Copertina

Understanding and Harnessing Sparsity in Unified Multimodal Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	He, Shwai, Deng, Chaorui, Li, Ang, Yan, Shen
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration
di: He, Shwai, et al.
Pubblicazione: (2024)

UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding
di: Xu, Chenkai, et al.
Pubblicazione: (2025)

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
di: Zhang, Huichao, et al.
Pubblicazione: (2026)

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
di: Wen, Zimo, et al.
Pubblicazione: (2026)

UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation
di: Li, Yi, et al.
Pubblicazione: (2025)

Steering Visual Generation in Unified Multimodal Models with Understanding Supervision
di: Liu, Zeyu, et al.
Pubblicazione: (2026)

What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models
di: Fan, Yingqi, et al.
Pubblicazione: (2026)

Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning
di: LASA Team, et al.
Pubblicazione: (2025)

Unified Multimodal Understanding via Byte-Pair Visual Encoding
di: Zhang, Wanpeng, et al.
Pubblicazione: (2025)

A Unified Understanding of Adversarial Vulnerability Regarding Unimodal Models and Vision-Language Pre-training Models
di: Zheng, Haonan, et al.
Pubblicazione: (2024)

Free Lunch for Unified Multimodal Models: Enhancing Generation via Reflective Rectification with Inherent Understanding
di: Jiang, Yibo, et al.
Pubblicazione: (2026)

HaploOmni: Unified Single Transformer for Multimodal Video Understanding and Generation
di: Xiao, Yicheng, et al.
Pubblicazione: (2025)

Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding
di: Liang, Yongyuan, et al.
Pubblicazione: (2025)

UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models
di: Li, Jinke, et al.
Pubblicazione: (2025)

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
di: Qu, Liao, et al.
Pubblicazione: (2024)

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
di: Hong, Jixiang, et al.
Pubblicazione: (2025)

Lance: Unified Multimodal Modeling by Multi-Task Synergy
di: Fu, Fengyi, et al.
Pubblicazione: (2026)

Semantic Generative Tuning for Unified Multimodal Models
di: Yu, Songsong, et al.
Pubblicazione: (2026)

Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
di: Chen, Xiaokang, et al.
Pubblicazione: (2025)

UniPTS: A Unified Framework for Proficient Post-Training Sparsity
di: Xie, Jingjing, et al.
Pubblicazione: (2024)

Photon: Speedup Volume Understanding with Efficient Multimodal Large Language Models
di: Fang, Chengyu, et al.
Pubblicazione: (2026)

Unified Modeling Enhanced Multimodal Learning for Precision Neuro-Oncology
di: Yi, Huahui, et al.
Pubblicazione: (2024)

ARMOR: Empowering Multimodal Understanding Model with Interleaved Multimodal Generation Capability
di: Sun, Jianwen, et al.
Pubblicazione: (2025)

UniToken: Harmonizing Multimodal Understanding and Generation through Unified Visual Encoding
di: Jiao, Yang, et al.
Pubblicazione: (2025)

Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models
di: Ye, Sen, et al.
Pubblicazione: (2026)

Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding
di: Li, Yinghui, et al.
Pubblicazione: (2026)

COEF-VQ: Cost-Efficient Video Quality Understanding through a Cascaded Multimodal LLM Framework
di: Dong, Xin, et al.
Pubblicazione: (2024)

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights
di: Tian, Juanxi, et al.
Pubblicazione: (2025)

Text-VQA Aug: Pipelined Harnessing of Large Multimodal Models for Automated Synthesis
di: Joshi, Soham, et al.
Pubblicazione: (2025)

Are Unified Vision-Language Models Necessary: Generalization Across Understanding and Generation
di: Zhang, Jihai, et al.
Pubblicazione: (2025)

RS-GPT4V: A Unified Multimodal Instruction-Following Dataset for Remote Sensing Image Understanding
di: Xu, Linrui, et al.
Pubblicazione: (2024)

MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image
di: Song, Shezheng, et al.
Pubblicazione: (2024)

Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification
di: Kumar, Raja, et al.
Pubblicazione: (2024)

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
di: Wu, Chengyue, et al.
Pubblicazione: (2024)

UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128}}$ for Unified Multimodal Large Language Model
di: Zhuang, Shaobin, et al.
Pubblicazione: (2026)

Harnessing PDF Data for Improving Japanese Large Multimodal Models
di: Baek, Jeonghun, et al.
Pubblicazione: (2025)

Instinct vs. Reflection: Unifying Token and Verbalized Confidence in Multimodal Large Models
di: Dang, Yunkai, et al.
Pubblicazione: (2026)

EventVL: Understand Event Streams via Multimodal Large Language Model
di: Li, Pengteng, et al.
Pubblicazione: (2025)

IAD-Unify: A Region-Grounded Unified Model for Industrial Anomaly Segmentation, Understanding, and Generation
di: Zheng, Haoyu, et al.
Pubblicazione: (2026)

Enhancing Multimodal Unified Representations for Cross Modal Generalization
di: Huang, Hai, et al.
Pubblicazione: (2024)