Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
cs.CV
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/Hpesojyjx/Saccades-AR
Terminology
Sources
- Gemini: A Family of Highly Capable Multimodal Models
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
- Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
- Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens
- VideoPoet: A Large Language Model for Zero-Shot Video Generation
- Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
- Autoregressive Image Generation without Vector Quantization
- Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining
- STAR: Scale-wise Text-conditioned AutoRegressive image generation
- Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
- LLaMA: Open and Efficient Foundation Language Models
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation
- Qwen2 Technical Report
- Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs