Aristo Team at AI2
@ai2_aristo
Followers
916
Following
67
Media
10
Statuses
77
Building machines that can read, learn and reason at @allen_ai Join us: https://t.co/U4rmyx7f1E
Seattle, WA
Joined April 2022
RT @JesseDodge: Today we released SciArena! It's totally free, try asking questions about scientific topics, papers, citations, etc! Every….
0
8
0
RT @allen_ai: 🚨 We're hiring a #ResearchScientist in #AI for Scientific Discovery at Ai2!. Are you passionate about intelligent agents, dat….
0
8
0
RT @allen_ai: Today we’re releasing a prototype of Genesys, an autonomous multi-agent LLM discovery system that aims to discover new types….
0
35
0
RT @allen_ai: Imagine AI doing science: reading papers, generating ideas, designing and running experiments, analyzing results… How many mo….
0
97
0
RT @bhavana_dalvi: We (@peterjansen_ai, @mbodhisattwa, @tusharkhot,.@harsh3vedi, @Hoper_Tom, @_DougDowney, @erichorvitz) are excited to ann….
0
11
0
AppWorld ( recognized at #ACL2024nlp with a Best Resource Paper award!. Congratulations to @harsh3vedi and collaborators from @stonybrooku and @allen_ai for this exciting new environment for interactive coding agents!.
🏆 AppWorld received a Best Resource Paper award @ #ACL2024nlp #NLProc. ✨ I am honored & deeply grateful for it. AppWorld has been my key focus for the last 1.5 yrs. I can't overstate how much hard work, care, patience & obsession w/ quality have gone into its every aspect. 1/n
0
2
12
Want to build or test Interactive Coding Agents? Check out AppWorld, an exciting new multi-app simulated environment and benchmark from @stonybrooku and @allen_ai !.
🔥 Autonomous AI Assistants (e.g., #googleio2024, #WWDC24) and coding agents (e.g., #Devin, #SWEAgent) have garnered a lot of attention recently. We can envision coding agents autonomously completing complex day-to-day tasks across apps using APIs on our behalf. But how can we
0
2
10
NLRSE workshop @ ACL 2024: Deadline extended to May 21 AoE! Also note that non-archival cross-submissions (papers accepted to other venues, such as ACL Findings) can be submitted on the Google Form here:
We ( @gregd_nlp , @bhavana_dalvi , @peterjansen_ai , @danilodnr2 , @xiye_nlp , @wzhao_nlp , @ben_lipkin , and Lionel Wong from @MITCoCoSci ) are excited to announce the 2nd Workshop on Natural Language Reasoning and Structured Explanations (NLRSE), co-located with ACL 2024. 🧵
0
1
5
RT @gu_yuling: Our paper 🤖 “Digital Socrates: Evaluating LLMs through Explanation Critiques” 🤖 has been accepted to the #ACL2024NLP main co….
0
8
0
RT @gregd_nlp: We ( @gregd_nlp , @bhavana_dalvi , @peterjansen_ai , @danilodnr2 , @xiye_nlp , @wzhao_nlp , @ben_lipkin , and Lionel Wong f….
0
26
0
RT @mbodhisattwa: Incredibly proud of our teamwork, now in @icmlconf! This position starts a series of work on data-driven scientific disco….
0
14
0
RT @hsanchaita: 🌻 Super excited about my first Computer Science publication at @naaclmeeting (main)! @mbodhisattwa and I study the language….
0
7
0
RT @clefourrier: Is chain of thought actually helping your model? 🤔. According to the CoT Leaderboard, it seems more useful for the smaller….
0
6
0
"The Illusion of State in State Space Models" -- @lambdaviking, @jowenpetty, and @Ashish_S_AI find that newly popular "state" space models (SSMs) are surprisingly as limited as Transformers when it comes to tracking state.
✨Excited to finally drop our new paper: SSMs “look like” RNNs, but we show their statefulness is an illusion🪄🐇. Current SSMs cannot express basic state tracking, but a minimal change fixes this! 👀. w/ @jowenpetty, @Ashish_S_AI.
1
0
13
Wondering why Chain-of-Thought appears to make Transformers more powerful? Find out from @benbenbrubaker's elegant and broad overview📜 in Quanta Magazine, covering an upcoming ICLR-2024 paper by @lambdaviking, @Ashish_S_AI on precisely this topic!.
Today in Quanta Magazine, @benbenbrubaker gives a new overview of our work (w/ @Ashish_S_AI) on the expressive power of transformers with/without CoT.
0
0
1
RT @ArchikiPrasad: 🎉Our work ADaPT on enabling LLM agents to dynamically “adapt” to task complexity & LLM capabilities via recursive decomp….
0
28
0
RT @mbodhisattwa: Is it possible to build end-to-end autonomous discovery systems using Large Generative Models (LGMs)? 🧬. In this position….
0
33
0
RT @gu_yuling: Looking for an ✨⚙️ interpretable explanation evaluation tool 🔧💫 that can 🤩🔎 automatically characterize the explanation capab….
0
2
0