Stay updated with the latest research and technology news
arXiv:2602.03789v1 Announce Type: cross Abstract: Stochastic interpolants unify flows and diffusions, popular generative modeling frameworks. A primary hyperparameter in these methods is the interpolation schedule...
arXiv:2602.03823v1 Announce Type: cross Abstract: We introduce a new preference-based framework for conditional treatment effect estimation and policy learning, built on the Conditional Preference-based Treatment...
arXiv:2602.03824v1 Announce Type: cross Abstract: The evolution of biological morphology is critical for understanding the diversity of the natural world, yet traditional analyses often involve...
arXiv:2602.03833v1 Announce Type: cross Abstract: We show that every graph $G$ excluding an apex-forest $H$ as a minor has layered pathwidth at most $|V(H)|-2$, and...
arXiv:1711.00282v4 Announce Type: replace Abstract: We study the complexity of approximating the independent set polynomial $Z_G(\lambda)$ of a graph $G$ with maximum degree $\Delta$ when...
arXiv:2110.08902v5 Announce Type: replace Abstract: Experience replay is a core ingredient of modern deep reinforcement learning, yet its benefits in policy optimization are poorly understood...
arXiv:2201.02514v3 Announce Type: replace Abstract: Asymmetric Numeral Systems (ANS) is a class of entropy encoders that had an immense impact on the data compression, substituting...
arXiv:2202.11663v4 Announce Type: replace Abstract: The concept of programmable matter envisions a very large number of tiny and simple robot particles forming a smart material....
arXiv:2301.07473v3 Announce Type: replace Abstract: Many types of data from fields including natural language processing, computer vision, and bioinformatics, are well represented by discrete, compositional...
arXiv:2301.12412v4 Announce Type: replace Abstract: We introduce a unified framework for contextual and causal Bayesian optimisation, which aims to design intervention policies maximising the expectation...
arXiv:2304.04914v5 Announce Type: replace Abstract: Appropriately regulating artificial intelligence is an increasingly urgent and widespread policy challenge. We identify two primary, competing problem. First is...
arXiv:2305.11408v3 Announce Type: replace Abstract: Attention is the core mechanism of today's most used architectures for natural language processing and has been analyzed from many...
arXiv:2403.13393v5 Announce Type: replace Abstract: On the one side, the formalism of Global Transformations comes with the claim of capturing any transformation of space that...
arXiv:2405.02162v5 Announce Type: replace Abstract: Panoptic maps enable robots to reason about both geometry and semantics. However, open-vocabulary models repeatedly produce closely related labels that...
arXiv:2405.09125v2 Announce Type: replace Abstract: Scene Text Recognition (STR) is challenging in extracting effective character representations from visual data when text is unreadable. Permutation language...
arXiv:2405.14273v4 Announce Type: replace Abstract: A data-driven inverse optimization problem (DDIOP) seeks to estimate an objective function (i.e., weights) that is consistent with observed optimal-solution...
arXiv:2405.15743v3 Announce Type: replace Abstract: Several challenges make it difficult for sparse neural networks to compete with dense models. First, setting a large fraction of...
arXiv:2405.18605v2 Announce Type: replace Abstract: The extraction of chemical-gene relations plays a pivotal role in understanding the intricate interactions between chemical compounds and genes, with...
arXiv:2406.13930v4 Announce Type: replace Abstract: Multi-agent credit assignment is a fundamental challenge for cooperative multi-agent reinforcement learning (MARL), where a team of agents learn from...
arXiv:2406.15163v3 Announce Type: replace Abstract: Sentiment Analysis (SA) is a crucial aspect of Natural Language Processing (NLP), focusing on identifying and interpreting subjective assessments in...
arXiv:2407.03094v4 Announce Type: replace Abstract: Uncertainty quantification of causal effects is crucial for safety-critical applications such as personalized medicine. A powerful approach for this is...
arXiv:2409.00592v4 Announce Type: replace Abstract: The rapid growth of large models' size has far outpaced that of computing resources. To bridge this gap, encouraged by...
arXiv:2409.15113v3 Announce Type: replace Abstract: We address the fundamental task of inferring cross-document coreference and hierarchy in scientific texts, which has important applications in knowledge...
arXiv:2410.01615v2 Announce Type: replace Abstract: Existing approaches for video moment retrieval and highlight detection are not able to align text and video features efficiently, resulting...