Faeze Brahman @faeze_brh Twitter profile | Pikagi

Pikagi

Faeze Brahman

@faeze_brh

1,602

Followers

1,068

Following

30

Media

479

Statuses

Postdoc @allen_ai @ai2_mosaic @uw | Ph.D. from UCSC | Former Intern @MSFTResearch , @allen_ai | Researcher in #NLProc , #ML

Seattle, WA

https://t.co/DcEd3SiT0g

Joined May 2018

Don't wanna be here? Send us removal request.

Pinned Tweet

@faeze_brh

Faeze Brahman

7 months

📢 Generative models seem to acquire generation abilities more effectively than understanding, in contrast to human intelligence where generation is usually harder! Excited to announce our very recent work on 🔥Generative AI Paradox! paper:

Tweet card media

The Generative AI Paradox: "What It Can Create, It May Not...

The recent wave of generative AI has sparked unprecedented global attention, with both excitement and concern over potentially superhuman levels of artificial intelligence: models now take only...

@PeterWestTM

Peter West

7 months

Richard Feynman said “What I cannot create, I do not understand”💡 Generative Models CAN create, i.e. generate, but do they understand? Our 📣new work📣 finds that the answer might unintuitively be NO🚫 We call this the 💥Generative AI Paradox💥 paper:

Tweet media one

23

110

565

1

18

75

Last Seen Profiles

@wiktil_345

@massrrevolution

@OSUsoccer

@poopy69poopy420

@sarahbergstromm

@r8toa

@slb77579988804

@ProficFicus

@jandakembangstw

@SHANKK50

@Anaimiya2

@tchxls

@TwinkGlobal

@Sukabinorstw11

@stwmaniax

@pookiefnr

@MetaDOS

@FutbolRebelia

@pengen_stw

@StrikesTakeOver

@Fitriniez06

@Fitriniez06

@Fitriniez06

@thinkazazel

@AFCBergholt

@SempereBomboi

@BassettKai45070

@kristendodgen

@DigitalPalm

@Fitriniez06

@jandakembangstw

@Lone_associate

@SBrondello

@sulmamacita

@Sterlingcairo

@mango_don876

@faeze_brh

Faeze Brahman

1 year

Can small LMs perform planning with the same level of proficiency as #LLMs ? Can they reason abt contextualized situations that are often counterfactual?🔥Introducing PlaSma, a 2-pronged approach endowing smaller models with procedural knowledge & counterfactual planning abilities

Tweet media one

4

40

195

@faeze_brh

Faeze Brahman

2 years

💫A life update: today is my first day @allen_ai as a postdoc, where I’ll be working with the awesome @YejinChoinka in @ai2_mosaic group! Super excited to work and collaborate with all the amazing people here, and learn new things!

14

1

159

@faeze_brh

Faeze Brahman

6 months

Can we efficiently tailor LLMs towards arbitrary user objectives without fine-tuning them?! The answer is ✅yes with IPA which combines RL and inference-time techniques! Come to our poster “Inference-time Policy Adapters” tomorrow Dec 10th at 9:00am-10:30am! #emnlp2023

Tweet media one

4

26

125

@faeze_brh

Faeze Brahman

2 years

Still feel unreal, but a few weeks ago I successfully defended my Ph.D. thesis. I’m incredibly grateful to my advisor @snigdhac25 . Thanks to my collaborators for making this happen! And big thanks to my family and all the people supporting this journey ♥️

Tweet media one

20

0

123

@faeze_brh

Faeze Brahman

3 years

📢 #AAAI2021 Check out our paper "Learning to Rationalize" w @VeredShwartz @YejinChoinka @rachelrudinger Join QA session: BC-D1-R1, Cluster F, Position 3 4-Feb 8:45-10:30AM / 4:45-6:30PM PST 📰Paper: 📺Video:

Tweet media one

4

24

104

@faeze_brh

Faeze Brahman

3 years

💫 Excited to have 3 papers accepted to #EMNLP2021 , ranging from conditional text generation for sentence ordering, character-centric narrative understanding, and implicit gender bias detection in narrative domain. kudos to my amazing co-authors 🎉 Check out 👇🏼

5

5

99

@faeze_brh

Faeze Brahman

3 years

Please be the voice of Iran! The media doesn't show what's going on. Human disaster is happening in Iran. Iranian people need Covid Vaccine! Please retweet 🙏 @WHO #sosiran #sosiran

