AREX: Towards a Recursively Self-Improving Agent for Deep Research Paper • 2607.21461 • Published Jul 23 • 107
fpadovani/nld-latn-100mb-after-ppt-shuff-dyck-100mb-ckpt500_seed455 Text Generation • 0.1B • Updated Jul 17 • 69 • 1
SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding Paper • 2607.10400 • Published Jul 11 • 69
DataComp-VLM: Improved Open Datasets for Vision-Language Models Paper • 2606.28551 • Published Jun 26 • 52
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 65
Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning Paper • 2606.19808 • Published Jun 18 • 3