M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models Paper • 2405.15638 • Published May 24, 2024 • 1
BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation Paper • 2506.07530 • Published Jun 9, 2025 • 20
Revisiting Multimodal Positional Encoding in Vision-Language Models Paper • 2510.23095 • Published Oct 27, 2025 • 23
RefHCM: A Unified Model for Referring Perceptions in Human-Centric Scenarios Paper • 2412.14643 • Published Dec 19, 2024
