{"ID":2855869,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.12720","arxiv_id":"2510.12720","title":"Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception","abstract":"Fine-grained perception of multimodal information is critical for advancing human-AI interaction. With recent progress in audio-visual technologies, Omni Language Models (OLMs), capable of processing audio and video signals in parallel, have emerged as a promising paradigm for achieving richer understanding and reasoning. However, their capacity to capture and describe fine-grained details remains limited explored. In this work, we present a systematic and comprehensive investigation of omni detailed perception from the perspectives of the data pipeline, models, and benchmark. We first identify an inherent \"co-growth\" between detail and hallucination in current OLMs. To address this, we propose Omni-Detective, an agentic data generation pipeline integrating tool-calling, to autonomously produce highly detailed yet minimally hallucinatory multimodal data. Based on the data generated with Omni-Detective, we train two captioning models: Audio-Captioner for audio-only detailed perception, and Omni-Captioner for audio-visual detailed perception. Under the cascade evaluation protocol, Audio-Captioner achieves the best performance on MMAU and MMAR among all open-source models, surpassing Gemini 2.5 Flash and delivering performance comparable to Gemini 2.5 Pro. On existing detailed captioning benchmarks, Omni-Captioner sets a new state-of-the-art on VDC and achieves the best trade-off between detail and hallucination on the video-SALMONN 2 testset. Given the absence of a dedicated benchmark for omni detailed perception, we design Omni-Cloze, a novel cloze-style evaluation for detailed audio, visual, and audio-visual captioning that ensures stable, efficient, and reliable assessment. Experimental results and analysis demonstrate the effectiveness of Omni-Detective in generating high-quality detailed captions, as well as the superiority of Omni-Cloze in evaluating such detailed captions.","short_abstract":"Fine-grained perception of multimodal information is critical for advancing human-AI interaction. With recent progress in audio-visual technologies, Omni Language Models (OLMs), capable of processing audio and video signals in parallel, have emerged as a promising paradigm for achieving richer understanding and reasoni...","url_abs":"https://arxiv.org/abs/2510.12720","url_pdf":"https://arxiv.org/pdf/2510.12720v2","authors":"[\"Ziyang Ma\",\"Ruiyang Xu\",\"Zhenghao Xing\",\"Yunfei Chu\",\"Yuxuan Wang\",\"Jinzheng He\",\"Jin Xu\",\"Pheng-Ann Heng\",\"Kai Yu\",\"Junyang Lin\",\"Eng Siong Chng\",\"Xie Chen\"]","published":"2025-10-14T17:00:09Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.CV\",\"cs.MM\",\"cs.SD\"]","methods":"[\"Language Model\"]","has_code":false}