IV-Bench: A Benchmark for Image-Grounded Video Perception and Reasoning in Multimodal LLMs Paper • 2504.15415 • Published Apr 21, 2025 • 23
How Far Are We from Genuinely Useful Deep Research Agents? Paper • 2512.01948 • Published about 1 month ago • 54
COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values Paper • 2504.05535 • Published Apr 7, 2025 • 44