Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding Paper • 2512.17220 • Published Dec 19, 2025 • 112
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency Paper • 2508.18265 • Published Aug 25, 2025 • 214
PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts Paper • 2508.09848 • Published Aug 13, 2025 • 71
SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension Paper • 2508.01959 • Published Aug 3, 2025 • 59
VideoReasonBench: Can MLLMs Perform Vision-Centric Complex Video Reasoning? Paper • 2505.23359 • Published May 29, 2025 • 38