Image de couverture de livre

OmniDPO: A Preference Optimization Framework to Address Omni-Modal Hallucination

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Junzhe, Zhang, Tianshu, Huang, Shiyu, Niu, Yuwei, Sun, Chao, Zhang, Rongzhou, Zhou, Guanyu, Wen, Lijie, Hu, Xuming
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence Multimedia
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

V2A-DPO: Omni-Preference Optimization for Video-to-Audio Generation
par: Chan, Nolan, et autres
Publié: (2026)

OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs
par: Yan, Qianqi, et autres
Publié: (2026)

OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup
par: Cheng, Xize, et autres
Publié: (2024)

ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language Models
par: Chen, Junzhe, et autres
Publié: (2024)

OmniGAIA: Towards Native Omni-Modal AI Agents
par: Li, Xiaoxi, et autres
Publié: (2026)

OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities
par: Chen, Lichang, et autres
Publié: (2024)

AVID: A Benchmark for Omni-Modal Audio-Visual Inconsistency Understanding via Agent-Driven Construction
par: Chen, Zixuan, et autres
Publié: (2026)

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
par: Chen, Qian, et autres
Publié: (2026)

Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation
par: Chen, Yuheng, et autres
Publié: (2026)

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
par: Zhong, Zhisheng, et autres
Publié: (2024)

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation
par: Liu, Che, et autres
Publié: (2026)

LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding
par: Han, ZhaoYang, et autres
Publié: (2025)

ChronusOmni: Improving Time Awareness of Omni Large Language Models
par: Chen, Yijing, et autres
Publié: (2025)

Omni-Captioner: Data Pipeline, Models, and Benchmark for Omni Detailed Perception
par: Ma, Ziyang, et autres
Publié: (2025)

FashionDPO:Fine-tune Fashion Outfit Generation Model using Direct Preference Optimization
par: Yu, Mingzhe, et autres
Publié: (2025)

Ola: Pushing the Frontiers of Omni-Modal Language Model
par: Liu, Zuyan, et autres
Publié: (2025)

OralGPT-Omni: A Versatile Dental Multimodal Large Language Model
par: Hao, Jing, et autres
Publié: (2025)

OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
par: Li, Shufan, et autres
Publié: (2024)

Multi-view Hypergraph-based Contrastive Learning Model for Cold-Start Micro-video Recommendation
par: Lyu, Sisuo, et autres
Publié: (2024)

MGM-Omni: Scaling Omni LLMs to Personalized Long-Horizon Speech
par: Wang, Chengyao, et autres
Publié: (2025)

AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues
par: Zhou, Dingkun, et autres
Publié: (2025)

Explore the Limits of Omni-modal Pretraining at Scale
par: Zhang, Yiyuan, et autres
Publié: (2024)

Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision
par: Liu, Che, et autres
Publié: (2025)

OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-Extensions
par: Zhang, Yi-Kai, et autres
Publié: (2024)

LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos
par: Geng, Tiantian, et autres
Publié: (2024)

Omni-Dish: Photorealistic and Faithful Image Generation and Editing for Arbitrary Chinese Dishes
par: Liu, Huijie, et autres
Publié: (2025)

LongCat-Flash-Omni Technical Report
par: Meituan LongCat Team, et autres
Publié: (2025)

Omni-C: Compressing Heterogeneous Modalities into a Single Dense Encoder
par: Lau, Kin Wai, et autres
Publié: (2026)

Rethinking Fusion: Disentangled Learning of Shared and Modality-Specific Information for Stance Detection
par: Xie, Zhiyu, et autres
Publié: (2026)

OmniMER: Auxiliary-Enhanced LLM Adaptation for Indonesian Multimodal Emotion Recognition
par: Yan, Xueming, et autres
Publié: (2025)

Omni2Sound: Towards Unified Video-Text-to-Audio Generation
par: Dai, Yusheng, et autres
Publié: (2026)

OmniForcing: Unleashing Real-time Joint Audio-Visual Generation
par: Su, Yaofeng, et autres
Publié: (2026)

OmniPlay: Benchmarking Omni-Modal Models on Omni-Modal Game Playing
par: Bie, Fuqing, et autres
Publié: (2025)

CDIO: Cross-Domain Inference Optimization with Resource Preference Prediction for Edge-Cloud Collaboration
par: Yang, Zheming, et autres
Publié: (2025)

OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video
par: Pu, Junfu, et autres
Publié: (2026)

OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model
par: Li, Maomao, et autres
Publié: (2026)

OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text
par: Pian, Weiguo, et autres
Publié: (2026)

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
par: Fu, Yuhan, et autres
Publié: (2024)

TMDC: A Two-Stage Modality Denoising and Complementation Framework for Multimodal Sentiment Analysis with Missing and Noisy Modalities
par: Zhuang, Yan, et autres
Publié: (2025)

Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
par: Tian, Zeyue, et autres
Publié: (2026)