CoCoSci MIT
@MITCoCoSci
Followers
4K
Following
73
Media
23
Statuses
116
Computational Cognitive Science Group | MIT | BCS Latest updates from Josh Tenenbaum's lab + Alumni
Joined July 2020
RT @katie_m_collins: How do people reason so flexibly about new problems, bringing to bear globally-relevant knowledge while staying locall….
0
19
0
RT @T_BrookeWilson: How do people reason while still staying coherent – as if they have an internal ‘world model’ for situations they’ve ne….
0
26
0
RT @arcprize: Tomorrow, Oct. 8, @fchollet @mikeknoop are bringing ARC Prize live to @MIT in Boston!. Thanks to Prof. Josh Tenenbaum, @mitbr….
lu.ma
ARC Prize 2024 University Tour comes to MIT! AGI progress has stalled. You can change that. This is a private even open to university students and staff…
0
9
0
Ready to unlock new insights? Join this upcoming workshop and let's learn together!.
Hi friends — I'm delighted to announce a new summer workshop on the emerging interface between cognitive science 🧠 and computer graphics 🫖!. We're calling it: COGGRAPH! June – July 2024, free & open to the public.(all career stages, all disciplines). 🧶
0
0
12
RT @DaeHoulihan: I'm deeply honored to receive one of this year's @cogsci_soc Glushko Dissertation Prizes. While I'm still in a state of….
0
10
0
Work done jointly with w/ Lio Wong, @maojiayuan, @pratyusha_PS, @siegelz_, @feng_jiahai, Noa Korneev, Josh Tenenbaum, & @jacobandreas.
1
1
8
We show that Ada *dramatically outperforms* other approaches for using LLMs in planning (including a Voyager-like model!) on two interactive planning benchmarks — Mini Minecraft and ALFRED. We’re excited to try scaling this to harder robotics domains! [4/5].
1
5
33
Then, we interactively use these abstractions to build concrete plans, in the process learning *which actions are actually useful for solving problems*, and *how to implement them in the environment*. [3/5]
1
3
15
We use LLMs as *priors* over high-level, symbolic action abstractions that might be useful for collections of related tasks like cooking or game-playing. [2/5]
2
3
25
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]
3
46
216
RT @MIT_CBMM: [publication] "Perception of 3D shape integrates intuitive physics and analysis-by-synthesis". Research from @MITCoCoSci stud….
0
4
0
RT @cpilab: In a seminal paper by @LakeBrenden @TomerUllman @MITCoCoSci and @gershbrain put forward core domains of intelligence that are e….
0
3
0
RT @katie_m_collins: There have been tremendous advances at the nexus of AI + mathematics. But it’s worth reflecting what our goals are for….
0
94
0
RT @chentoast1: Once upon a time, a mighty sphinx, the Area Chair of Thebes, terrorized all who dared to cross the mountain path into the c….
0
6
0
RT @gabe_grand: What if we equipped LLMs with cutting-edge code refactoring tools? 🤖🛠. Presenting LILO: Library Induction with Language Obs….
0
46
0
RT @minimario1729: 📢 Introducing 🔗LINC, a neurosymbolic approach to logical reasoning w/ awesome co-first authors @theo_olausson, @ben_lipk….
0
31
0
RT @thomaspocon: 🔥Preprint Alert🔥 Excited to share some new work modeling human 3D shape perception!. “Approaching human 3D shape perceptio….
0
50
0
RT @judyefan: Cognitive scientists! You don’t want to miss our #CogSci2023 Workshop: “How does the mind discover useful abstractions?” http….
0
47
0
RT @gregd_nlp: 🔥 The program for the NLRSE workshop at #ACL2023NLP is posted 🔥.In addition to the 5 invited talks,….
nl-reasoning-workshop.github.io
Natural Language Reasoning and Structured Explanations Workshop ---
0
18
0