Tweet media one

Tweet media two

Tweet media three

5

48

85

@faeze_brh

Faeze Brahman

9 months

Wednesday was our anniversary and thanks to deadlines, I completely forgot about it! My spouse (for the past year): I think I am the first author of our life paper Me: 🫠

2

0

89

@faeze_brh

Faeze Brahman

4 years

💫Delighted to share that our paper "Learning to Rationalize for Nonmonotonic Reasoning with Distant Supervision" has been accepted to #AAAI2021 🥳 Many thanks and kudos to with my amazing mentors and collaborators @VeredShwartz @YejinChoinka , and @rachelrudinger at @ai2_mosaic

Tweet media one

1

8

78

@faeze_brh

Faeze Brahman

6 months

I will be at EMNLP ✈️🇸🇬 presenting 4 papers on reinforced algorithms to steer LMs generations, contextualize and defeasible machine reasoning! Open to chat about research on LLMs, robust reasoning and generalization, language agents and other fun activities! Come and say hi 👋🏼

0

1

69

@faeze_brh

Faeze Brahman

2 years

Come join us tomorrow at Narrative Understanding Workshop #NAACL2022 to learn about interesting research. We have an amazing set of speakers @YejinChoinka @maria_antoniak @dangoldwasser Andrew Piper. We are in person at 708 Sol Duc and in zoom.

Tweet media one

Tweet media two

2

13

61

@faeze_brh

Faeze Brahman

5 months

📢 Also happy to share that PlaSma will appear at #ICLR2024 💫 Thanks to my amazing collaborators @chandra_bhagav Jena D. Hwang @valentina__py @xiang_lorraine @HironaArai @ssanyal8 @KeisukeS_ @xiangrenNLP and @YejinChoinka See y’all in 🇦🇹

@faeze_brh

Faeze Brahman

1 year

Can small LMs perform planning with the same level of proficiency as #LLMs ? Can they reason abt contextualized situations that are often counterfactual?🔥Introducing PlaSma, a 2-pronged approach endowing smaller models with procedural knowledge & counterfactual planning abilities

Tweet media one

4

40

195

1

8

56

@faeze_brh

Faeze Brahman

2 years

✈️ I will be at #EMNLP2022 in Abu Dhabi where my colleagues and I present several works at the main conference, Findings as well as the GEM workshop. Details below: 🧵(1/5)

1

2

45

@faeze_brh

Faeze Brahman

5 months

📢Happy to share that our Generative AI Paradox has been accepted to #ICLR2024 ! 🤩 This is a joint work with all amazing people at @allen_ai and @uwnlp !

@faeze_brh

Faeze Brahman

7 months

📢 Generative models seem to acquire generation abilities more effectively than understanding, in contrast to human intelligence where generation is usually harder! Excited to announce our very recent work on 🔥Generative AI Paradox! paper:

1

18

75

1

2

36

@faeze_brh

Faeze Brahman

2 years

I’m so sad leaving my Monstera behind 😭😭😭 I literally watched it grow during the last 3 years. It’s like killing me inside 😞 #someone_is_moving

Tweet media one

1

0

36

@faeze_brh

Faeze Brahman

3 years

Happy #Nowruz May this spring brings back life and beauty to our world again! #SpringEquinox #happyspring #نوروز

Tweet media one

2

0

34

@faeze_brh

Faeze Brahman

6 months

We're at 22A 😀

Tweet media one

@faeze_brh

Faeze Brahman

6 months

Can we efficiently tailor LLMs towards arbitrary user objectives without fine-tuning them?! The answer is ✅yes with IPA which combines RL and inference-time techniques! Come to our poster “Inference-time Policy Adapters” tomorrow Dec 10th at 9:00am-10:30am! #emnlp2023

Tweet media one

4

26

125

0

3

30

@faeze_brh

Faeze Brahman

9 months

Ever wonder if and how useful are modern LLMs to expert writers in their writing process? Great collaboration with @TuhinChakr @vishakh_pk and @SmaraMuresanNLP

@TuhinChakr

Tuhin Chakrabarty

9 months

🚨AI-assisted writing is a nebulous space with researchers and writers being both curious & apprehensive. How useful are current SOTA LLMs to writers?What are their needs & expectations?If this intrigues you, then buckle up🚨 Paper: #NLProc #HCI #ChatGPT

