AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward | Paper Citation Record

Observation 4eaed5f7-1f2a-4ff8-8f8f-92924844fd08 · outbound

This paper cites Avocado: An audiovisual video captioner driven by temporal orchestration.arXiv preprint arXiv:2510.10395, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Avocado: An audiovisual video captioner driven by temporal orchestration.arXiv preprint arXiv:2510.10395, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.001303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b695bdef-a788-4514-949d-8065a0a98e1f · outbound

This paper cites Ugc-videocaptioner: An omni ugc video detail caption model and new benchmarks.arXiv preprint arXiv:2507.11336, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Ugc-videocaptioner: An omni ugc video detail caption model and new benchmarks.arXiv preprint arXiv:2507.11336, 2025

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.012944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad1b155c-49ef-45af-b7b2-78dea5511969 · outbound

This paper cites Daily-omni: Towards audio-visual reasoning with temporal alignment across modalities.arXiv preprint arXiv:2505.17862, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Daily-omni: Towards audio-visual reasoning with temporal alignment across modalities.arXiv preprint arXiv:2505.17862, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.020242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f454879b-db8d-4894-b6a7-98084bef545c · outbound

This paper cites VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.027540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f6e4ae1-519f-4569-be74-61cf0eed85a9 · outbound

This paper cites Sharegpt4video: Improving video understanding and generation with better captions.Advances in Neural Information Processing Systems, 37: 19472–19495, 2024.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Sharegpt4video: Improving video understanding and generation with better captions.Advances in Neural Information Processing Systems, 37: 19472–19495, 2024

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:47.162755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 55a344b0-2078-444f-9837-3581bfcb57db · outbound

This paper cites Mavors: Multi-granularity video representation for multimodal large language model.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Mavors: Multi-granularity video representation for multimodal large language model

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.043255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c73a9e0-e967-446c-a679-d61cfd231a08 · outbound

This paper cites Timechat: A time-sensitive multimodal large language model for long video understanding.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Timechat: A time-sensitive multimodal large language model for long video understanding

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.051144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90db9274-bbf3-46ad-8514-45a615392547 · outbound

This paper cites Tarsier: Recipes for Training and Evaluating Large Video Description Models.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Tarsier: Recipes for Training and Evaluating Large Video Description Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.059127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b84cf9f9-f405-441b-9a80-a8a0db9a6853 · outbound

This paper cites Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.066103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac750a63-35b8-467a-9019-cfa9d9a1d905 · outbound

This paper cites Panda-70m: Captioning 70m videos with multiple cross-modality teachers.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Panda-70m: Captioning 70m videos with multiple cross-modality teachers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.074176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 727dae58-6d8b-4478-bb13-886fcd349312 · outbound

This paper cites Advancing high-resolution video-language representation with large-scale video transcriptions.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Advancing high-resolution video-language representation with large-scale video transcriptions

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:47.108399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6995e3e9-3e81-4806-af86-eef40d176bdb · outbound

This paper cites video-salmonn 2: Captioning-enhanced audio-visual large language models.arXiv preprint arXiv:2506.15220, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward video-salmonn 2: Captioning-enhanced audio-visual large language models.arXiv preprint arXiv:2506.15220, 2025

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.087226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f752d0b-4aad-460d-9aba-c565c4d88bb7 · outbound

This paper cites AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.093438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70ff3cbf-52e2-4513-b5d7-e931862558b8 · outbound

This paper cites Longvale: Vision-audio-language-event benchmark towards time-aware omni-modal perception of long videos.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Longvale: Vision-audio-language-event benchmark towards time-aware omni-modal perception of long videos

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:47.086591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8db4405e-fa54-4f54-95d9-ff440f26235c · outbound

This paper cites Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.106889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a402971b-163d-41f1-bf6a-5779e77e4a33 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.113320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fafedc81-20fb-4608-872c-4b5035d3bde9 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.120212Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87b8dd1b-90a8-4b20-bc27-6bb85e24b4a2 · outbound

