# D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning

arXiv: https://arxiv.org/abs/2602.07960 · HTML: https://mlsanity.com/paper/2602.07960/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 56 references that are in the map.
- First posted on arXiv 8 Feb 2026.

## Builds on (most cited first, 30 of 44)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research](https://mlsanity.com/paper/1904.03493/) (2019)
- [Clotho: An Audio Captioning Dataset](https://mlsanity.com/paper/1910.09387/) (2019)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research](https://mlsanity.com/paper/2303.17395/) (2023)
- [NVILA: Efficient Frontier Visual Language Models](https://mlsanity.com/paper/2412.04468/) (2024)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs](https://mlsanity.com/paper/2502.04326/) (2025)
- [AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark](https://mlsanity.com/paper/2410.03051/) (2024)
- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?](https://mlsanity.com/paper/2505.21374/) (2025)
- [Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities](https://mlsanity.com/paper/2505.17862/) (2025)
- [OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM](https://mlsanity.com/paper/2510.15870/) (2025)
- [Joint Speaker Counting, Speech Recognition, and Speaker Identification for Overlapped Speech of Any Number of Speakers](https://mlsanity.com/paper/2006.10930/) (2020)
- [ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts](https://mlsanity.com/paper/2507.20939/) (2025)
- [Audio-centric Video Understanding Benchmark without Text Shortcut](https://mlsanity.com/paper/2503.19951/) (2025)
- [Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis](https://mlsanity.com/paper/2011.02014/) (2020)

## Built on by (most cited first, 6 of 6)

- [CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales](https://mlsanity.com/paper/2606.21949/) (2026)
- [TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos](https://mlsanity.com/paper/2605.07593/) (2026)
- [Who Says What: Symbolic Trimodal Binding Mechanisms in Audio-Visual LLMs](https://mlsanity.com/paper/2609.31193/) (2026)
- [video-SALMONN-R3: Learning to ReWatch, ReAsk, and ReAnswer for Efficient Video Understanding](https://mlsanity.com/paper/2606.24477/) (2026)
- [Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas](https://mlsanity.com/paper/2607.02504/) (2026)
- [Uncovering Ordinal-Matching Bias in Audio-Visual LLMs](https://mlsanity.com/paper/2609.34223/) (2026)

## Abstract (arXiv)

Spoken dialogue is a primary source of information in videos; therefore, accurately identifying who spoke what and when is essential for deep video understanding. We introduce D-ORCA, a dialogue-centric omni-modal large language model optimized for robust audio-visual captioning. We further curate DVD, a large-scale, high-quality bilingual dataset comprising nearly 40,000 multi-party dialogue videos for training and 2000 videos for evaluation in English and Mandarin, addressing a critical gap in the open-source ecosystem. To ensure fine-grained captioning accuracy, we adopt group relative policy optimization with three novel reward functions that assess speaker attribution accuracy, global speech content accuracy, and sentence-level temporal boundary alignment. These rewards are derived from evaluation metrics widely used in speech processing and, to our knowledge, are applied for the first time as reinforcement learning objectives for audio-visual captioning. Extensive experiments demonstrate that D-ORCA substantially outperforms existing open-source models in speaker identification, speech recognition, and temporal grounding. Notably, despite having only 8 billion parameters, D-ORCA achieves performance competitive with Qwen3-Omni across several general-purpose audio-visual understanding benchmarks. Demos are available at hrefhttps://d-orca-llm.github.io/https://d-orca-llm.github.io/. Our code, data, and checkpoints will be available at hrefhttps://github.com/WeChatCV/D-ORCA/https://github.com/WeChatCV/D-ORCA/.