bhavana dalvi @bhavana_dalvi
Lead Research Scientist at Allen Institute for Artificial Intelligence @allenai_org , NLP/AI Research Seattle WA Joined August 2009-
Tweets34
-
Followers116
-
Following47
-
Likes23
Is it possible to build end-to-end autonomous discovery systems using Large Generative Models (LGMs)? 🧬 In this position paper, we argue: arxiv.org/pdf/2402.13610… 🧵 (1/n) @allen_ai @ai2_aristo @surana_h @UMassAmherst @UUtah
Excited to share our recent paper led by @Nathaniel_Weir 🥳 Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic tinyurl.com/bdehyv5k Thanks to all the collaborators!
Excited to share our recent paper led by @Nathaniel_Weir 🥳 Enhancing Systematic Decompositional Natural Language Inference Using Informal Logic tinyurl.com/bdehyv5k Thanks to all the collaborators!
Excited to share our work on Continual Learning via Skill Set Optimization🥳 Can a language agent explore new interactive tasks, automatically identify useful skills, generalize them to new tasks? allenai.github.io/sso with @kolbytn @mbodhisattwa @sameer_ Peter Clark @roydfox
Excited to share our work on Continual Learning via Skill Set Optimization🥳 Can a language agent explore new interactive tasks, automatically identify useful skills, generalize them to new tasks? allenai.github.io/sso with @kolbytn @mbodhisattwa @sameer_ Peter Clark @roydfox
Excited to share our work, "Skill Set Optimization", a continual learning method for LLM actors that: - Automatically extracts modular subgoals to use as skills - Reinforces skills using environment reward - Facilitates skill retrieval based on state allenai.github.io/sso 🧵
Using a dynamic, persistent memory, CLIN is the first continually learning model that excels in both task adaptation & generalization to unseen tasks in a zero-shot setup. Explore this exciting new work by AI2's @mbodhisattwa and @bhavana_dalvi, and the @ai2_aristo team:
Using a dynamic, persistent memory, CLIN is the first continually learning model that excels in both task adaptation & generalization to unseen tasks in a zero-shot setup. Explore this exciting new work by AI2's @mbodhisattwa and @bhavana_dalvi, and the @ai2_aristo team:
We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. @ai2_aristo @allen_ai Website: allenai.github.io/clin/ Let's dive in 🧵 (1/n)
(n/n) This was only possible with the huge team effort: @bhavana_dalvi, @peterjansen_ai, Oyvind, Niket, @liharryzhang, Chris Callison-Burch, and Peter Clark! CLIN is open source: github.com/allenai/clin Paper: arxiv.org/pdf/2310.10134…
The deadline for the Workshop on Natural Language Reasoning and Structured Explanations ( nl-reasoning-workshop.github.io ) has been extended until *May 3, AoE*. This is mostly accommodate ACL decisions, but gives you a chance to make your submissions even more awesome :)
📣Call for papers! The Natural Language Reasoning and Structured Explanations Workshop will be the first of its kind at ACL 2023, and the deadline for paper submissions is April 24. Learn more and submit here: nl-reasoning-workshop.github.io
We ( @bhavana_dalvi , @peterjansen_ai , @danilodnr2 , @_jasonwei , and Lionel Wong from @MITCoCoSci ) are excited to announce the 1st Workshop on Natural Language Reasoning and Structured Explanations, co-located with ACL 2023. 🧵 nl-reasoning-workshop.github.io
Models can output the darnedest things. But how do they come up with their answers, and what if you could help correct them? Bhavana Dalvi and teammates from @ai2_aristo introduce TeachMe, a framework to understand and correct AI models: blog.allenai.org/towards-teacha…
Please vote for the workshop proposals for EACL/ACL-IJCNLP/EMNLP/ NAACL-HLT 2021 forms.gle/kkfsQZjjs2hFYi… @acl2020 @naacl @allenai_org @uwnlp @ACL_NLP #ACL2020 #naacl #NLP #ACL_NLP -- The EACL/ ACL-IJCNLP / EMNLP / NAACL-HLT 2021 Workshop chairs
3/3 papers accepted #emnlp2019 #ai2 🎉 -Everything Happens for a Reason: Discovering the Purpose of Actions -WIQA: A dataset for What if... reasoning -Pretrained Language Models for Sequential Sentence Classification @KeisukeS_ @armancohan @danielking36 @i_beltagy @ds @scottyih
Buses still not running due to excessive snow on roads :P
Again, we do not anticipate restoring bus and T service tonight, and will reassess early tomorrow morning.
