G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation
cs.CV
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/DAGroup-PKU/G-STAR
Project page: https://dagroup-pku.github.io/G-STAR
Terminology
Sources
- BitDance: Scaling Autoregressive Generative Models with Binary Tokens
- Qwen3-VL Technical Report
- Muse: Text-To-Image Generation via Masked Generative Transformers
- DFlash: Block Diffusion for Flash Speculative Decoding
- SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation
- Are We on the Right Way for Evaluating Large Vision-Language Models?
- Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
- DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation
- Emu3.5: Native Multimodal Models are World Learners
- Emerging Properties in Unified Multimodal Pretraining
- FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark
- A Neural Algorithm of Artistic Style
- X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
- ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
- DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
- LLaVA-OneVision: Easy Visual Task Transfer
- Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation
- Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis
- Step1X-Edit: A Practical Framework for General Image Editing
- Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual 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