Copertina

Free-MoRef: Instantly Multiplexing Context Perception Capabilities of Video-MLLMs within Single Inference

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wang, Kuo, Zheng, Quanlong, Xie, Junlin, Zhang, Yanhao, Luo, Jinguo, Lu, Haonan, Lin, Liang, Zhou, Fan, Li, Guanbin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

H2VU-Benchmark: A Comprehensive Benchmark for Hierarchical Holistic Video Understanding
di: Wu, Qi, et al.
Pubblicazione: (2025)

OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
di: Liang, Zhijia, et al.
Pubblicazione: (2026)

Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLM
di: Liu, Peng, et al.
Pubblicazione: (2025)

Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation
di: Zhou, Yuxiang, et al.
Pubblicazione: (2025)

An Empirical Study on Configuring In-Context Learning Demonstrations for Unleashing MLLMs' Sentimental Perception Capability
di: Wu, Daiqing, et al.
Pubblicazione: (2025)

LLMI3D: MLLM-based 3D Perception from a Single 2D Image
di: Yang, Fan, et al.
Pubblicazione: (2024)

Achieving Net‐Zero Through AI ‐Enabled Dynamic Capability and Green Servitization in Chinese Furniture Manufacturing Industry
di: Jinguo Li
Pubblicazione: (2026)

From Pixels to Feelings: Aligning MLLMs with Human Cognitive Perception of Images
di: Chen, Yiming, et al.
Pubblicazione: (2025)

Perception-R1: Advancing Multimodal Reasoning Capabilities of MLLMs via Visual Perception Reward
di: Xiao, Tong, et al.
Pubblicazione: (2025)

Large Multimodal Agents: A Survey
di: Xie, Junlin, et al.
Pubblicazione: (2024)

Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games
di: Zhong, Keyang, et al.
Pubblicazione: (2026)

RefTok: Reference-Based Tokenization for Video Generation
di: Fan, Xiang, et al.
Pubblicazione: (2025)

RefDecoder: Enhancing Visual Generation with Conditional Video Decoding
di: Fan, Xiang, et al.
Pubblicazione: (2026)

Credible Teacher for Semi-Supervised Object Detection in Open Scene
di: Zhuang, Jingyu, et al.
Pubblicazione: (2024)

Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs
di: Zhu, Rui, et al.
Pubblicazione: (2026)

VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
di: Wang, Qi, et al.
Pubblicazione: (2025)

VLDrive: Vision-Augmented Lightweight MLLMs for Efficient Language-grounded Autonomous Driving
di: Zhang, Ruifei, et al.
Pubblicazione: (2025)

LocRef-Diffusion:Tuning-Free Layout and Appearance-Guided Generation
di: Deng, Fan, et al.
Pubblicazione: (2024)

Exploring the Design Space of Visual Context Representation in Video MLLMs
di: Du, Yifan, et al.
Pubblicazione: (2024)

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding
di: Sun, Peiwen, et al.
Pubblicazione: (2026)

RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
di: Fan, Jiaojiao, et al.
Pubblicazione: (2024)

MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments
di: Liu, Yang, et al.
Pubblicazione: (2024)

CodePercept: Code-Grounded Visual STEM Perception for MLLMs
di: Guan, Tongkun, et al.
Pubblicazione: (2026)

Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustness
di: Zhao, Yusheng, et al.
Pubblicazione: (2025)

InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling
di: Wang, Yi, et al.
Pubblicazione: (2025)

ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing
di: Zhao, Xuanle, et al.
Pubblicazione: (2025)

RefAlign: Representation Alignment for Reference-to-Video Generation
di: Wang, Lei, et al.
Pubblicazione: (2026)

DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering
di: Luo, Jingzhou, et al.
Pubblicazione: (2025)

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation
di: Han, Su Ho, et al.
Pubblicazione: (2025)

V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding
di: Ge, Junqi, et al.
Pubblicazione: (2024)

Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models
di: Wu, Junjie, et al.
Pubblicazione: (2025)

Tuning-Free Long Video Generation via Global-Local Collaborative Diffusion
di: Ma, Yongjia, et al.
Pubblicazione: (2025)

360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method
di: Tran, Huyen T. T., et al.
Pubblicazione: (2026)

A Retrospect to Multi-prompt Learning across Vision and Language
di: Chen, Ziliang, et al.
Pubblicazione: (2025)

MarvelOVD: Marrying Object Recognition and Vision-Language Models for Robust Open-Vocabulary Object Detection
di: Wang, Kuo, et al.
Pubblicazione: (2024)

Linking Perception, Confidence and Accuracy in MLLMs
di: Du, Yuetian, et al.
Pubblicazione: (2026)

Region-Adaptive Video Sharpening via Rate-Perception Optimization
di: Pang, Yingxue, et al.
Pubblicazione: (2025)

HumanSense: From Multimodal Perception to Empathetic Context-Aware Responses through Reasoning MLLMs
di: Qin, Zheng, et al.
Pubblicazione: (2025)

Ref-DGS: Reflective Dual Gaussian Splatting
di: Fan, Ningjing, et al.
Pubblicazione: (2026)

Interpretable Embeddings for Segmentation-Free Single-Cell Analysis in Multiplex Imaging
di: Gutwein, Simon, et al.
Pubblicazione: (2024)