Amazed by Britains got talent episodes, so many people with so many talents :D
http://www.youtube.com/watch?v=9AP30br94ro&feature=related
Ashutosh Mehra @ashutoshmehra
1K Followers 5K Following Senior Principal Scientist at Adobe. Working on Acrobat AI Assistant, LLMs, and document ML.Iris Ma @iris_ma14
107 Followers 934 Following PhD Student @UCIrvine under @cristalopes | #SE | #LLM4Code | program verificationNathaniel Weir @Nathaniel_Weir
507 Followers 851 Following PhD candidate @jhuclsp working on reasoning. Formerly @ai2_aristo, MS Semantic Machines, @MSFTResearch, @BrownCSDept. On the job market (industry/postdoc)Dhruv Agarwal @dhruvagarwal17
208 Followers 549 Following CS PhD student @UMassAmherst IESL @UMass_NLP, working on ML for NLP. Multi-step reasoning, retrieval augmentation, and automated scientific discovery.AI Deeply @AiDeeply
404 Followers 5K Following AI is reshaping the world. Who are the people and companies driving the change? Visit our website to search more than 5,000 profiles.wangzhuxi666 @wangzhuxi666
93 Followers 4K FollowingTeemu Summanen @teemusum
193 Followers 3K Following A software engineer working with AI, security, healthcare technology.👨🏼💻At X for reading diverse views by professionals and hobbyists.🔬📚🫶Yuntian Deng @yuntiandeng
3K Followers 3K Following #NLProc Postdoc @ai2_mosaic | Assistant Professor @UWaterloo '24 | Faculty Affiliate @VectorInst '24 | PhD @HarvardAllen Institute for A.. @allen_ai
54K Followers 361 Following AI for the Common Good. › Join us: https://t.co/DqTs1G4bGO › Get our newsletter: https://t.co/tvb1VpySfLZhaowei Wang @ZhaoweiWang4
725 Followers 673 Following PhD student @HKUSTKnowComp | Supervised by @yqsong | Intern @NVlDlAAl | Linguistic Entailment & Abstraction | Causal Inferenceresearcher Gpt LLM @researchGptllm
233 Followers 4K Followingturing — e/acc @linus_turing
614 Followers 5K FollowingShramay Palta @PaltaShramay
484 Followers 910 Following Incoming Research Intern @MSFTResearch | CS PhD student @umdcs. #NLProc at @ClipUmd. | B.E. EEE @bitspilaniindia | Commonsense + NLP, AI, CompLing | he/himErfan Shayegani @Erf_Shayegani
129 Followers 438 Following BSc EE @ SUT — 2nd year PhD CS @UCR_CSE GenAI - Trustworthiness - AI Safety 😈 Incoming Intern at @MSFTResearchKnowComp HKUST @HKUSTKnowComp
405 Followers 532 Following Knowledge Computation Group@HKUST, led by Prof. Yangqiu Song @yqsong.Keshav Bimbraw @KeshavBimbraw
435 Followers 5K Following Ph.D. Candidate, Robotics @WPI | @Google CSRMP 2021B | Prev: @merl_news @BellLabs @Bose @GeorgiaTech @iitdelhi @TIETofficialAnirudh Thatipelli @AThatipelli
453 Followers 3K Following MS-CS @UCR_CSE, Former Applied Science Intern at @amazonMarziyeh Movahedi @MarziMovahedi
59 Followers 1K Following CAPTCHA Verified Human | Trained on Multi Modal Data over the past decades but not converged yet | #WomenLifeFreedomRoss @ma1547372858
15 Followers 1K FollowingMatthew Finlayson @mattf1n
799 Followers 868 Following First year PhD at @nlp_usc | Former predoc at @allen_ai on @ai2_aristo | Harvard 2021 CS & LinguisticsRoshan Sharma @RoshanSSharma2
301 Followers 370 Following Research Scientist Google | PhD @CMU_ECE | #SpeechProc #NLProc | Previously @AIatMeta @QualcommAniket Vashishtha @AniketVashisht8
354 Followers 554 Following Predoctoral Research Fellow working on NLP & Causality @MSFTResearchBasel Mousi @baselmousi995
280 Followers 1K Following An electrical and computer engineer with a BE from @aub_lebanon. Research assistant @QatarComputingWenting Zhao @wzhao_nlp
812 Followers 356 Following PhD student @cornell_tech Food for life, NLP for soul!NaKuL Dharaskar @nakuldharaskar
124 Followers 566 Followingrahul roy @remo_delhi
12 Followers 34 Followingnishagupta @nishagupta5495
0 Followers 15 FollowingShravan Kumar @hshravankumar
131 Followers 136 FollowingSameer Kurkure @kurkure
97 Followers 226 Followingnithin @nithindharm