Tweet media one

4

34

100

0

2

29

@faeze_brh

Faeze Brahman

6 months

📣I am not attending Neurips but go talk to amazing @billyuchenlin about our SwiftSage, a powerful language agent for complex and situated long-horizon planning inspired by human dual process theory 🧠 ⏱️: spotlight poster session @12 /13 5Pm

@billyuchenlin

Bill Yuchen Lin 🤖

6 months

[1] SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks 📄: 🖥️: 🗣️: Spotlight Poster Session (12/13 5PM) @ Great Hall & Hall B1+B2 (level 1) #405

1

9

46

0

1

27

@faeze_brh

Faeze Brahman

11 months

Congrats to @ai2_mosaic for winning the best paper and outstanding awards! Go mosaic 🔥 Especially to authors @jmhessel @YejinChoinka @xiangrenNLP @melaniesclar @alsuhr @Ronan_LeBras @PeterWestTM @anmarasovic et al.

@allen_ai

Allen Institute for AI

11 months

Congratulations to the team, including AI2ers, who worked on "Do Androids Laugh at Electric Sheep? Humor 'Understanding' Benchmarks from The New Yorker Caption Contest" — selected for a Best Paper Award at #ACL2023 !

2

18

109

0

0

26

@faeze_brh

Faeze Brahman

3 years

💫 If you are working on multilingual/cross-lingual domains, please check our new TACL paper: "ParsiNLU: A Suite of Language Understanding Challenges for Persian"

@DanielKhashabi

Daniel Khashabi 🕊️

@DanielKhashabi

3 years

Excited that our big collaborative effort, "ParsiNLU: A Suite of Language Understanding Challenges for Persian" will appear in TACL'21! If you're working on multilingual/cross-lingual NLP, give it a look! Paper:

3

37

114

0

3

25

@faeze_brh

Faeze Brahman

3 years

First try #watercolor 🪶 🍃

Tweet media one

2

0

25

@faeze_brh

Faeze Brahman

4 years

#EMNLP2020 Check out our paper on Emotion-Aware Storytelling 🙂☹️😟😡 Join us on @ gather session: When: Nov 17, 18:00-20:00 UTC / 10:00-12:00 PST Paper: Video: With @snigdhac25

Tweet media one

1

5

25

@faeze_brh

Faeze Brahman

11 months

📢Stop by our #ACL2023NLP poster on Monday poster session 1 from 14:00-15:30 at Frontenac Ballroom to discuss information theoretic evaluation of rationales

@faeze_brh

Faeze Brahman

1 year

Existing metrics for free-text rationales narrowly focus on association with labels, offering little understanding of new information contained in the rationale to explain the label! We overcome this by introducing REV! 💫By our amazing ex-intern @hanjie_chen

1

2

18

1

4

24

@faeze_brh

Faeze Brahman

2 years

📣Checkout our recent EMNLP’22 work on story generation where we modeled inter-personal character relationships!

@nvshrao

Anvesh Rao

2 years

Check out our EMNLP 2022 @emnlpmeeting paper. We explore story generation based on inter-personal relationships! 💔👩‍❤️‍👨😃 () with @faeze_brh and @snigdhac25 at @unccs @uncnlp @UNC

Tweet media one

0

7

26

0

1

24

@faeze_brh

Faeze Brahman

3 years

Can’t agree more!

Tweet media one

0

0

23

@faeze_brh

Faeze Brahman

3 years

📢Submissions are open for the 3rd Workshop on Narrative Understanding. The workshop will be co-located with #naacl2021 on June 11. Submission deadline: 22 March 2021 More info: Submission link:

1

10

24

@faeze_brh

Faeze Brahman

2 years

A very well deserved award for the one and only @YejinChoinka 💫 super grateful to be working with her!

