BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression
cs.CV, cs.AI, cs.CL, cs.LG
Submitted: 2026-11-06
Updated: 2026-11-09
Code: https://github.com/gecgomes/Uncertainty_BEiTScore_pp
Terminology
Sources
- From Images to Sentences through Scene Description Graphs using Commonsense Reasoning and Knowledge
- PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions
- A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
- BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model
- EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation
- Regularization Strategies for Quantile Regression
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