8 Followers 216 Following cool guy!!!!!!ma life ma own rules!!!!!bitches fuckoff!!!!!Ben Alford @stuntcamel
70 Followers 163 Followingvijay @thoutamvijay
116 Followers 2K Followingsheikabdulla @sheikab87158747
43 Followers 731 Followingசுதாகர்.. @sudakarganesan
188 Followers 4K Following என்னை மதிக்காதவர்களை நானும் மதிப்பதில்லை அதற்கு நீங்கள் வைக்கும் பெயர் தலைக்கனம் என்றால் நான் வைக்கும் பெயர் தன்மானம்...Rajarshi Rakshit @rajarshirakshit
90 Followers 48 Following A fool who wants to understand himself...yusuf sayyad @YusufSayyad5
738 Followers 3K Following कागज की नाव बनाके हम भी खेले हैं। दुनिया के जुल्म हमने भी झेले हैं। बे परवाह हैं वो जालिम जमाना जिसने दुनिया में मजहबी ज़हर घोलें हैं।Varun Arora @2pointsomeone
616 Followers 2K Following Founder, @OpenCurriculum. Author of "AI in Schools" https://t.co/Xb0B4MSums. Former Anne Lewis fellow at @CarnegieMellon. Interested in everything about teaching. 🌱Ravi @guindyexpress
398 Followers 4K Following PhD Candidate @UCF🎓, NLP, Social Computing, Biomed, Applied ML. @Snap👻, @SiemensHealth🧠 *I am on the job market for postdoc and industry research positions!*Sarah Wiegreffe @sarahwiegreffe
4K Followers 984 Following At @allen_ai @ai2_aristo @uwnlp. Research in language model transparency & interpretability. PhD from @mlatgt @icatgt @gtcomputing. Views my own.hyunji amy lee @hyunji_amy_lee
432 Followers 239 Following PhD student @kaist_ai. Previously: @allen_ai. Working on Information Retrieval and Retrieval Augmented LMsValentina Pyatkin @valentina__py
2K Followers 1K Following Postdoc at the Allen Institute for AI @allen_ai and @uwnlpYao Fu @Francis_YAO_
14K Followers 2K Following PhD @EdinburghNLP on LLMs and Machine Reasoning. Ex. @Columbia @PKU1898 @MITIBMLab @allen_ai AGI has yet to come, so keep runningIan Magnusson @IanMagnusson
250 Followers 294 Following Predoctoral Young Investigator on AllenNLP at @allen_ai. Working on domain adaptation, reproducibility, and evaluation in NLP.Vaish Shrivastava @VaishShrivas
69 Followers 398 Following MS CS @Stanford @StanfordNLP @StanfordAILab Advised by @percyliang Applied Scientist - @Microsoft AI BS CS @CaltechArchiki Prasad @ArchikiPrasad
975 Followers 821 Following PhD student @uncnlp, advised by @mohitban47 | Undergrad @iitbombay | Prev: @allenai_org @AdobeResearch; Research interests: #NLProc #MLPeter Jansen @peterjansen_ai
1K Followers 643 Following Associate Professor @uarizona; Visiting Scientist @allen_ai, AI/NLP; EntailmentBank; ScienceWorld; WorldTree; ExplanationBank. Tweets/opinions my own.Qiming (Bill) Bao @qiming_bao
408 Followers 3K Following Ph.D. Candidate @witbrock @AucklandUni in #LLMs #Reasoning; AI Engineer @xtractaapp; ex: R&D Engineer LAIR, AIIT, @PKU1898; @AucklandUni (First-class Honours).Mrinmaya Sachan @mrinmayasachan
2K Followers 2K Following Assistant Professor of Computer Science at ETH Zurich working in natural language processing (#NLProc), machine learning and education (#edtech).Ankita Bhaumik @AnkitaBhaumik3
43 Followers 198 Following PhD student @RPI 👩🏻🏫 | NLP AI Enthusiast 😵💫 | Bibliolater 📖 |Kolby Nottingham @kolbytn
209 Followers 228 Following CS PhD at @UCIrvine researching RL+NLP and interactive LLMs. Upcoming intern @riotgames. Previously @allen_ai, @AiDungeon, @unity, and @nvidia .Hanna Hajishirzi @HannaHajishirzi
6K Followers 328 Following Associate professor at @uw_cse; senior director at @allen_ai co-leading @allenNLP; AI/NLP researcher at @uw_nlpBodhisattwa Majumder @mbodhisattwa
1K Followers 795 Following Research @allen_ai. Scientific Discovery, Language & Interactive Agents. PhD @ucsd_cse, @AdobeResearch Fellow. Prev @googleai @metaai @msftresearchAllen Institute for A.. @allen_ai
54K Followers 361 Following AI for the Common Good. › Join us: https://t.co/DqTs1G4bGO › Get our newsletter: https://t.co/tvb1VpySfLAristo Team at AI2 @ai2_aristo
782 Followers 9 Following Building machines that can read, learn and reason at @allen_ai Join us: https://t.co/U4rmyx7f1ENAACL HLT 2024 @naaclmeeting
