VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair
cs.LG
Submitted: 2026-10-01
Updated: 2026-10-01
Sources
- Evaluating Self-Correcting Vision Agents Through Quantitative and Qualitative Metrics
- ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models
- VisEditBench: Can Vision-Language Models Edit Visualization Code from Multimodal Feedback?
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks