DCVLM Collection Raw data pools, pre-mixed ready-to-train datasets and checkpoints for DataComp-VLM. • 14 items • Updated 4 days ago • 4
view article Article Continuous batching from first principles +1 ror, ArthurZ, mcpotato • Nov 25, 2025 • 425
DataComp-VLM: Improved Open Datasets for Vision-Language Models Paper • 2606.28551 • Published Jun 26 • 52
DataComp-VLM: Improved Open Datasets for Vision-Language Models Paper • 2606.28551 • Published Jun 26 • 52
DataComp-VLM: Improved Open Datasets for Vision-Language Models Paper • 2606.28551 • Published Jun 26 • 52
Concept-Aware Batch Sampling Improves Language-Image Pretraining Paper • 2511.20643 • Published Nov 25, 2025 • 4
On Calibration of Object Detectors: Pitfalls, Evaluation and Baselines Paper • 2405.20459 • Published May 30, 2024
GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features Paper • 2211.12482 • Published Nov 19, 2022
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding Paper • 2605.30126 • Published May 28 • 10
Language-Unlocked ViT (LUViT): Empowering Self-Supervised Vision Transformers with LLMs Paper • 2507.00754 • Published Jul 8, 2025
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection Paper • 2309.14976 • Published Feb 1, 2024
PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding Paper • 2605.30126 • Published May 28 • 10