8K Followers 50 Following The official account of the Annual Conference of the North American Chapter of the Association for Computational Linguistics.NAACL @naacl
6K Followers 3 FollowingVipul Mathur🐧 @VipulMathur
966 Followers 2K Following Infrastructure for AI and AI for Infrastructure • Find me at https://t.co/dKkgqkLdmWPriya Radhakrishnan @PriyaRKrishnan
78 Followers 87 Following PhD in Computer Science Engineering, ALU alumni.Sapna Jain @sapnajainkansal
75 Followers 198 FollowingIz Beltagy @i_beltagy
2K Followers 422 Following Cofounder @SpiffyAI, Research Lead building OLMo at @allenai_org, formerly @UTCompSci PhD.Amazon Prime Student @primestudent
121K Followers 126 Following The Official Amazon Prime Student Twitter FeedNaman Gupta @nakugu
48 Followers 34 FollowingInner Awakening @Inner_Awakening
1K Followers 1K Following Inner awakening: a 21 day experiential meditation program providing inspiration, life tools, yoga & meditation to Radiate Enlightenment. Paramahamsa Nithyanandafreefoodcam @freefoodcam
89 Followers 0 FollowingAjay Sarda @ajaykrsarda
52 Followers 21 FollowingShubha Maheshwari @shubha_mohunta
59 Followers 74 FollowingKuldeep @kuldeepgharat
50 Followers 37 FollowingPraj K @pskalekar
301 Followers 152 Followingsandeep @nabulain
11 Followers 8 FollowingYogesh Powar | यो.. @yogeshpowar
295 Followers 485 Following Tech Architect: Web & Semiconductors. A runner (26.2) turned triathlete (70.3). and an Ajinkyan.MovedTo @VipulMathur @VipulMathur8
114 Followers 1 Following This twitter account is no longer active. Please interact with @VipulMathur instead.Amit Lokare @amitlokare
46 Followers 189 Followingkritipuniyani @kritipuniyani
93 Followers 62 FollowingSantosh C @santoshyd
43 Followers 69 FollowingVibhooti Verma @VibhootiVerma
68 Followers 47 Followingsandeep @sandeepsatpal
148 Followers 98 FollowingSaurabh Sahni @saurabhsahni
1K Followers 490 Following Developer Platform at @SlackHQ, Tech, Startups, Foodie, Traveler, Reader, Formerly: @Yahoo, @YDN, @FlurryMobile. Author @OReillyMedia https://t.co/GNDri1lRGQIs it possible to build end-to-end autonomous discovery systems using Large Generative Models (LGMs)? 🧬 In this position paper, we argue: arxiv.org/pdf/2402.13610… 🧵 (1/n) @allen_ai @ai2_aristo @surana_h @UMassAmherst @UUtah
🚨 How can we achieve high-quality logic in LLM-powered entailment engines? 🔍 We introduce: 1️⃣ A theory-driven method to classify good vs bad compositional entailments 2️⃣ A novel corpus-grounded entailment tree generator, TreeWise 🌲 Paper: arxiv.org/abs/2402.14798 🧵
New work from @ai2_aristo is live on arxiv! Congrats to all involved -- @kolbytn @mbodhisattwa @bhavana_dalvi @sameer_ Peter Clark and @roydfox 🙌 Learn more ▶️ Project Site: allenai.github.io/sso Paper: arxiv.org/abs/2402.03244 Code: github.com/allenai/sso
Excited to share our work, "Skill Set Optimization", a continual learning method for LLM actors that: - Automatically extracts modular subgoals to use as skills - Reinforces skills using environment reward - Facilitates skill retrieval based on state allenai.github.io/sso 🧵
Excited to share our work, "Skill Set Optimization", a continual learning method for LLM actors that: - Automatically extracts modular subgoals to use as skills - Reinforces skills using environment reward - Facilitates skill retrieval based on state allenai.github.io/sso 🧵
Thank you to my coauthors @mbodhisattwa, @bhavana_dalvi, @sameer_, Peter Clark, and @roydfox! Learn more at the links below: Project Site: allenai.github.io/sso Paper: arxiv.org/abs/2402.03244 Code: github.com/allenai/sso
Congratulations to @swabhz, a previous AI2 Young Investigator, for her recognition as an Intel Rising Star Faculty member. Read more about Swabha's journey via @USCViterbi: viterbischool.usc.edu/news/2023/10/s…
