most citedSelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

Are Reasoning Vision-Language Models Robust to Semantic Visual Distractions?

Yizheng Sun, Mochuan Zhan, Yanan Ma +10

Reasoning Vision-Language Models (VLMs) achieve strong performance on complex multimodal tasks, but reliable real-world application requires handling visual inputs that are messier…