@uwcse

Allen School

2 years

#UWAllen @uwnlp 's @YejinChoinka aims to develop #AI with the ability to reason and communicate about the world in physical and abstract terms, like humans can do. As a 2022 #MacFellow , she looks forward to taking the “adventurous route” in her research:

Tweet media one

9

66

390

0

0

23

@faeze_brh

Faeze Brahman

3 years

📢 I am co-organizing the 3rd Workshop on Narrative Understanding with my awesome colleagues. If you are doing some work related to stories/events, consider attending/submitting to our workshop. @eaclark07 @snigdhac25 @MohitIyyer @dojoteef @LangTechLara

@aclmeeting

ACL 2024

3 years

📣Seventh Workshop on Computational Linguistics and Clinical Psychology (CLPsych) 📣The Third Workshop on Narrative Understanding 📣The Third Workshop on Privacy in NLP (7/n) #NAACL2021

1

0

3

0

8

19

@faeze_brh

Faeze Brahman

11 months

This is a sad recurring story !

@linguistMasoud

Masoud

@linguistMasoud

11 months

I’m quite used to the cruelty students can face when they apply for a US visa but this one broke me. We offered admission to a stellar, talented & hardworking student. After months of work and hundreds of dollars, an embassy officer saw him for 5 mins & said no. why? …

1K

13K

89K

1

0

19

@faeze_brh

Faeze Brahman

2 years

Happy Yalda, the darkest and longest night of the year, celebrating winter solstice! 🍉🥜🍪 #yaldanight

Tweet media one

0

0

19

@faeze_brh

Faeze Brahman

1 year

Existing metrics for free-text rationales narrowly focus on association with labels, offering little understanding of new information contained in the rationale to explain the label! We overcome this by introducing REV! 💫By our amazing ex-intern @hanjie_chen

@hanjie_chen

Hanjie Chen

1 year

How informative are explanations generated by LLMs to explain their predictions? In our #ACL2023 paper, we investigate this research question from an information-theoretic perspective (w/ @faeze_brh @xiangrenNLP @yangfeng_ji @YejinChoinka @swabhz ). Link:

Tweet media one

2

22

124

1

2

18

@faeze_brh

Faeze Brahman

3 years

Best way ( #TahChin ) to end the holidays 😍 #tahchin #persianfood

Tweet media one

1

0

14

@faeze_brh

Faeze Brahman

3 years

(3) Uncovering Implicit Gender Bias in Narratives through Commonsense Inference. At Findings. Special congrats to @DanielH68771331 for his first paper acceptance! 🎉 W/ @VeredShwartz , @snigdhac25

Tweet media one

0

2

13

@faeze_brh

Faeze Brahman

3 years

We are presenting our work on Sentence Ordering using ReBART in half an hour with @SomnathBrc at the Virtual poster session II: Semantics (12:30-14:30 AST). Come say hi if you are around 🤩 📹… #EMNLP2021 @snigdhac25

@faeze_brh

Faeze Brahman

3 years

(1) Is Everything in Order? A Simple Way to Order Sentences. Accepted at Main. Proposed a conditional text-to-marker generation framework, making the problem more tractable, and less prone to neural text degeneration. W/ @SomnathBrc and @snigdhac25

Tweet media one

1

0

7

0

3

11

@faeze_brh

Faeze Brahman

3 years

📣 Looking forward to seeing you tomorrow on our narrative understanding workshop 🤩

@snigdhac25

Snigdha Chaturvedi

3 years

Join us tomorrow for the workshop on Narrative Understanding with -Talks by @VioletNPeng @NateChambers @nasrinmmm @dbamman & @thompson_laure -Panel discussion with Laure, Nasrin, Nate, & Prashant Pandey--screenwriter from Bollywood -Exciting papers

1

13

38

0

1

11

@faeze_brh

Faeze Brahman

3 years

I bought this little cute plant on the left, and it turned out to be the one on the right in 2 months! What’s wrong with you dude? 😳🤪 We just decided to plant it somewhere one midnight and just flee 🏃🏼‍♀️

Tweet media one

Tweet media two

0

0

11

@faeze_brh

Faeze Brahman

3 years

Shouldn’t we add “please” when making requests? Or am I making a big deal of it? 🧐

0

0

10

@faeze_brh

Faeze Brahman

4 years

My pleasure to present at Wordplay workshop @NeurIPS

@rajammanabrolu

Prithviraj (Raj) Ammanabrolu

@rajammanabrolu

4 years

Our 3rd contributed talk is Towards Emotion-Aware Storytelling Using Reinforcement Learning by @faeze_brh and @snigdhac25 . Generating stories about a topic with a predefined emotional arc.

