3 papers
cs.CL2026
One Ring to Rule Them All: Unifying Group-Based RL via Dynamic Power-Mean Geometry
Weisong Zhao, Tong Wang, Zichang Tan +11
Group-based reinforcement learning has evolved from the arithmetic mean of GRPO to the geometric mean of GMPO. While GMPO improves stability by constraining a conservative objectiv…
cs.CV2025
EEA: Exploration-Exploitation Agent for Long Video Understanding
Te Yang, Xiangyu Zhu, Bo Wang +3
Long-form video understanding requires efficient navigation of extensive visual data to pinpoint sparse yet critical information. Current approaches to longform video understanding…
cs.CV2024
Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Te Yang, Jian Jia, Xiangyu Zhu +9
Large Language Models (LLMs) have strong instruction-following capability to interpret and execute tasks as directed by human commands. Multimodal Large Language Models (MLLMs) hav…