This paper cites Watch, listen, and describe: Globally and locally aligned cross-modal attentions for video captioning.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Watch, listen, and describe: Globally and locally aligned cross-modal attentions for video captioning

Reference 18

Resolution: verified exact; doi, observed 2026-08-10T18:13:44.635267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e10c871d-faef-49c8-bac8-ad08c41aec11 · outbound

This paper cites VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.133036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a17029f-7952-4eac-a5f8-50f77b513d43 · outbound

This paper cites Qwen2.5-VL Technical Report.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Qwen2.5-VL Technical Report

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.140160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d47876c-b084-4857-a211-94c6eba7760b · outbound

This paper cites Glave-cap: Global-local aligned video captioning with vision expert integration.arXiv preprint arXiv:2509.11360, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Glave-cap: Global-local aligned video captioning with vision expert integration.arXiv preprint arXiv:2509.11360, 2025

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.146443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8f1a29e-aef0-4ac8-9db6-e8e868898a3a · outbound

This paper cites Qwen2.5-Omni Technical Report.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Qwen2.5-Omni Technical Report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.151110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ead60c4d-46c1-4950-977f-efa478de054f · outbound

This paper cites OmniCaptioner: One Captioner to Rule Them All.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward OmniCaptioner: One Captioner to Rule Them All

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.157674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c38d65-50d3-4629-b59f-5b52c5a203e4 · outbound

This paper cites Omni-captioner: Data pipeline, models, and benchmark for omni detailed perception.arXiv preprint arXiv:2510.12720, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Omni-captioner: Data pipeline, models, and benchmark for omni detailed perception.arXiv preprint arXiv:2510.12720, 2025

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.163332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aab17aee-273f-41a8-9111-9ea95809ed00 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.169838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91ab4e8d-8701-43e7-a6f1-180c2e0142ef · outbound

This paper cites Video-R1: Reinforcing Video Reasoning in MLLMs.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Video-R1: Reinforcing Video Reasoning in MLLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.176917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dfeba4d-990f-4466-961f-7991cdc82a8b · outbound

This paper cites AdaTooler-V: Adaptive Tool-Use for Images and Videos.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward AdaTooler-V: Adaptive Tool-Use for Images and Videos

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.183615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e486e27-48ba-4008-87db-37a63dcf1e18 · outbound

This paper cites Deepvideo-r1: Video rein- forcement fine-tuning via difficulty-aware regressive grpo.arXiv preprint arXiv:2506.07464, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Deepvideo-r1: Video rein- forcement fine-tuning via difficulty-aware regressive grpo.arXiv preprint arXiv:2506.07464, 2025

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.190682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89671b3f-be56-4556-bfb1-d94ce96e8412 · outbound

This paper cites Editthinker: Unlocking iterative reasoning for any image editor.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Editthinker: Unlocking iterative reasoning for any image editor

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.197366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e3a51c8-22b5-4d13-a606-cc7a0e510022 · outbound

This paper cites Sophiavl-r1: Reinforcing mllms reasoning with thinking reward.arXiv preprint arXiv:2505.17018, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Sophiavl-r1: Reinforcing mllms reasoning with thinking reward.arXiv preprint arXiv:2505.17018, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.204027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ec3c7c0-87f4-447b-885a-edc9ca334b31 · outbound

This paper cites Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.209331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf7d5b55-0444-40c4-aacb-a628a9681f73 · outbound

This paper cites Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.215349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65539722-4660-4024-be93-223a12fa8d76 · outbound

This paper cites OneThinker: All-in-one Reasoning Model for Image and Video.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward OneThinker: All-in-one Reasoning Model for Image and Video

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.221576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2eb3994f-034a-49ca-a654-13259944ce9d · outbound

This paper cites VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.228889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53fcffc3-aa5f-49b5-ac92-20dd6ee28176 · outbound

This paper cites VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.235558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d031b374-8983-4f7e-a325-cc8741da424e · outbound

