| Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos | Jan 7, 2025 | 2kLanguage Modeling | CodeCode Available | 5 |
| Long-context LLMs Struggle with Long In-context Learning | Apr 2, 2024 | 2kIn-Context Learning | CodeCode Available | 5 |
| Scaling Granite Code Models to 128K Context | Jul 18, 2024 | 2k4k | CodeCode Available | 4 |
| CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets | May 30, 2024 | 2k3D geometry | CodeCode Available | 4 |
| MovieChat+: Question-aware Sparse Memory for Long Video Question Answering | Apr 26, 2024 | 2kQuestion Answering | CodeCode Available | 4 |
| SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection | Mar 11, 2024 | 2D Object Detection2k | CodeCode Available | 4 |
| Highly Accurate Dichotomous Image Segmentation | Mar 6, 2022 | 2k3D Reconstruction | CodeCode Available | 4 |
| FlashDepth: Real-time Streaming Video Depth Estimation at 2K Resolution | Apr 9, 2025 | 2kDecision Making | CodeCode Available | 3 |
| MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction | Feb 17, 2025 | 2kAutonomous Driving | CodeCode Available | 3 |
| 1.5-Pints Technical Report: Pretraining in Days, Not Months -- Your Language Model Thrives on Quality Data | Aug 7, 2024 | 16k2k | CodeCode Available | 3 |