AI2's CEO Ali Farhadi believes that advancements in AI demand "radical openness." In a conversation with @nytimes' @SteveLohr, Ali pushes for a glass box approach, allowing researchers to better understand AI behavior: nytimes.com/2023/10/19/tec…
Great work! Life-long learning for language agents is such an important and tricky problem, glad that CLIN presents a nice solution🙋♀️
We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. @ai2_aristo @allen_ai Website: allenai.github.io/clin/ Let's dive in 🧵 (1/n)
To create truly personalized LLM-powered systems, LLMs need to learn from very few interactions, quickly adapt, and transfer learned knowledge. Congrats to @mbodhisattwa, @bhavana_dalvi, and team. Lot's of exciting work happening at @ai2_aristo!
We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. @ai2_aristo @allen_ai Website: allenai.github.io/clin/ Let's dive in 🧵 (1/n)
Using a dynamic, persistent memory, CLIN is the first continually learning model that excels in both task adaptation & generalization to unseen tasks in a zero-shot setup. Explore this exciting new work by AI2's @mbodhisattwa and @bhavana_dalvi, and the @ai2_aristo team:
We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. @ai2_aristo @allen_ai Website: allenai.github.io/clin/ Let's dive in 🧵 (1/n)
We are excited to announce CLIN 🤖: The first continually learning language agent that excels in both task adaptation and generalization to unseen tasks and environments in a pure zero-shot setup. @ai2_aristo @allen_ai Website: allenai.github.io/clin/ Let's dive in 🧵 (1/n)
(n/n) This was only possible with the huge team effort: @bhavana_dalvi, @peterjansen_ai, Oyvind, Niket, @liharryzhang, Chris Callison-Burch, and Peter Clark! CLIN is open source: github.com/allenai/clin Paper: arxiv.org/pdf/2310.10134…
Large language models are impressive, but do they have coherent "beliefs" about the world? And do they form anything like a mental model when reasoning? Check out this talk by AI2's Interim CEO Peter Clark for @sfiscience: "What do our Machines Dream of?" youtube.com/watch?v=H7p4HI…
The deadline for the Workshop on Natural Language Reasoning and Structured Explanations ( nl-reasoning-workshop.github.io ) has been extended until *May 3, AoE*. This is mostly accommodate ACL decisions, but gives you a chance to make your submissions even more awesome :)
At long last, it's out! The Semantic Reader Project - our vision for an AI-augmented scientific reading interface... semanticscholar.org/reader/67a5bac… @SemanticScholar @allen_ai
📣Call for papers! The Natural Language Reasoning and Structured Explanations Workshop will be the first of its kind at ACL 2023, and the deadline for paper submissions is April 24. Learn more and submit here: nl-reasoning-workshop.github.io
I was one of the *so many*. Couldn't agree more! (For us Iranians there was a travel ban in effect too! For 4/5 years of my student life )
This point is never mentioned: There are *so many* international grad students "stuck" in the US because they might be denied re-entrance / renewing their travel visa would take forever. Their only chance of presenting in person is that occasionally conferences are in the US.
On the PRIOR team, @ehsanik is pushing the boundaries of indoor robotics. Read about her career journey, current work and favorite Seattle activities in her Featured AI2er profile: blog.allenai.org/featured-ai2er…
We ( @bhavana_dalvi , @peterjansen_ai , @danilodnr2 , @_jasonwei , and Lionel Wong from @MITCoCoSci ) are excited to announce the 1st Workshop on Natural Language Reasoning and Structured Explanations, co-located with ACL 2023. 🧵 nl-reasoning-workshop.github.io
Models can output the darnedest things. But how do they come up with their answers, and what if you could help correct them? Bhavana Dalvi and teammates from @ai2_aristo introduce TeachMe, a framework to understand and correct AI models: blog.allenai.org/towards-teacha…