๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

Utkarsh
@utk7arsh
ai/ml @Asteralabs | cs @penn & @ucla | Researching on VLMs, VLAs | #ynwa#
๊ฐ€์ž… May 2024
496 ํŒ”๋กœ์ž‰ ์ค‘    1.9K ํŒฌ
Lots of world-models papers exist today but there is almost no map of how they connect ๐Ÿงฌ @ylecun said, โ€œThe world model is a kind of simulator of the relevant aspects of the world. It predicts future world states from observations, prior state, and action.โ€ So I built Engram, a second brain for world-models research: โ†’ Timeline: 57 papers across 8 paradigms distributed by year of release โ†’ Neuron: force-directed clusters across the paradigms inspired by Karpathy's version of second brain. โ†’ Random: land somewhere unexpected and get started on learning something new today โ†’ Every paper has arXiv and github links baked into it. There is also @askalphaxiv link attached to each paper so you can learn better and use their incredible features. PlaNet โ†’ Dreamer โ†’ DreamerV3. MuZero โ†’ EfficientZero. JEPA, Genie, GAIA and much much more. ๐ŸŒ โญ Launching today! Please try it and tell me whatโ€™s broken, missing, or inaccurate. Have fun with it!!
๋” ๋ณด๊ธฐ