Stay updated with the latest research and technology news
arXiv:2602.05805v1 Announce Type: new Abstract: Large language models increasingly spend inference compute sampling multiple chain-of-thought traces or searching over merged checkpoints. This shifts the bottleneck...
arXiv:2602.05809v1 Announce Type: new Abstract: Vision-language models (VLMs) often generate massive visual tokens that greatly increase inference latency and memory footprint; while training-free token pruning...
arXiv:2602.05810v1 Announce Type: new Abstract: Autonomous agents excel in self-improvement through reflection and iterative refinement, which reuse successful task trajectories as in-context examples to assist...
arXiv:2602.05811v1 Announce Type: new Abstract: The integration of spatial multi-omics data from single tissues is crucial for advancing biological research. However, a significant data imbalance...
arXiv:2602.05812v1 Announce Type: new Abstract: We present a principled framework for confidence estimation in computed tomography (CT) reconstruction. Based on the sequential likelihood mixing framework...
arXiv:2602.05813v1 Announce Type: new Abstract: We study adaptive learning rate scheduling for norm-constrained optimizers (e.g., Muon and Lion). We introduce a generalized smoothness assumption under...
arXiv:2602.05817v1 Announce Type: new Abstract: The rapid expansion of Internet of Things (IoT) ecosystems has led to increasingly complex and heterogeneous network topologies. Traditional network...
arXiv:2602.05818v1 Announce Type: new Abstract: Temporal knowledge graph question answering (TKGQA) aims to answer time-sensitive questions by leveraging temporal knowledge bases. While Large Language Models...
arXiv:2602.05819v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as collaborative partners in writing. However, this raises a critical challenge of authorship,...
arXiv:2602.05822v1 Announce Type: new Abstract: We propose NVS-HO, the first benchmark designed for novel view synthesis of handheld objects in real-world environments using only RGB...
arXiv:2602.05825v1 Announce Type: new Abstract: Generative AI often produces results misaligned with user intentions, for example, resolving ambiguous prompts in unexpected ways. Despite existing approaches...
arXiv:2602.05826v1 Announce Type: new Abstract: Large-scale outdoor mixed reality (MR) art exhibitions distribute curated virtual works across open public spaces, but interpretation rarely scales without...
arXiv:2602.05827v1 Announce Type: new Abstract: Why must vision-language navigation be bound to detailed and verbose language instructions? While such details ease decision-making, they fundamentally contradict...
arXiv:2602.05829v1 Announce Type: new Abstract: Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving...
arXiv:2602.05830v1 Announce Type: new Abstract: Floating-point neural networks dominate modern machine learning but incur substantial inference cost, motivating interest in Boolean networks for resource-constrained settings....
arXiv:2602.05832v1 Announce Type: new Abstract: Online Reinforcement Learning (RL) offers a promising paradigm for enhancing GUI agents through direct environment interaction. However, its effectiveness is...
arXiv:2602.05833v1 Announce Type: new Abstract: There is a need for synthetic training and test datasets that replicate statistical distributions of original datasets without compromising their...
arXiv:2602.05835v1 Announce Type: new Abstract: We study a stylized social learning dynamics where self-interested agents collectively follow a simple multi-armed bandit protocol. Each agent controls...
arXiv:2602.05836v1 Announce Type: new Abstract: In response to the 2008 global financial crisis, Science Foundation Ireland (SFI), now Research Ireland, pivoted to research with potential...
arXiv:2602.05837v1 Announce Type: new Abstract: Synchrotron facilities like the Cornell High Energy Synchrotron Source (CHESS) generate massive data volumes from complex beamline experiments, but face...
arXiv:2602.05838v1 Announce Type: new Abstract: Data is the lifeblood of AI, yet much of the most valuable data remains locked in silos due to privacy...
arXiv:2602.05842v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance in language-centric tasks. However, in agentic settings, LLMs often struggle to anticipate...
arXiv:2602.05843v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments....
arXiv:2602.05845v1 Announce Type: new Abstract: Self-supervised learning (SSL) methods based on Siamese networks learn visual representations by aligning different views of the same image. The...