GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset Paper โข 2507.21033 โข Published 23 days ago โข 20
The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements Paper โข 2506.22419 โข Published Jun 27 โข 14
Complex-Edit: CoT-Like Instruction Generation for Complexity-Controllable Image Editing Benchmark Paper โข 2504.13143 โข Published Apr 17 โข 8
A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning Paper โข 2503.06960 โข Published Mar 10 โข 3
Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning Paper โข 2312.11420 โข Published Dec 18, 2023 โข 2
A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor? Paper โข 2409.15277 โข Published Sep 23, 2024 โข 39
Benchmarking Multi-Image Understanding in Vision and Language Models: Perception, Knowledge, Reasoning, and Multi-Hop Reasoning Paper โข 2406.12742 โข Published Jun 18, 2024 โข 15