Amortized-Precision Quantization for Early-Exit Vision Transformers
cs.CV, cs.AI
Submitted: 2026-05-08
Updated: 2026-11-07
Terminology
Sources
- Multi-Exit Vision Transformer for Dynamic Inference
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
- Quantizing deep convolutional networks for efficient inference: A whitepaper
- Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE
- MPTQ-ViT: Mixed-Precision Post-Training Quantization for Vision Transformer
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