#Discrete Diffusion

10개의 포스트

[논문리뷰] MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation

arXiv에 게시된 'MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action (VLA)#Discrete Diffusion #Multi-modal Generation #Robotic Manipulation #Action Chunking #World Model #Hybrid Attention

2026년 4월 1일

[논문리뷰] LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model

arXiv에 게시된 'LLaDA-o: An Effective and Length-Adaptive Omni Diffusion Model' 논문에 대한 자세한 리뷰입니다.

#Review #Omni Diffusion Model #Multimodal AI #Length Adaptation #Mixture of Diffusion #Discrete Diffusion #Continuous Diffusion #Text-to-Image Generation

2026년 3월 2일

[논문리뷰] The Design Space of Tri-Modal Masked Diffusion Models

arXiv에 게시된 'The Design Space of Tri-Modal Masked Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Masked Diffusion Models #Multimodal AI #Scaling Laws #Discrete Diffusion #SDE Parameterization #Hyperparameter Transfer #Unified Generation

2026년 2월 25일

[논문리뷰] MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models

arXiv에 게시된 'MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models' 논문에 대한 자세한 리뷰입니다.

#Review #Molecular Generation #Graph Diffusion Models #Hierarchical Diffusion #Discrete Diffusion #Atom Encoding #Drug Discovery #Material Science

2026년 2월 25일

[논문리뷰] The Diffusion Duality, Chapter II: Ψ-Samplers and Efficient Curriculum

Subham Sekhar Sahoo이 arXiv에 게시한 'The Diffusion Duality, Chapter II: Ψ-Samplers and Efficient Curriculum' 논문에 대한 자세한 리뷰입니다.

#Review #Discrete Diffusion #Ψ-Samplers #Predictor-Corrector #Language Modeling #Image Generation #Curriculum Learning #Efficient Training

2026년 2월 24일

[논문리뷰] Uniform Discrete Diffusion with Metric Path for Video Generation

arXiv에 게시된 'Uniform Discrete Diffusion with Metric Path for Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Discrete Diffusion #Video Generation #Metric Path #Long Video Generation #Asynchronous Scheduling #Text-to-Video #Multimodal Generation

2025년 10월 29일

[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] Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

Hang Zhao이 arXiv에 게시한 'Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving' 논문에 대한 자세한 리뷰입니다.

#Review #Autonomous Driving #Vision-Language-Action Models #Discrete Diffusion #Reflection Mechanism #Trajectory Generation #Safety Constraints #Imitation Learning

2025년 9월 26일

[논문리뷰] Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies

Sitong Mao이 arXiv에 게시한 'Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action (VLA)#Discrete Diffusion #Action Decoding #Transformer #Robot Control #Masked Modeling #Adaptive Decoding #Reinforcement Learning

2025년 8월 28일

[논문리뷰] Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference

Fan Xia이 arXiv에 게시한 'Seed Diffusion: A Large-Scale Diffusion Language Model with High-Speed Inference' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion Models #Language Models #Code Generation #Non-Autoregressive Inference #High-Speed Inference #Discrete Diffusion #LLM Inference

2025년 8월 6일