#Image Understanding

11개의 포스트

[논문리뷰] Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models

arXiv에 게시된 'Insight-V++: Towards Advanced Long-Chain Visual Reasoning with Multimodal Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Visual Reasoning #Image Understanding #Video Understanding #Multi-Agent System #Reinforcement Learning #Self-Evolving

2026년 3월 23일

[논문리뷰] UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations

arXiv에 게시된 'UniCom: Unified Multimodal Modeling via Compressed Continuous Semantic Representations' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Multimodal Model #Image Generation #Image Understanding #Semantic Compression #Continuous Representation #Diffusion Model #Transformer #Image Editing

2026년 3월 11일

[논문리뷰] OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation

arXiv에 게시된 'OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Visual Encoder #Image Understanding #Image Generation #VAE #Vision Transformer #Multimodal Learning #Reconstruction #Contrastive Learning

2026년 1월 22일

[논문리뷰] UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation

arXiv에 게시된 'UniX: Unifying Autoregression and Diffusion for Chest X-Ray Understanding and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Chest X-Ray #Medical Foundation Model #Autoregressive Model #Diffusion Model #Multimodal Learning #Image Understanding #Image Generation #Cross-Modal Attention

2026년 1월 20일

[논문리뷰] OneThinker: All-in-one Reasoning Model for Image and Video

Kaixuan Fan이 arXiv에 게시한 'OneThinker: All-in-one Reasoning Model for Image and Video' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Reinforcement Learning #Visual Reasoning #Generalist Model #Image Understanding #Video Understanding #Multitask Learning #EMA-GRPO

2025년 12월 3일

[논문리뷰] Architecture Decoupling Is Not All You Need For Unified Multimodal Model

Hongyu Li이 arXiv에 게시한 'Architecture Decoupling Is Not All You Need For Unified Multimodal Model' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Multimodal Models #Architecture Decoupling #Cross-Modal Attention #Attention Interaction Alignment (AIA) Loss #Task Conflicts #Image Generation #Image Understanding

2025년 11월 30일

[논문리뷰] SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

arXiv에 게시된 'SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Multimodal Models #Self-Rewarding #Text-to-Image Generation #Image Understanding #Post-Training #Global-Local Reward #Compositional Reasoning

2025년 10월 15일

[논문리뷰] Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

Linyi Jin이 arXiv에 게시한 'Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Multimodal Model #Camera-Centric #Image Understanding #Image Generation #Spatial Reasoning #Camera Parameters #Instruction Tuning #Multimodal Spatial Intelligence

2025년 10월 13일

[논문리뷰] Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer

arXiv에 게시된 'Ming-UniVision: Joint Image Understanding and Generation with a Unified Continuous Tokenizer' 논문에 대한 자세한 리뷰입니다.

#Review #Unified Vision-Language Model #Continuous Tokenizer #Autoregressive Generation #Image Understanding #Image Generation #Multimodal AI #In-context Editing

2025년 10월 9일

[논문리뷰] Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding

arXiv에 게시된 'Lumina-DiMOO: An Omni Diffusion Large Language Model for Multi-Modal Generation and Understanding' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-modal LLM #Discrete Diffusion #Image Generation #Image Understanding #Omni-modal #Interactive Retouching #Generative AI #Reinforcement Learning

2025년 10월 9일

[논문리뷰] Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation

Zhe Lin이 arXiv에 게시한 'Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal AI #Masked Diffusion Models #Image Understanding #Image Generation #Image Editing #Object Grounding #ElasticMoT #Self-reflection

2025년 9월 25일