TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation
Abstract
TTS-VAR, a test-time scaling framework for visual auto-regressive models, improves generation quality by dynamically adjusting batch sizes and using clustering and resampling techniques.
Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and promising performance. In this work, we present TTS-VAR, the first general test-time scaling framework for visual auto-regressive (VAR) models, modeling the generation process as a path searching problem. To dynamically balance computational efficiency with exploration capacity, we first introduce an adaptive descending batch size schedule throughout the causal generation process. Besides, inspired by VAR's hierarchical coarse-to-fine multi-scale generation, our framework integrates two key components: (i) At coarse scales, we observe that generated tokens are hard for evaluation, possibly leading to erroneous acceptance of inferior samples or rejection of superior samples. Noticing that the coarse scales contain sufficient structural information, we propose clustering-based diversity search. It preserves structural variety through semantic feature clustering, enabling later selection on samples with higher potential. (ii) In fine scales, resampling-based potential selection prioritizes promising candidates using potential scores, which are defined as reward functions incorporating multi-scale generation history. Experiments on the powerful VAR model Infinity show a notable 8.7% GenEval score improvement (from 0.69 to 0.75). Key insights reveal that early-stage structural features effectively influence final quality, and resampling efficacy varies across generation scales. Code is available at https://github.com/ali-vilab/TTS-VAR.
Community
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- MINT: Memory-Infused Prompt Tuning at Test-time for CLIP (2025)
- HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation (2025)
- BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models (2025)
- STAGE: A Stream-Centric Generative World Model for Long-Horizon Driving-Scene Simulation (2025)
- Rectified Sparse Attention (2025)
- Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment (2025)
- Seedance 1.0: Exploring the Boundaries of Video Generation Models (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper