Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention

3 October 2025

Papers citing "Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention"

1 / 1 papers shown

Title
RTV-Bench: Benchmarking MLLM Continuous Perception, Understanding and Reasoning through Real-Time Video Shuhang Xun Sicheng Tao Jiajun Li Yibo Shi Zhixin Lin ... Shikang Wang Rahul Gupta Hao Zhang Ying Ma Xuming Hu VLM LRM 195 2 0 04 May 2025