📰 AI News

arXiv:2603.25686v1 Announce Type: cross Abstract: Cross-view geo-localization (CVGL) estimates a camera's location by matching a street-view image to geo-refere

arXiv:2603.25692v1 Announce Type: cross Abstract: Trustworthy artificial intelligence increasingly relies on probabilistic computation to achieve robustness, in

arXiv:2603.25697v1 Announce Type: cross Abstract: Code production is now a commodity; the bottleneck is knowing what to build and proving it works. We present t

arXiv:2603.25699v1 Announce Type: cross Abstract: Transfer learning and knowledge distillation has recently gained a lot of attention in the deep learning commu

arXiv:2603.25716v1 Announce Type: cross Abstract: Video world models have shown immense potential in simulating the physical world, yet existing memory mechanis

arXiv:2603.25723v1 Announce Type: cross Abstract: Agent performance increasingly depends on \emph{harness engineering}, yet harness design is usually buried in

arXiv:2603.25728v1 Announce Type: cross Abstract: Fine-grained facial expression editing has long been limited by intrinsic semantic overlap. To address this, w

arXiv:2603.25730v1 Announce Type: cross Abstract: Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by i

arXiv:2603.25740v1 Announce Type: cross Abstract: Human driving behavior is inherently personal, which is shaped by long-term habits and influenced by short-ter

arXiv:2603.25741v1 Announce Type: cross Abstract: Vision-language-action models have reshaped autonomous driving to incorporate languages into the decision-maki

arXiv:2410.20894v3 Announce Type: replace Abstract: Artificial General Intelligence (AGI) Agents and Robots must be able to cope with everchanging environments

arXiv:2411.01029v2 Announce Type: replace Abstract: Strong solving of perfect-information games certifies optimal play from every reachable position, but the re

arXiv:2501.04480v2 Announce Type: replace Abstract: The convergence of drone delivery systems, virtual worlds, and blockchain has transformed logistics and supp

arXiv:2503.03361v3 Announce Type: replace Abstract: Early in development, infants learn to extract surprisingly complex aspects of visual scenes. This early lea

arXiv:2504.15780v3 Announce Type: replace Abstract: Geometric problem solving (GPS) requires precise multimodal understanding and rigorous, step-by-step logical

arXiv:2506.22609v2 Announce Type: replace Abstract: Games have long been used as benchmarks and testing environments for research in artificial intelligence. A

arXiv:2508.13663v4 Announce Type: replace Abstract: Methods for query answering over incomplete knowledge graphs retrieve entities that are \emph{likely} to be

arXiv:2509.03345v2 Announce Type: replace Abstract: Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex

arXiv:2509.23768v2 Announce Type: replace Abstract: The chemical reaction recommendation is to select proper reaction condition parameters for chemical reaction

arXiv:2510.18087v2 Announce Type: replace Abstract: Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion langua

arXiv:2511.07436v2 Announce Type: replace Abstract: The integration of AI tools into medical applications has aimed to improve the efficiency of diagnosis. The

arXiv:2601.04426v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on dynamic structured generation, such as tool calling and response prot

arXiv:2603.08561v4 Announce Type: replace Abstract: Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rew

arXiv:2603.15017v2 Announce Type: replace Abstract: Because human preferences are too complex to codify, AIs operate with misspecified objectives. Optimizing su