Tweet media one

1

3

4

0

2

10

@faeze_brh

Faeze Brahman

1 year

We also introduce Counterfactual Planning, a novel task that requires plan revision in response to counterfactual situations. 📊Our experiments show orders-of-magnitude smaller models (770M-11B parameters) can compete and often surpass their larger teacher models' capabilities!

1

3

11

@faeze_brh

Faeze Brahman

5 months

I’m looking for emergency reviewers! Please DM me if you’re willing to help! 🙏🏻 #reasoning #inference

5

1

9

@faeze_brh

Faeze Brahman

6 months

work by @GXiming @PeterWestTM @jaehunjung_com @jaehunjung_com @lasha_nlp @billyuchenlin @khyathi_chandu @rajammanabrolu @Lianhuiq @liweijianglw Sahana Ramnath @nouhadziri Jillian Fisher @SkylerHallinan @wellecks @xiangrenNLP @YejinChoinka

0

1

9

@faeze_brh

Faeze Brahman

3 years

Isn’t this just incredible? 🤩 Missed my country more than ever 😭

Tweet card media

Architecture & Design (@architectanddesign) • Instagram photos and videos

www.instagram.com

1

0

9

@faeze_brh

Faeze Brahman

1 year

Work done @allen_ai @uwnlp w/ @chandra_bhagav @valentina__py Jena D. Hwang @xiang_lorraine @HironaArai @ssanyal8 @KeisukeS_ @xiangrenNLP and @YejinChoinka 🔗Check details:

Tweet card media

PlaSma: Making Small Language Models Better Procedural Knowledge...

Procedural planning, which entails decomposing a high-level goal into a sequence of temporally ordered steps, is an important yet intricate task for machines. It involves integrating common-sense...

0

1

10

@faeze_brh

Faeze Brahman

3 years

@ilyaraz2 Normal life of Iranian students even without pandemic ...

1

0

8

@faeze_brh

Faeze Brahman

1 year

🚀With PlaSma, we developed symbolic procedural knowledge distillation to enhance implicit knowledge in small language models and an inference-time algorithm for more structured and accurate reasoning!

Tweet media one

Tweet media two

1

0

8

@faeze_brh

Faeze Brahman

1 year

Super exciting news!

@allen_ai

Allen Institute for AI

1 year

Today we're thrilled to announce our new undertaking to collaboratively build the best open language model in the world: AI2 OLMo. Uniquely open, 70B parameters, coming early 2024 – join us!

34

194

662

0

0

8

@faeze_brh

Faeze Brahman

1 year

Combining the power of behavior cloning and LLMs takes grounded action planning to a new level! Read our new paper to discover how to excel in complex interactive reasoning tasks!

@billyuchenlin

Bill Yuchen Lin 🤖

1 year

How should we maximize the planning ability of #LLM while reducing the computation cost? 🚀 Introducing SwiftSage, an agent inspired by “fast & slow thinking”, which solves complex interactive tasks much better than prior agents (e.g., DRRN, SayCan, ReAct, and Reflexion). [1/n]

Tweet media one

2

54

253

0

0

8

@faeze_brh

Faeze Brahman

3 years

(2) "Let Your Characters Tell Their Story'': A Dataset for Character-Centric Narrative Understanding. At Findings. New dataset and tasks to explore narrative understanding from character's perspective! W/ Meng Huang, Oyvind Tafjord, @zhaochaocs , @mrinmayasachan , @snigdhac25

Tweet media one

1

1

8

@faeze_brh

Faeze Brahman

1 year

Looking forward to future iterations 🙌

@VioletNPeng

Violet Peng

1 year

We wrapped up the workshop with a well-attended room and exciting discussions over the posters. Shoutout to the co-organizers @HawShiuan @RuohanGao1 @faeze_brh @rajammanabrolu @jiajunwu_cs @mohitban47 Julian McAuley, Jing Huang, Arindam Mandal

Tweet media one

Tweet media two

0

1

9

0

0

7

@faeze_brh

Faeze Brahman

6 months

Paper: Code:

Tweet card media

GitHub - GXimingLu/IPA: Codebase for Inference-Time Policy Adapters

Codebase for Inference-Time Policy Adapters. Contribute to GXimingLu/IPA development by creating an account on GitHub.

