DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning Paper • 2411.04983 • Published Nov 7, 2024 • 10
BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games Paper • 2411.13543 • Published Nov 20, 2024 • 18
DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation Paper • 2411.04999 • Published Nov 7, 2024 • 17
Training Language Models on Synthetic Edit Sequences Improves Code Synthesis Paper • 2410.02749 • Published Oct 3, 2024 • 12