Evaluating the factuality of long-form generations has focused predominantly on precision, measuring whether the claims a model makes are correct. The dominant decompose-search-verify pipeline catches incorrect…
Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs…
Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform…
Asynchronous reinforcement learning improves throughput by decoupling rollout generation from optimization, but staleness is an inevitable byproduct compounded by policy lag, engine delays, and mixture-of-experts routing.…
arXiv:2607.19064v1 Announce Type: cross Abstract: Large-scale visual generators are increasingly capable but costly to train, fine-tune, and deploy. We introduce Mage-Flow, a compact 4B-scale generative stack…
arXiv:2607.19011v1 Announce Type: cross Abstract: Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural…
arXiv:2607.18432v1 Announce Type: new Abstract: This paper reports on a collaboration between the Directorate-General for Translation (DGT) and the European Master's in Translation (EMT) to localise…
arXiv:2601.15368v3 Announce Type: replace Abstract: Generative image inpainting can produce realistic results even with large, irregular masks, but existing methods still suffer from two common problems:…
arXiv:2607.18625v1 Announce Type: new Abstract: Vision Mamba models replace quadratic self-attention with linear complexity selective state space models (SSMs), emerging as efficient visual backbones. However, MambaOut…
arXiv:2607.18283v1 Announce Type: new Abstract: Accurate localization of the corpus callosum (CC) in fetal ultrasound (US) images is crucial for the early identification of neurodevelopmental abnormalities.…
arXiv:2602.10552v3 Announce Type: replace Abstract: Whereas most brain-computer interface research has focused on decoding neural signals into behavior or intent, the reverse challenge-using controlled stimuli to…
arXiv:2607.18559v1 Announce Type: new Abstract: Gaussian graphical model selection is usually studied under independent sampling, but in many applications the data arise as a single trajectory…
arXiv:2607.19219v1 Announce Type: cross Abstract: Large language models (LLMs) have been widely applied to automated essay scoring (AES) and automated feedback generation (AFG). However, existing studies…
arXiv:2607.18256v1 Announce Type: new Abstract: Optimization modeling is the process of translating real-world decision problems, often described in natural language, into formal mathematical formulations and executable…
arXiv:2607.18413v1 Announce Type: new Abstract: Large language models (LLMs) largely rely on Transformers, where self-attention provides global token interaction but does not explicitly encode the locality…
arXiv:2607.19146v1 Announce Type: cross Abstract: Cooperative perception enables autonomous vehicles (AVs) to improve situational awareness by aggregating detection outputs from multiple agents and sensing platforms, often…
arXiv:2607.18713v1 Announce Type: cross Abstract: Vision-based heading prediction is useful for UAV--UGV cooperation, but accurate prediction alone does not guarantee that every predicted heading should be…
arXiv:2607.18282v1 Announce Type: new Abstract: Bayesian Optimization is widely used for expensive black-box optimization, yet its success often depends on choosing a kernel that matches the…
arXiv:2607.19090v1 Announce Type: cross Abstract: Chemistry describes aspects of the universe in terms of molecules and their reactions. In this exploratory work we present a way…
arXiv:2607.18734v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) is essential to experimental mechanics, but has become particularly relevant in computational mechanics, manifesting in two fundamental problem…
arXiv:2605.15250v3 Announce Type: replace-cross Abstract: Multi-head Latent Attention (MLA), the attention used in DeepSeek-V2/V3, jointly compresses keys and values into a low-rank latent and matches the…
arXiv:2607.19153v1 Announce Type: cross Abstract: Supervised learning models in the predictive maintenance field are regularly trained on highly imbalanced industrial datasets: machine failures occur rarely but…
arXiv:2607.14512v2 Announce Type: replace-cross Abstract: Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions. The…
arXiv:2506.10386v2 Announce Type: replace Abstract: The burial state of anthropogenic objects on the seafloor provides insight into localized sedimentation dynamics and is also critical for assessing…