0

3

7

@faeze_brh

Faeze Brahman

1 year

We extended the submission deadline through 4/28 for the 5th Narrative Understanding Workshop! Consider submitting archival or non-archival works! See you at ACL this year

@eaclark07

Elizabeth Clark

1 year

The 5th Workshop on Narrative Understanding is now accepting submissions! We’ll be at ACL this year and are accepting both archival and non-archival submissions (deadline: April 24). Hope to see you there!

0

6

14

0

0

7

@faeze_brh

Faeze Brahman

2 years

Submit your works to our workshop on Creative AI across modalities at AAAI’23! The submission deadline is Nov 4.

@rajammanabrolu

Prithviraj (Raj) Ammanabrolu

@rajammanabrolu

2 years

Announcing the 1st Workshop on 🎨Creative AI Across Modalities🎶 at AAAI 2023! Come chat and learn about the latest in creative AI for Art, Music, Narrative, Poetry, Sciences and so much more from the entire community! 4-8 pg submissions due: Nov 4 More:

Tweet media one

1

34

130

0

0

7

@faeze_brh

Faeze Brahman

3 years

(1) Is Everything in Order? A Simple Way to Order Sentences. Accepted at Main. Proposed a conditional text-to-marker generation framework, making the problem more tractable, and less prone to neural text degeneration. W/ @SomnathBrc and @snigdhac25

Tweet media one

1

0

7

@faeze_brh

Faeze Brahman

2 years

On Dec 11, come to Commonsense reasoning session at 9:00-10:30 (Hall B) to hear us presenting Maieutic prompting 🤩 with Jaehun and @Lianhuiq @wellecks @chandra_bhagav Ronan and @YejinChoinka 🧵(4/5) 👇

@ethayarajh

Kawin Ethayarajh

2 years

A favorite recent read: Maieutic Prompting LLMs have a soft intuition for whether a claim is true/false even if they get it wrong, so ask them to recursively explain why, use log prob as confidence, build a graph, then feed it into a weighted SAT solver.

Tweet media one

3

40

260

1

1

6

@faeze_brh

Faeze Brahman

3 years

@jmhessel Almost 3 years 😔 Wish you a Xmas that’s merry and bright! ⭐️

0

0

6

@faeze_brh

Faeze Brahman

2 years

On 10th, @nvshrao and I present our work on inter-character relationship-driven story generation. Location: virtual poster poster session 10 Time: 3:30pm Also come chat in person!👇 🧵(3/5)

@nvshrao

Anvesh Rao

2 years

Check out our EMNLP 2022 @emnlpmeeting paper. We explore story generation based on inter-personal relationships! 💔👩‍❤️‍👨😃 () with @faeze_brh and @snigdhac25 at @unccs @uncnlp @UNC

Tweet media one

0

7

26

1

0

6

@faeze_brh

Faeze Brahman

2 years

On 7th at GEM, I will present #EMNLP2022 Findings paper where we proposed a new task of Grounded-keys-to-text generation along with a large-scale dataset to generate paragraph-level entity description given only guiding keys. Time: 21:00-22:30 @snigdhac25

Tweet media one

Tweet media two

2

1

6

@faeze_brh

Faeze Brahman

3 years

Question to the community: When do you think we should be afraid of AI? 🧐 I go first 🙋🏻‍♀️: When it can predict USCIS’s output with a moderate accuracy!!!

1

1

5

@faeze_brh

Faeze Brahman

2 years

The narrative of what happened yesterday and last night in #دانشگاه_شریف is the size of a book. In addition to all its bitterness, the formation of a human wall of professors, generally veterans, for the students to leave the university was beautiful.

@SharifiZarchi

علی شریفی زارچی

2 years

روایت آنچه دیروز و دیشب در #دانشگاه_شریف رخ داد به اندازه‌ی یک کتاب است. در کنار همه‌ی تلخی‌های آن، تشکیل دیوار انسانی استادان، عموما پیش‌کسوت، برای خروج دانشجویان از دانشگاه زیبا بود.

