…elevating the overall production automation to over 95%, demonstrating MapAgent's practicality and effectiveness for large-scale lane-level map generation. View arXiv page View PDF Project page GitHub 5 Add to…
…View arXiv page View PDF Project page GitHub 14 Add to collection Community Xetrieval: Mechanistically Explaining Dense Retrieval This is an automated message from the Librarian Bot . I found the following papers…
…3) To alleviate the current scarcity of spatial audio datasets, we also develop an automated annotation pipeline for generating detailed spatial captions . Experimental results demonstrate that SwanSphere achieves superior performance in both…
…View arXiv page View PDF Project page GitHub 19 Add to collection Community A stability-plasticity benchmark and geometry-based diagnosis of parameter-efficient finetuning. This is an automated message from the…
…Xinkai Ma , , , , , , , Qianqian Xie , , , , , , , , , Minghao Liu , , , , , Abstract A multimodal deep research benchmark and agent framework are introduced to evaluate and improve the factual reliability and visual alignment of automated report generation systems…
…200 instances calibrated through automated filtering and human-LLM review . Relevant resources will be soon released at https://github.com/ClawGym. View arXiv page View PDF Project page Add to collection Community…
…View arXiv page View PDF Project page GitHub 201 Add to collection Community Github Page: https://github.com/shawn0728/OpenSearch-VL Project Page: https://huggingface.co/OpenSearch-VL This is an automated…
…View arXiv page View PDF Project page GitHub 3 Add to collection Community Accepted by KDD2026 This is an automated message from the Librarian Bot . I found the following papers similar to…
…View arXiv page View PDF Project page GitHub 32 Add to collection Community Project page: https://quanhaol.github.io/DiffusionOPD-site/ This is an automated message from the Librarian Bot . I found…
…We construct 75 social roles across five granularity levels and collect 91,200 role-conditioned responses over shared questions and prompt variants, then extract role-level hidden states and project them onto…