news

Mar 2026 Our Amazon internship work, Visual Reasoning through Tool-supervised Reinforcement Learning, was accepted to CVPR 2026 Findings. Paper coming soon.
Mar 2026 The code and data for our ICLR 2026 paper Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks are released at ref-adv.github.io.
Feb 2026 Our new preprint Fine-T2I is released: Fine-T2I: An Open, Large-Scale, and Diverse Dataset for High-Quality T2I Fine-Tuning. The dataset is available on HuggingFace and was trending #1 in datasets!
Jan 2026 One paper accepted at ICLR 2026: Ref-Adv: Exploring MLLM Visual Reasoning in Referring Expression Tasks!
Oct 2025 Honored to receive the Outstanding Reviewer Award at ICCV 2025!