This paper cites Exploring the role of audio in video captioning.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Exploring the role of audio in video captioning

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:47.067484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 81e8b0ea-9029-44e0-8c6e-06c0df6bdacb · outbound

This paper cites Hybrid transformers for music source separation.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Hybrid transformers for music source separation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:47.049145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cc0ed116-12d4-4b94-929f-bb14edf82074 · outbound

This paper cites Audio-visual event localization in unconstrained videos.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Audio-visual event localization in unconstrained videos

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.255613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3944060-20a1-4e43-ac79-d894f5e3ef54 · outbound

This paper cites Vggsound: A large-scale audio-visual dataset.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Vggsound: A large-scale audio-visual dataset

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:47.018344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3ca62a8c-3c7f-419f-b375-76f43901be93 · outbound

This paper cites Condensed movies: Story based retrieval with contextual embeddings.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Condensed movies: Story based retrieval with contextual embeddings

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.268021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4d9dd4f-6e26-4315-92f0-725f21550be2 · outbound

This paper cites Avqa: A dataset for audio-visual question answering on videos.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Avqa: A dataset for audio-visual question answering on videos

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.276994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fee2fdf0-5625-4f0b-a12f-fb4d2404f25a · outbound

This paper cites Movienet: A holistic dataset for movie understanding.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Movienet: A holistic dataset for movie understanding

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.978977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c4d13c8f-2283-41b8-ba93-d06bd766d3e0 · outbound

This paper cites A dataset for movie description.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward A dataset for movie description

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.962720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 09d3fbeb-410e-4146-9ec5-ad05891eb23f · outbound

This paper cites Auroracap: Efficient, performant video detailed captioning and a new benchmark.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Auroracap: Efficient, performant video detailed captioning and a new benchmark

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.946632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cdd33149-e7cc-4cc7-89a3-72bc5fc4f766 · outbound

This paper cites Time-r1: Post-training large vision language model for temporal video grounding.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Time-r1: Post-training large vision language model for temporal video grounding

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.929111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 41f95256-3d3a-4c1f-a884-73c828d10848 · outbound

This paper cites Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-08-10T18:13:44.864443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d6ea50e2-06d0-4b15-981a-95988c63ed04 · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.329322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 324bbfe1-68ca-488a-968a-de6c43b9bfcf · outbound

This paper cites Lora: Low-rank adaptation of large language models.ICLR, 1 (2):3, 2022.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Lora: Low-rank adaptation of large language models.ICLR, 1 (2):3, 2022

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.336856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa408bef-362d-41bb-b75f-70b2b82f91e1 · outbound

This paper cites Efficient memory management for large language model serving with pagedattention.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Efficient memory management for large language model serving with pagedattention

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.342904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455e53d5-8b79-462a-8263-e33b9bceb9df · outbound

This paper cites Vbench: Comprehensive benchmark suite for video generative models.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Vbench: Comprehensive benchmark suite for video generative models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.369645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 367cf444-21a9-45a3-bae8-ce99e94b6814 · outbound

This paper cites VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.376026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1074ca18-4c48-469d-a37d-db46b91920bc · outbound

This paper cites HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.385618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aeb4fe0-9bc3-4f5c-9714-ed4492a388df · outbound

This paper cites ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward ARC-Hunyuan-Video-7B: Structured Video Comprehension of Real-World Shorts

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.392418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d59819bb-9364-46b4-a338-0f3746d8b9a2 · outbound

This paper cites Minicpm-o 2.6: A gpt-4o level mllm for vision, speech, and multimodal live stream- ing on your phone.https://github.com/OpenBMB/MiniCPM-V, 2025.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Minicpm-o 2.6: A gpt-4o level mllm for vision, speech, and multimodal live stream- ing on your phone.https://github.com/OpenBMB/MiniCPM-V, 2025

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.876062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dc9de645-8519-4180-9fae-51dfd07e6618 · outbound

This paper cites InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.406841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be280df9-dcdb-4e6d-9846-4a4242ff3b46 · outbound

This paper cites Self- critical sequence training for image captioning.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Self- critical sequence training for image captioning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.414464Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c49af00d-fb79-4ee8-ac0e-6cd6f366ea28 · outbound

This paper cites id": "sample id.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward id": "sample id

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.848800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation da44a066-d0cc-4715-a367-9fcfba7c58c0 · outbound

This paper cites Use the exact terminology found in the text (e.g., if the caption says ”shatters”, use ”shatters”, not ”breaks”).

