Jiayuan Mao @maojiayuan Twitter profile

Last Seen Profiles

@N00ling

@BoofBaldy

@BinorRaja

@stwgemoy

@1920yesilay

@IAS_conference

@MissMalav

@jandakembangstw

@pdmcleod

@PlattsmouthFB

@FiscGralLibert

@david_darmofal

@ktlrx7

@Zeeks_1

@akittvn

@SIAC_cardio

@aNewLeafgame

@proofftm

@mourfil

@MicHustlin1

@i_trzr2

@oddxxxow1

@elf_3125

@Gusmao_pedro1

@UCLASenate

@Burritoexp

@joe_weller_

@CorkLGFA

@DaytonMVP

@bokeplokalmalam

@Prost_1726

@trepiante

@Manami_ebisu

@SamdTaf

@CrossWayne50579

@Ayanami_402

Jiayuan Mao

@maojiayuan

8 months

Check out our new framework that automatically generates planning domain knowledge with LLMs, learns to ground it, and verifies it through interaction. We believe that learning such verifiable and compositional planning representations from language is important for embodied AI!

CoCoSci MIT

@MITCoCoSci

8 months

People don't take a one-size-fits-all approach to planning: we change how we abstract the world to fit our goals. Our approach, Ada, integrates LLMs + formal planning to learn libraries of composable skills adapted to individual planning domains: 🧵 [1/5]

225

125

Jiayuan Mao

@maojiayuan

9 months

Definitely one of my top 3 favourite papers :) It marries deep learning with a minimal set of universal grammar rules for grounded language learning. It draws inspiration from lexicalist linguistics and cognitive science (bootstrapping from core knowledge).

Freda Shi

@fredahshi

9 months

🚨(Not Really) Old Paper Alert🚨: sharing our 2-year-old NeurIPS paper that I’m still quite excited about. We learn grounded, neuro-symbolic CCGs from multi-modal data and demonstrate nearly perfect compositional generalization to unseen sentences and scenes. (1/)

108

Jiayuan Mao

@maojiayuan

8 months

Come chat with us on Tuesday morning at #203 at @NeurIPSConf !

Joy Hsu

@joycjhsu

8 months

Excited to talk about Logic-Enhanced Foundation Models (LEFT) @NeurIPSConf next week! Come chat with us on Tuesday morning at #203 . Try out our Colab notebook to train your own LEFT and learn concepts on a new dataset in ~100 lines of code. 🔗Colab: