstract: Deep learning on climatic data holds potential for macroecological applications. However, its adoption remains limited among scientists outside the deep...
arXiv:2504.05698v2 Announce Type: replace Abstract: Recent point-based object completion methods have demonstrated the ability to accurately recover the missing geometry of partially observed objects. However,...
arXiv:2504.06254v3 Announce Type: replace Abstract: We present a new technique, Safe Concurrent Optimistic Traversals (SCOT), to address a well-known problem related to optimistic traversals with...
arXiv:2504.08804v2 Announce Type: replace Abstract: Estimating item difficulty through field-testing is often resource-intensive and time-consuming. As such, there is strong motivation to develop methods that...
arXiv:2504.09021v2 Announce Type: replace Abstract: Deep reinforcement learning has achieved superhuman racing performance in high-fidelity simulators like Gran Turismo 7 (GT7). It typically utilizes global...
arXiv:2504.09156v4 Announce Type: replace Abstract: Accurate and efficient recognition of emotional states is critical for human social functioning, and impairments in this ability are associated...
arXiv:2504.09452v2 Announce Type: replace Abstract: We present an adaptive approximation scheme for jump-diffusion SDEs with discontinuous drift and (possibly) degenerate diffusion. This transformation-based doubly-adaptive quasi-Milstein...