Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 09298v1 Announce Type: cross Abstract: Action-conditioned world models (ACWMs) promise to provide embodied AI with scalable predictive simulators for planning, policy evaluation, and data generation.
arXiv:2608. 08085v1 Announce Type: cross Abstract: Code performance optimization is a vital aspect of modern software development, as it enables faster response times and reduced resource usage.
arXiv:2608. 09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.
arXiv:2608. 09688v1 Announce Type: cross Abstract: Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias.
arXiv:2607. 28503v3 Announce Type: replace Abstract: In this paper we present an active, constantly updated AI benchmark which measures the integrity of frontier language models against being co-opted for use by authoritarian state "information operations": intentional, coordinated activities by one state to influence public opinion and information ecosystems in another state.
arXiv:2505. 16941v4 Announce Type: replace-cross Abstract: Foundation models (FMs) promise to address core limitations of traditional supervised machine learning: (i) reliance on large amounts of labeled data, (ii) task specificity, and (iii) poor transportability.
arXiv:2507. 14056v3 Announce Type: replace-cross Abstract: Recent work in continual learning has highlighted the stability gap -- a temporary performance drop on previously learned tasks when new ones are introduced.
arXiv:2604. 02047v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates large language model inference by drafting multiple candidate tokens and verifying them in a single forward pass.
arXiv:2608. 08068v1 Announce Type: cross Abstract: Long-tailed class-incremental learning (LT-CIL) must learn new classes from imbalanced streams while retaining old classes.
arXiv:2608. 08944v1 Announce Type: cross Abstract: A failed retrieval-augmented generation (RAG) answer can be consistent with several unseen responses to evidence repair.
arXiv:2608. 09519v1 Announce Type: cross Abstract: We present a reproducibility study of XFeat, a lightweight local feature extractor and matcher designed to identify corresponding points across images efficiently on resource-constrained hardware.
arXiv:2608. 09193v1 Announce Type: cross Abstract: Unsupervised time-series domain adaptation (DA) addresses the challenge of transferring a classifier from a labeled source domain to an unlabeled target domain under distribution shifts induced by different users, sensors, devices, acquisition conditions, or temporal dynamics.
arXiv:2507. 00945v2 Announce Type: replace Abstract: Short-term forecasting of aggregated human mobility flows supports urban planning, intelligent transportation systems, and emergency response, yet existing models often require substantial mobility history and learn spatial structure implicitly through grids or graphs.
arXiv:2605. 00941v5 Announce Type: replace Abstract: Flow matching provides a highly effective framework for generative modeling, yet estimating the uncertainty of its generated samples remains a fundamental challenge.
arXiv:2605. 00754v4 Announce Type: replace-cross Abstract: Reward models (RMs) have become an indispensable fixture of the language model (LM) post-training playbook, enabling policy alignment and test-time scaling.
arXiv:2608. 07693v1 Announce Type: cross Abstract: Generative traffic video forecasting aims to synthesize long-horizon, temporally coherent future videos of traffic scenes from a short observation history and textual descriptions.
arXiv:2608. 00417v2 Announce Type: replace Abstract: Although large language models (LLMs) can produce fluent spatial reasoning traces, their intermediate relations may fail to support the final conclusion, making token-level confidence insufficient for final-answer reliability estimation.
arXiv:2608. 09230v1 Announce Type: new Abstract: Industrial-safety understanding requires more than detecting workers, equipment, and personal protective equipment.
arXiv:2508. 03875v2 Announce Type: replace Abstract: Many sequential decision problems offer qualitatively different ways of influencing the environment: some interventions act immediately, whereas others induce persistent effects that continue to shape future states long after the decision that initiated them.
arXiv:2608. 07533v1 Announce Type: new Abstract: An embodied agent is an intelligent entity that interacts with its environment through a physical body.