3K

21K

81K

0

1

5

@faeze_brh

Faeze Brahman

1 year

@valentina__py @rajammanabrolu LOL, alright then. I should maybe enjoy a bit! ☀️

0

0

5

@faeze_brh

Faeze Brahman

1 year

@mbodhisattwa @limufar Well, if I don’t, someone else does! Better to hear from someone who felt the pain, lol! No I’m kidding. You will enjoy the best next 5 months of it 🥳☀️🚣‍♀️⛵️

1

0

5

@faeze_brh

Faeze Brahman

1 year

Go work with Raj! He is super cool and great 🥳

@rajammanabrolu

Prithviraj (Raj) Ammanabrolu

@rajammanabrolu

1 year

Soon™, I'll be an Asst Prof @UCSanDiego @UCSD_CSE focusing on interactive & grounded AI, RL, NLP I will also be a research scientist @MosaicML helping lead efforts to make tech like RLHF more accessible Looking for PhD students & research eng/scientists to join me in ☀️SoCal🏖️

Tweet media one

Tweet media two

Tweet media three

74

41

549

1

0

5

@faeze_brh

Faeze Brahman

2 years

Our workshop ddl is now extended to Nov 18! More time to be more Creative 👨‍🎨🎶📚

@rajammanabrolu

Prithviraj (Raj) Ammanabrolu

@rajammanabrolu

2 years

By popular request we're extending our deadline by two weeks to Nov 18! More time to get your creative submissions in!

0

6

13

0

0

5

@faeze_brh

Faeze Brahman

2 years

What else should happen for this to be covered by media outlets?!

@HannaHajishirzi

Hanna Hajishirzi

@HannaHajishirzi

2 years

My alma mater, Sharif University of Technology, Iran's premier university, was under siege yesterday. Many students were arrested, heavily injured or perhaps killed. Many Iranian scholars and PhD students whom you know have received their BSc degrees from this university.

1

57

399

0

0

3

@faeze_brh

Faeze Brahman

3 years

@real_asli @YejinChoinka @iclr_conf Can those not registered for the conf somehow watch a recorded talk later? :)

1

0

4

@faeze_brh

Faeze Brahman

3 years

@ilyaraz2 I actually hope things go back to a good normal for all 😇

0

0

3

@faeze_brh

Faeze Brahman

3 years

@aellienation بیا کالیفورنیا ( north cal) اونوقت لازم نیست با کسی رقابت کنی 😅

1

0

4

@faeze_brh

Faeze Brahman

1 year

@anmarasovic I think all min/max pooling and average logits of subtokens can be used and its empirical . Btw if you define labels as special tokens, you’d perhaps get single logit for the label word?

0

0

4

@faeze_brh

Faeze Brahman

6 months

@hyunw__kim @jmhessel @liweijianglw @PeterWestTM @GXiming @YoungjaeYu3 @peizNLP @Ronan_LeBras @malihealikhani @gunheekim @MaartenSap @YejinChoinka @allen_ai Congrats 🎉🤩

0

0

3

@faeze_brh

Faeze Brahman

2 years

@VeredShwartz Why didn’t I get one when flying w/ Frontier, arrived 1 hour earlier and had to *remain seated* the entire one hour 🤦🏻‍♀️

0

0

4

@faeze_brh

Faeze Brahman

3 years

Seriously why not metric? 😃🤦🏻‍♀️

Tweet media one

0

0

4

@faeze_brh

Faeze Brahman

1 year

@VeredShwartz @peterjansen_ai Moms-like advice: don't express your interest in the apartment 😀

0

0

4

@faeze_brh

Faeze Brahman

2 years

Submission for the fourth Workshop on Narrative Understanding (WNU) is now open!

@MohitIyyer

Mohit Iyyer

2 years

Call for papers for the fourth Workshop on Narrative Understanding (WNU, to be held at #NAACL2022 ) is now available! Please consider submitting your work :) #NLProc Submission deadline: April 15

0

14

33

0

2

4

@faeze_brh

Faeze Brahman

2 years

And come chat with @zhaochaocs @snigdhac25 and I about our recent dataset 🌳NarraSum, an abstractive narrative summarization dataset with plot pairs of movies and TV episodes 🧵(5/5) 👇

@zhaochaocs

Chao Zhao

2 years

Introducing 🌳 NarraSum: an abstractive narrative summarization dataset with 122K plot pairs of movies and TV episodes. w/ @faeze_brh , Kaiqiang, Wenlin, Dian, and @snigdhac25 #emnlp2022 Paper: Data:

Tweet media one

0

7

28

0

0

4

@faeze_brh

Faeze Brahman

5 months

Joint work w/ @PeterWestTM @GXiming @nouhadziri @LINJIEFUN Jena D Huang @liweijianglw Jillian Fisher @lasha_nlp @khyathi_chandu Benjamin Newman @PangWeiKoh @AllysonEttinger and @YejinChoinka 🤩

0

0

4

@faeze_brh

Faeze Brahman

3 years

@MaartenSap That’s so true! I initially thought this feeling and act of comparison are because of the very competitive culture I was raised in. Now I think it’s not really restricted to a culture or country. And one should just practice self-appreciation.

