Cover Image

Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Che, Ma, Lichao, Zhang, Xiangyu Tony, Zhang, Yuxin, Zhang, Haoyang, Yang, Xuerui, Tian, Fei
Format:	Preprint
Published:	2026
Subjects:	Multimedia Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LongInsightBench: A Comprehensive Benchmark for Evaluating Omni-Modal Models on Human-Centric Long-Video Understanding
by: Han, ZhaoYang, et al.
Published: (2025)

OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video
by: Pu, Junfu, et al.
Published: (2026)

Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation
by: Chen, Yuheng, et al.
Published: (2026)

FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs
by: Chen, Qian, et al.
Published: (2026)

Causal Debiasing for Visual Commonsense Reasoning
by: Zou, Jiayi, et al.
Published: (2025)

OmniForcing: Unleashing Real-time Joint Audio-Visual Generation
by: Su, Yaofeng, et al.
Published: (2026)

OmniSep: Unified Omni-Modality Sound Separation with Query-Mixup
by: Cheng, Xize, et al.
Published: (2024)

TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning
by: Xie, Jingjing, et al.
Published: (2024)

Explore the Limits of Omni-modal Pretraining at Scale
by: Zhang, Yiyuan, et al.
Published: (2024)

OralGPT-Omni: A Versatile Dental Multimodal Large Language Model
by: Hao, Jing, et al.
Published: (2025)

Improving Multi-modal Large Language Model through Boosting Vision Capabilities
by: Sun, Yanpeng, et al.
Published: (2024)

ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding
by: Zhang, Zhenxing, et al.
Published: (2024)

Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision
by: Liu, Che, et al.
Published: (2025)

Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing
by: Li, Yanjun, et al.
Published: (2025)

2D or 3D: Who Governs Salience in VLA Models? -- Tri-Stage Token Pruning Framework with Modality Salience Awareness
by: Zheng, Zihao, et al.
Published: (2026)

Unified Generative and Discriminative Training for Multi-modal Large Language Models
by: Chow, Wei, et al.
Published: (2024)

FCBoost-Net: A Generative Network for Synthesizing Multiple Collocated Outfits via Fashion Compatibility Boosting
by: Zhou, Dongliang, et al.
Published: (2025)

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
by: Zhong, Zhisheng, et al.
Published: (2024)

Hierarchical Refinement of Universal Multimodal Attacks on Vision-Language Models
by: Zhang, Peng-Fei, et al.
Published: (2026)

GSE: Evaluating Sticker Visual Semantic Similarity via a General Sticker Encoder
by: Chee, Heng Er Metilda, et al.
Published: (2025)

Gradient-Guided Modality Decoupling for Missing-Modality Robustness
by: Wang, Hao, et al.
Published: (2024)

UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval
by: Wen, Haokun, et al.
Published: (2026)

ChronusOmni: Improving Time Awareness of Omni Large Language Models
by: Chen, Yijing, et al.
Published: (2025)

MCIHN: A Hybrid Network Model Based on Multi-path Cross-modal Interaction for Multimodal Emotion Recognition
by: Zhang, Haoyang, et al.
Published: (2025)

Mitigating Image Captioning Hallucinations in Vision-Language Models
by: Zhao, Fei, et al.
Published: (2025)

LongVALE: Vision-Audio-Language-Event Benchmark Towards Time-Aware Omni-Modal Perception of Long Videos
by: Geng, Tiantian, et al.
Published: (2024)

Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
by: Yu, Xiaomin, et al.
Published: (2026)

Towards Robust and Realible Multimodal Misinformation Recognition with Incomplete Modality
by: Zhou, Hengyang, et al.
Published: (2025)

Taming Modality Entanglement in Continual Audio-Visual Segmentation
by: Hong, Yuyang, et al.
Published: (2025)

PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Tasks
by: Wu, Jianyu, et al.
Published: (2025)

Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval
by: Yang, Yuxin, et al.
Published: (2026)

Enhancing Vision-Language Tracking by Effectively Converting Textual Cues into Visual Cues
by: Feng, X., et al.
Published: (2024)

T$^\text{3}$SVFND: Towards an Evolving Fake News Detector for Emergencies with Test-time Training on Short Video Platforms
by: Zhang, Liyuan, et al.
Published: (2025)

Interactive Spatial-Frequency Fusion Mamba for Multi-Modal Image Fusion
by: Zhu, Yixin, et al.
Published: (2026)

Anisotropic Modality Align
by: Yu, Xiaomin, et al.
Published: (2026)

Identity-Preserving Text-to-Video Generation via Training-Free Prompt, Image, and Guidance Enhancement
by: Gao, Jiayi, et al.
Published: (2025)

ReconBoost: Boosting Can Achieve Modality Reconcilement
by: Hua, Cong, et al.
Published: (2024)

Teacher-Guided Pseudo Supervision and Cross-Modal Alignment for Audio-Visual Video Parsing
by: Chen, Yaru, et al.
Published: (2025)

OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-Extensions
by: Zhang, Yi-Kai, et al.
Published: (2024)

OmniGAIA: Towards Native Omni-Modal AI Agents
by: Li, Xiaoxi, et al.
Published: (2026)