#Autoregressive Generation

17개의 포스트

[논문리뷰] AvatarPointillist: AutoRegressive 4D Gaussian Avatarization

arXiv에 게시된 'AvatarPointillist: AutoRegressive 4D Gaussian Avatarization' 논문에 대한 자세한 리뷰입니다.

#Review #4D Gaussian Avatar #Autoregressive Generation #Transformer #3D Gaussian Splatting #One-shot Generation #Identity-preserving

2026년 4월 6일

[논문리뷰] LoST: Level of Semantics Tokenization for 3D Shapes

arXiv에 게시된 'LoST: Level of Semantics Tokenization for 3D Shapes' 논문에 대한 자세한 리뷰입니다.

#Review #3D Shape Tokenization #Semantic Salience #Autoregressive Generation #Relational Inter-Distance Alignment #Diffusion Models #Triplane

2026년 3월 18일

[논문리뷰] WorldCompass: Reinforcement Learning for Long-Horizon World Models

arXiv에 게시된 'WorldCompass: Reinforcement Learning for Long-Horizon World Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #World Models #Video Generation #Autoregressive Generation #Long-Horizon #Post-training #Diffusion Models #Reward Functions

2026년 2월 9일

[논문리뷰] Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening

Haitham Bou Ammar이 arXiv에 게시한 'Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Reasoning #Distribution Sharpening #Power Sampling #Training-Free #Monte Carlo Estimation #Jackknife Correction #Autoregressive Generation #Inference Efficiency

2026년 1월 29일

[논문리뷰] Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models

arXiv에 게시된 'Few Tokens Matter: Entropy Guided Attacks on Vision-Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Adversarial Attacks #Entropy-Guided Attacks #Token Vulnerability #Harmful Content #Cross-Model Transferability #Autoregressive Generation

2026년 1월 8일

[논문리뷰] VA-π: Variational Policy Alignment for Pixel-Aware Autoregressive Generation

Yicong Li이 arXiv에 게시한 'VA-π: Variational Policy Alignment for Pixel-Aware Autoregressive Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Generation #Pixel-Aware Alignment #Variational Optimization #Reinforcement Learning #Visual Tokenizers #Image Quality #ELBO #Post-Training Framework

2025년 12월 25일

[논문리뷰] WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion

arXiv에 게시된 'WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion' 논문에 대한 자세한 리뷰입니다.

#Review #Novel View Synthesis #3D Geometry Propagation #Video Diffusion Models #Gaussian Splatting #Autoregressive Generation #Spatio-Temporal Noise #Geometric Consistency

2025년 12월 22일

[논문리뷰] FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering

Hendrik P. A. Lensch이 arXiv에 게시한 'FrameDiffuser: G-Buffer-Conditioned Diffusion for Neural Forward Frame Rendering' 논문에 대한 자세한 리뷰입니다.

#Review #Neural Rendering #Diffusion Models #G-Buffer #Autoregressive Generation #Temporal Consistency #ControlNet #ControlLoRA #Interactive Applications

2025년 12월 18일

[논문리뷰] OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory

arXiv에 게시된 'OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Shot Video Generation #Adaptive Memory #Long-Range Context #Frame Selection #Diffusion Models #Image-to-Video #Autoregressive Generation #Narrative Coherence

2025년 12월 9일

[논문리뷰] Rethinking Training Dynamics in Scale-wise Autoregressive Generation

arXiv에 게시된 'Rethinking Training Dynamics in Scale-wise Autoregressive Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Autoregressive Generation #Visual Synthesis #Exposure Bias #Student Forcing #Self-Autoregressive Refinement #Scale-wise Prediction #Image Generation

2025년 12월 8일

[논문리뷰] MotionStream: Real-Time Video Generation with Interactive Motion Controls

arXiv에 게시된 'MotionStream: Real-Time Video Generation with Interactive Motion Controls' 논문에 대한 자세한 리뷰입니다.

#Review #Real-Time Video Generation #Motion Control #Diffusion Models #Autoregressive Generation #Self-Forcing #Attention Sink #Streaming Inference #Video Distillation

2025년 11월 9일

[논문리뷰] Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs

arXiv에 게시된 'Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Visual Reasoning #Latent Space #Sketch Generation #Visual Thinking #Autoregressive Generation #Interpretability

2025년 10월 29일

[논문리뷰] ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

arXiv에 게시된 'ARGenSeg: Image Segmentation with Autoregressive Image Generation Model' 논문에 대한 자세한 리뷰입니다.

#Review #Image Segmentation #Autoregressive Generation #Multimodal Large Language Models (MLLMs)#Visual Understanding #VQ-VAE #Multi-scale Prediction #Referring Expression Segmentation #Image Generation

2025년 10월 24일

[논문리뷰] Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs

Jingyi Liao이 arXiv에 게시한 'Patch-as-Decodable-Token: Towards Unified Multi-Modal Vision Tasks in MLLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Large Language Models (MLLMs)#Visual Reference Tokens (VRTs)#Dense Prediction #Referring Expression Comprehension (REC)#Open-Vocabulary Detection (OVD)#Image Captioning #Unified Architecture #Autoregressive Generation

2025년 10월 9일

[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] Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing

Hao Zhang이 arXiv에 게시한 'Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion Forcing' 논문에 대한 자세한 리뷰입니다.

#Review #Diffusion LLMs #Faster Inference #Discrete Diffusion Forcing (D2F)#Autoregressive Generation #KV Cache Optimization #Parallel Decoding #Text Generation #Model Distillation

2025년 8월 14일

[논문리뷰] LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

Chenyang Si이 arXiv에 게시한 'LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation' 논문에 대한 자세한 리뷰입니다.

#Review #Ultra-long Video Generation #Multimodal Guidance #Controllable Video Generation #Diffusion Models #Temporal Consistency #Visual Quality #Autoregressive Generation #Degradation-aware Training

2025년 8월 6일