OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models Paper • 2601.21639 • Published 17 days ago • 49
Running on CPU Upgrade 584 GAIA Leaderboard 🦾 584 Submit your model answers and view GAIA benchmark scores
Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detection Paper • 2308.14286 • Published Aug 28, 2023
Solving Token Gradient Conflict in Mixture-of-Experts for Large Vision-Language Model Paper • 2406.19905 • Published Jun 28, 2024