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Use the exact terminology found in the text (e.g., if the caption says ”shatters”, use ”shatters”, not ”breaks”)

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.829527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 31b2fb4b-b1be-4066-88df-0ed9d35bbe6f · outbound

This paper cites an unresolved cited work.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Unresolved cited work

Reference 61

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:13:46.809850Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 06ff5225-4b67-4407-a027-13511abd61a4 · outbound

This paper cites Start directly with the answer content.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Start directly with the answer content

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.788962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fa9669e6-ff5d-45ad-bb6c-b38be7b63981 · outbound

This paper cites strengths.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward strengths

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.764825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4a20e370-b5df-4187-8a70-e124cda1f609 · outbound

This paper cites an unresolved cited work.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:13:46.742112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bee123fd-afc5-43ed-bb1d-2bd4514bc827 · outbound

This paper cites evaluation.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward evaluation

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.717454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6f54366b-2833-4bff-a4bb-38ad54d5fcc9 · outbound

This paper cites Do not add any artistic interpretation, subjective analysis, or infer any character’s internal 23 thoughts, emotions, or intentions beyond what is explicitly visible or audible.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Do not add any artistic interpretation, subjective analysis, or infer any character’s internal 23 thoughts, emotions, or intentions beyond what is explicitly visible or audible

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.692726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 90a1999f-d774-4123-a162-e1bbae85ba49 · outbound

This paper cites While Character A is speaking, Character B simultaneously turns their head.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward While Character A is speaking, Character B simultaneously turns their head

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.668462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 36b615f7-5d65-48b6-b411-84544350326a · outbound

This paper cites He closed the door,.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward He closed the door,

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.648814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a39cd8a8-82c3-4890-ab62-d46deb18892b · outbound

This paper cites The camera cuts to a close-up of her face,.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward The camera cuts to a close-up of her face,

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.628650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 52b76ef2-21c0-4633-a1fe-87058085ec5f · outbound

This paper cites an unresolved cited work.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-10T18:13:46.608847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e8eebfdd-7bb2-4176-9ed5-f3a690bb0f80 · outbound

This paper cites Do not use bullet points, headings, or line breaks within the narrative.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Do not use bullet points, headings, or line breaks within the narrative

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.577670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 70b54954-8d96-4140-823a-14fdffbda128 · outbound

This paper cites His voice, thick with sarcasm, says.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward His voice, thick with sarcasm, says

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.553912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 90c315f3-909b-46c3-93ad-2d8bb8a5336c · outbound

This paper cites thud" as a book hits the table, a.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward thud" as a book hits the table, a

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.526057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 64b2eb73-aa40-48d3-8df0-360d4fdca671 · outbound

This paper cites While Person A’s hand reaches for the glass, Person B’s eyes dart to the side, and the music swells.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward While Person A’s hand reaches for the glass, Person B’s eyes dart to the side, and the music swells

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.499941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0092d044-e526-435f-8cb0-7f3df378f2fb · outbound

This paper cites Avoid summarizing.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward Avoid summarizing

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.471133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8457dc9e-0c4b-4dcb-8fe2-d16d504a83a2 · outbound

This paper cites strengths.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward strengths

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:13:46.445294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 271c8407-3349-4ac9-8db6-390573dd5ff2 · outbound

This paper cites WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs.

AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-10T18:13:44.362349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers