arXiv:2510.10181v3 Announce Type: replace
Abstract: Embodied agents face a fundamental limitation: once deployed in real-world environments, they cannot easily acquire new knowledge to improve task performance. In this paper, we propose Dejavu, a gene…
arXiv:2502.08691v2 Announce Type: replace-cross
Abstract: Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significant paradigmatic shift. By leveraging bottom-up simu…
arXiv:2604.08644v1 Announce Type: new
Abstract: This technical report introduces EXAONE 4.5, the first open-weight vision language model released by LG AI Research. EXAONE 4.5 is architected by integrating a dedicated visual encoder into the existing …
arXiv:2604.09132v1 Announce Type: new
Abstract: Recent advancements in autoregressive transformers have demonstrated remarkable potential for generating artist-quality meshes. However, the token ordering strategies employed by existing methods typical…
arXiv:2604.08723v1 Announce Type: new
Abstract: Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream reasoning gains. We as…
arXiv:2604.08552v1 Announce Type: cross
Abstract: Scientific metadata are often incomplete and noncompliant with community standards, limiting dataset findability, interoperability, and reuse. When reporting guidelines exist, they typically lack machi…
arXiv:2512.17425v2 Announce Type: replace
Abstract: Exoskeletons modulate human movement across diverse applications, from performance augmentation to daily-life assistance. These systems often enforce specific kinematic patterns to mitigate injury ri…
arXiv:2604.08603v1 Announce Type: cross
Abstract: Existing LLM-based agent systems share a common architectural failure: they answer from the unrestricted knowledge space without first simulating how active business scenarios reshape that space for th…
arXiv:2604.09450v1 Announce Type: new
Abstract: Chest X-ray report generation (CXR-RG) has the potential to substantially alleviate radiologists’ workload. However, conventional autoregressive vision–language models (VLMs) suffer from high inference …
arXiv:2603.15757v2 Announce Type: replace
Abstract: What happens when a pretrained generative robot policy is provided a constant initial noise as input, rather than repeatedly sampling it from a Gaussian? We demonstrate that the performance of a pret…