MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Space Paper • 2504.13835 • Published 4 days ago • 35
InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models Paper • 2504.10479 • Published 8 days ago • 239
Creation-MMBench: Assessing Context-Aware Creative Intelligence in MLLM Paper • 2503.14478 • Published Mar 18 • 47
Running 106 106 Open VLM Video Leaderboard 🌎 VLMEvalKit Eval Results in video understanding benchmark
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation Paper • 2407.17438 • Published Jul 24, 2024 • 25