Cover Image

Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Songlin, Kong, Xianghao, Rao, Anyi
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ProFashion: Prototype-guided Fashion Video Generation with Multiple Reference Images
by: Kong, Xianghao, et al.
Published: (2025)

Composing Concepts from Images and Videos via Concept-prompt Binding
by: Kong, Xianghao, et al.
Published: (2025)

Simulating the Real World: A Unified Survey of Multimodal Generative Models
by: Hu, Yuqi, et al.
Published: (2025)

Pseudo Contrastive Learning for Diagram Comprehension in Multimodal Models
by: Sasaki, Hiroshi
Published: (2026)

SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment
by: Zhao, Zhuoran, et al.
Published: (2026)

Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal Models
by: Rao, Abinav, et al.
Published: (2026)

FlexMUSE: Multimodal Unification and Semantics Enhancement Framework with Flexible interaction for Creative Writing
by: Chen, Jiahao, et al.
Published: (2025)

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

Pseudo Labelling for Enhanced Masked Autoencoders
by: Nandam, Srinivasa Rao, et al.
Published: (2024)

Controllable Navigation Instruction Generation with Chain of Thought Prompting
by: Kong, Xianghao, et al.
Published: (2024)

ScriptViz: A Visualization Tool to Aid Scriptwriting based on a Large Movie Database
by: Rao, Anyi, et al.
Published: (2024)

Discrete Diffusion Models with MLLMs for Unified Medical Multimodal Generation
by: Mao, Jiawei, et al.
Published: (2025)

ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation
by: Yang, Songlin, et al.
Published: (2026)

SUM: Saliency Unification through Mamba for Visual Attention Modeling
by: Hosseini, Alireza, et al.
Published: (2024)

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

UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors
by: Chen, Houyuan, et al.
Published: (2026)

Understanding and Harnessing Sparsity in Unified Multimodal Models
by: He, Shwai, et al.
Published: (2025)

Complementary Pseudo Multimodal Feature for Point Cloud Anomaly Detection
by: Cao, Yunkang, et al.
Published: (2023)

Blocks as Probes: Dissecting Categorization Ability of Large Multimodal Models
by: Fu, Bin, et al.
Published: (2024)

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

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

Revealing Temporal Label Noise in Multimodal Hateful Video Classification
by: Yang, Shuonan, et al.
Published: (2025)

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

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

MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
by: Zhang, Jusheng, et al.
Published: (2025)

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

BarkXAI: A Lightweight Post-Hoc Explainable Method for Tree Species Classification with Quantifiable Concepts
by: Huang, Yunmei, et al.
Published: (2025)

Revealing the Underlying Patterns: Investigating Dataset Similarity, Performance, and Generalization
by: Achara, Akshit, et al.
Published: (2023)

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

OmniCam: Unified Multimodal Video Generation via Camera Control
by: Yang, Xiaoda, et al.
Published: (2025)

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

PiPa++: Towards Unification of Domain Adaptive Semantic Segmentation via Self-supervised Learning
by: Chen, Mu, et al.
Published: (2024)

Enhancing Alignment for Unified Multimodal Models via Semantically-Grounded Supervision
by: Kim, Jiyeong, et al.
Published: (2026)

Archon: A Unified Multimodal Model for Holistic Digital Human Generation
by: Bao, Chong, et al.
Published: (2026)

Taming Flow-based I2V Models for Creative Video Editing
by: Kong, Xianghao, et al.
Published: (2025)

Adversarial Prompt Injection Attack on Multimodal Large Language Models
by: Ding, Meiwen, et al.
Published: (2026)

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

Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics
by: Roy, Subhadeep, et al.
Published: (2026)

Stretching Each Dollar: Diffusion Training from Scratch on a Micro-Budget
by: Sehwag, Vikash, et al.
Published: (2024)

Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy
by: Huang, Jiahao, et al.
Published: (2026)