0

0

3

@faeze_brh

Faeze Brahman

5 months

@wzhao_nlp @alsuhr @xiang_lorraine Congrats Wenting 😊🎊

0

0

2

@faeze_brh

Faeze Brahman

3 years

@DESpevak @BackHomeBeer Cool, thanks for sharing! Sounds interesting!

2

0

2

@faeze_brh

Faeze Brahman

3 years

@yufanghou @ReviewAcl I didn’t even sign up to review for the month of November and yet got 5. Can someone please let me know how should we opt out/in per month basis?

1

0

3

@faeze_brh

Faeze Brahman

6 months

The work is led by @GXiming who unfortunately could not attend due to Visa issues!

0

0

3

@faeze_brh

Faeze Brahman

1 year

@mbodhisattwa @limufar 🙌🙃💯

1

0

3

@faeze_brh

Faeze Brahman

4 years

Really liked it!

@emnlp2020

emnlp2020

4 years

A big shoutout to @ConnectedPapers and @SemanticScholar , who ingested our papers ahead of anthology publication, built a graph for each of them, and built a custom version of their website for us in just 2 weeks!

Tweet media one

2

13

122

0

0

3

@faeze_brh

Faeze Brahman

2 years

Thank you so much everyone 😊

0

0

3

@faeze_brh

Faeze Brahman

3 years

If and only if I learn how to deal with people who only care about themselves! #BigLifeLesson

0

0

3

@faeze_brh

Faeze Brahman

1 year

@anmarasovic 😂

0

0

3

@faeze_brh

Faeze Brahman

2 years

@VeredShwartz @allen_ai @YejinChoinka @ai2_mosaic Thanks Vered for all the support 🤗

0

0

3

@faeze_brh

Faeze Brahman

2 years

@nouhadziri @allen_ai @YejinChoinka Welcome to the team! 😊

1

0

3

@faeze_brh

Faeze Brahman

4 months

@xiamengzhou Very interesting!

0

0

3

@faeze_brh

Faeze Brahman

3 years

@VeredShwartz @UBC_CS Congrats Vered 🤩 🎉 How lucky @UBC_CS and your students are!

0

0

3

@faeze_brh

Faeze Brahman

3 years

@rajammanabrolu @mark_riedl Looking forward to it!

0

0

3

@faeze_brh

Faeze Brahman

1 year

@limufar @mbodhisattwa @ucsd_cse @allen_ai @ai2_aristo 😅😅😅already missed San Diego?!

1

0

3

@faeze_brh

Faeze Brahman

3 years

@NAACLHLT Just to clarify in case it sounds weird! My parents have not seen my husband in person yet. 😃

0

0

3

@faeze_brh

Faeze Brahman

2 years

@swabhz @USCViterbi Thanks for your support Swabha! 🌸

0

0

3

@faeze_brh

Faeze Brahman

2 years

Just because it's middle East doesn't mean it's justified! #be_our_voice #OpIran

0

0

3

@faeze_brh

Faeze Brahman

3 years

@poooyak We are amazing! We are the best 😂

0

0

3

@faeze_brh

Faeze Brahman

2 years

@ai2_mosaic team at @allen_ai is recruiting research interns for summer 2023. Come work with us ! ⏱ Apply by Nov 13.

@ai2_mosaic

MOSAIC

2 years

📢📢 Looking for a Summer 2023 research internship? Apply to the Mosaic team @allen_ai !! 📢📢 topics include: commonsense, language generation, vision+language, RL, + more! Applications due Nov 13th!

1

43

165

0

1

3

@faeze_brh

Faeze Brahman

3 years

@rajammanabrolu Wanna buy your current feeling 😃

1

0

3

@faeze_brh

Faeze Brahman

3 years

@nasrinmmm @allen_ai @YejinChoinka Great great talk @nasrinmmm 👌🏻!

0

0

3