Stay updated with the latest research and technology news
arXiv:2411.09109v4 Announce Type: replace Abstract: AIs can beat humans in game environments; however, how helpful those agents are to human remains understudied. We augment CICERO,...
arXiv:2411.11707v2 Announce Type: replace Abstract: By adapting Large Language Models (LLMs) to domain-specific tasks or enriching them with domain-specific knowledge, we can fully harness the...
arXiv:2411.15702v4 Announce Type: replace Abstract: Interactive computer vision (CV) plays a crucial role in various real-world applications, whose performance is highly dependent on communication networks....
arXiv:2411.16076v2 Announce Type: replace Abstract: Neural representations of 3D data have been widely adopted across various applications, particularly in recent work leveraging coordinate-based networks to...
arXiv:2411.17195v2 Announce Type: replace Abstract: Visual servoing techniques guide robotic motion using visual information to accomplish manipulation tasks, requiring high precision and robustness against noise....
arXiv:2411.17411v2 Announce Type: replace Abstract: Combinatorics studies how discrete objects can be counted, arranged, and combined under specified rules. Motivated by uncertainty in real-world data...
arXiv:2412.04272v4 Announce Type: replace Abstract: In recent years, table reasoning has garnered substantial research interest, particularly regarding its integration with Large Language Models (LLMs), which...
arXiv:2412.06106v3 Announce Type: replace Abstract: One of the key challenges in Transformer architectures is the quadratic complexity of the attention mechanism, which limits the efficient...
arXiv:2412.06117v3 Announce Type: replace Abstract: We further develop the formal foundations of Paraconsistent Belief Revision (PBR) by introducing Logics of Formal Inconsistency (LFIs) specifically designed...
arXiv:2412.07341v3 Announce Type: replace Abstract: HyperQPTL and HyperQPTL$^+$ are expressive specification languages for hyperproperties, properties that relate multiple executions of a system. Tight complexity bounds...
arXiv:2412.09355v3 Announce Type: replace Abstract: Entity resolution (ER) is a fundamental task in data integration that enables insights from heterogeneous data sources. The primary challenge...
arXiv:2412.15472v2 Announce Type: replace Abstract: Allocating indivisible goods is a ubiquitous task in fair division. We study additive welfarist rules, an important class of rules...
arXiv:2412.17596v4 Announce Type: replace Abstract: While Large Language Models (LLMs) demonstrate remarkable capabilities in scientific tasks such as literature analysis and experimental design (e.g., accurately...
arXiv:2501.00339v4 Announce Type: replace Abstract: Recent studies have demonstrated that many layers are functionally redundant in large language models (LLMs), enabling model compression by removing...
arXiv:2501.00773v2 Announce Type: replace Abstract: Graphs are fundamental data structures for modeling complex interactions in domains such as social networks, molecular structures, and biological systems....
arXiv:2501.06336v2 Announce Type: replace Abstract: We introduce MEt3R, a metric for multi-view consistency in generated images. Large-scale generative models for multi-view image generation are rapidly...
arXiv:2501.10471v2 Announce Type: replace Abstract: Clustering large high-dimensional datasets with diverse variable is essential for extracting high-level latent information from these datasets. Here, we developed...
arXiv:2501.13192v2 Announce Type: replace Abstract: In this article, we establish a comprehensive theoretical framework for remote estimation in a networked system composed of a source...
arXiv:2501.15461v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have shown great success in various graph-based learning tasks. However, it often faces the issue of...
arXiv:2501.17860v2 Announce Type: replace Abstract: Current medical AI systems often fail to replicate real-world clinical reasoning, as they are predominantly trained and evaluated on static...
arXiv:2502.03771v5 Announce Type: replace Abstract: Semantic caches return cached responses for semantically similar prompts to reduce LLM inference latency and cost. They embed cached prompts...
arXiv:2502.04591v4 Announce Type: replace Abstract: Oversmoothing is a fundamental challenge in graph neural networks (GNNs): as the number of layers increases, node embeddings become increasingly...
arXiv:2502.05795v5 Announce Type: replace Abstract: In this paper, we introduce the Curse of Depth, a concept that highlights, explains, and addresses the recent observation in...
arXiv:2502.08047v4 Announce Type: replace Abstract: Recent progress in GUI agents has substantially improved visual grounding, yet robust planning remains challenging, particularly when the environment deviates...