Aarash Feizi

Grounding Computer Use Agents on Human Demonstrations

PairBench: Are Vision-Language Models Reliable at Comparing What They See?

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

FairLoRA: Unpacking Bias Mitigation in Vision Models with Fairness-Regularized Low-Rank Adaptation