logo
today local_bar
Reinforcement Learning for Vision Language Models

1 paper across 1 session

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs
#4605 · Mohammad Shahab Sepehri, Berk Tinaz, Zalan Fabian, Mahdi Soltanolkotabi

Hyperphantasia is a synthetic benchmark of visual reasoning puzzles that probs mental visualization in MLLMs.