Cover Image

Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Qingyang, Gao, Bingjie, Fu, Canmiao, Huang, Zhipeng, Li, Chen, Wang, Feng, Chang, Shuochen, Wang, Shaobo, Wang, Yali, Ye, Keming, Li, Jiangtong, Niu, Li
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UnicEdit-10M: A Dataset and Benchmark Breaking the Scale-Quality Barrier via Unified Verification for Reasoning-Enriched Edits
by: Ye, Keming, et al.
Published: (2025)

WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens
by: Guo, Yiwei, et al.
Published: (2026)

D$^{3}$ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs
by: Chang, Shuochen, et al.
Published: (2025)

WeGen: A Unified Model for Interactive Multimodal Generation as We Chat
by: Huang, Zhipeng, et al.
Published: (2025)

WeTok: Powerful Discrete Tokenization for High-Fidelity Visual Reconstruction
by: Zhuang, Shaobin, et al.
Published: (2025)

Text-guided Visual Prompt DINO for Generic Segmentation
by: Guan, Yuchen, et al.
Published: (2025)

Unlocking the Black Box of Latent Reasoning: An Interpretability-Guided Approach to Intervention
by: Chang, Shuochen, et al.
Published: (2026)

Video-GPT via Next Clip Diffusion
by: Zhuang, Shaobin, et al.
Published: (2025)

Align and Aggregate: Compositional Reasoning with Video Alignment and Answer Aggregation for Video Question-Answering
by: Liao, Zhaohe, et al.
Published: (2024)

Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation
by: Zhang, Yabo, et al.
Published: (2026)

Interleaved Latent Visual Reasoning with Selective Perceptual Modeling
by: Dong, Shuai, et al.
Published: (2025)

DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusion
by: Liu, Junxiang, et al.
Published: (2025)

Get In Video: Add Anything You Want to the Video
by: Zhuang, Shaobin, et al.
Published: (2025)

Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization
by: Nie, Ming, et al.
Published: (2026)

Image Generation Based on Image Style Extraction
by: Chang, Shuochen
Published: (2025)

Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning
by: Yin, Shaofeng, et al.
Published: (2026)

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs
by: Jiang, Houcheng, et al.
Published: (2026)

InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for Debating
by: Wang, Fuyu, et al.
Published: (2025)

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
by: Li, Qingyun, et al.
Published: (2024)

Breaking the Recycling Bottleneck of Thermosets via Bio‐Tailoring Technology
by: Jinping Yu, et al.
Published: (2025)

ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking
by: Wang, Lihong, et al.
Published: (2025)

VINO: A Unified Visual Generator with Interleaved OmniModal Context
by: Chen, Junyi, et al.
Published: (2026)

Simple o3: Towards Interleaved Vision-Language Reasoning
by: Wang, Ye, et al.
Published: (2025)

UnAC: Adaptive Visual Prompting with Abstraction and Stepwise Checking for Complex Multimodal Reasoning
by: Wang, Yifan, et al.
Published: (2026)

Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation
by: Wang, Junjie, et al.
Published: (2026)

ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning
by: Gu, Jiawei, et al.
Published: (2025)

RLHFSpec: Breaking the Efficiency Bottleneck in RLHF Training via Adaptive Drafting
by: Wang, Siqi, et al.
Published: (2025)

DreamCom: Finetuning Text-guided Inpainting Model for Image Composition
by: Lu, Lingxiao, et al.
Published: (2023)

Representation Forcing for Bottleneck-Free Unified Multimodal Models
by: Wang, Yuqing, et al.
Published: (2026)

Unified Multimodal Visual Tracking with Dual Mixture-of-Experts
by: Hong, Lingyi, et al.
Published: (2026)

Breaking Through the Luminescence Stability Bottleneck of Oxyfluoride Phosphor for Sun‐Like Led Lighting
by: Ying Li, et al.
Published: (2024)

UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark
by: Li, Yanlin, et al.
Published: (2026)

Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
by: Guo, Ziyu, et al.
Published: (2025)

Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks
by: Jin, Jing, et al.
Published: (2026)

Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization
by: Shen, You, et al.
Published: (2025)

bjli1992/GULE: Global Understanding via Local Extraction for Data Clustering and Visualization
by: Li Bingjie
Published: (2025)

T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
by: Li, Jiachen, et al.
Published: (2024)

VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception
by: Yan, Ziang, et al.
Published: (2025)

Reasoning-Driven Multimodal LLM for Domain Generalization
by: Xu, Zhipeng, et al.
Published: (2026)

Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
by: Zeng, Xiangyu, et al.
Published: (2026)