Picture

Jason Weston @jaseweston

Research @MetaAI+NYU. Pretrain+FT: NLP from Scratch (2011). Multilayer attention+position embed+LLM: MemNets (2015). Recent (2023+):Sys 2 Attn, Self-Rewarding.. jaseweston.com nyc Joined April 2008
  • Tweets
    246
  • Followers
    9K
  • Following
    568
  • Likes
    1K
Jason Weston retweeted
swarnaNLP Profile Picture

Swarnadeep Saha @swarnaNLP

a month ago

Branch-Solve-Merge will be presented at #NAACL2024 😀 There's growing interest in using LLM as evaluator. BSM improves its correctness+consistency via task decomposition -- generating granular eval criteria & merging them. @omerlevy_ @real_asli @mohitban47 @jaseweston @xl_nlp

jaseweston Profile Picture

Jason Weston @jaseweston

6 months ago

Branch-Solve-Merge will be presented at #NAACL2024 😀 There's growing interest in using LLM as evaluator. BSM improves its correctness+consistency via task decomposition -- generating granular eval criteria & merging them. @omerlevy_ @real_asli @mohitban47 @jaseweston @xl_nlp

Jason Weston retweeted
ylecun Profile Picture

Yann LeCun @ylecun

2 months ago

Training a transformer to help A* planning. From FAIR.

_akhaliq Profile Picture

AK @_akhaliq

2 months ago

Training a transformer to help A* planning. From FAIR.

Jason Weston retweeted
robertarail Profile Picture

Roberta Raileanu @robertarail

2 months ago

🚨 Introducing ToolVerifier, our new method for generalization to new tools. 🚀 ToolVerifier outperforms GPT-4 on some tasks despite being based on Llama-2 70b. 🤖 Key ideas: - fine-tune on synthetically generated data for tool use with reasoning traces - self-verification…

jaseweston Profile Picture

Jason Weston @jaseweston

2 months ago

🚨 Introducing ToolVerifier, our new method for generalization to new tools. 🚀 ToolVerifier outperforms GPT-4 on some tasks despite being based on Llama-2 70b. 🤖 Key ideas: - fine-tune on synthetically generated data for tool use with reasoning traces - self-verification…

jaseweston Profile Picture

Jason Weston @jaseweston

3 months ago

Our team in FAIR labs (at Meta) is hiring researchers (RE, RS & PostDoc)! DM if interested. We work on the topics of Reasoning, Alignment and Memory/architectures (RAM). Recent work: Self-Rewarding LMs: arxiv.org/abs/2401.10020 Pairwise Cringe Loss: arxiv.org/abs/2312.16682…

Trends for United States

#bucciovertimechallenge
1.800 posts
Cavs
24,2 B posts
Feds
30,3 B posts
FaZe
23 B posts
Joe Milton
3.764 posts
Houser
1.534 posts
Jordan Travis
12,5 B posts
#UFCVegas91
4.818 posts
Lu Dort
1.716 posts
Johnny Wilson
4.593 posts
Austin Hill
Malik Washington
5.125 posts
#KristiNoemIsAMonster
20 B posts
Leverkusen
108 B posts
Brenden Rice
4.952 posts
Niang
4.079 posts
#LetEmKnow
3.558 posts
Mudryk
18,5 B posts
Ryan Truex
1.369 posts
Mobley
2.695 posts

You might like

professor at UW, director at AI2, adventurer at heart
Yejin Choi
@YejinChoinka
19K Followers
Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJw
Jacob Andreas
@jacobandreas
14K Followers
Cofounder & Chief Scientist https://t.co/hLfvKLkFHd (@MistralAI). Working on LLMs. Ex @MetaAI | PhD @Sorbonne_Univ_ | MSc @CarnegieMellon | X11 @Polytechnique
Guillaume Lample
@GuillaumeLample
37K Followers
Open-Endedness Team Lead @GoogleDeepMind, Professor of AI @AI_UCL, PI @UCL_DARK, @ELLISforEurope Scholar. ex @MetaAI (FAIR), @CompSciOxford. Opinions my own.
Tim Rocktäschel
@_rockt
29K Followers
Associate Professor at Columbia, advancing the frontier of NLP. Forbes 30 under 30. Amazon Alexa Prize winner.
zhou Yu
@Zhou_Yu_AI
9K Followers
Researcher in NLP/ML @deepmind, @ucl_nlp, @riedelcastro@sigmoid.social on Mastodon
Sebastian Riedel (@ri..
@riedelcastro
15K Followers
I build tough benchmarks for LMs and then I get the LMs to solve them. Postdoc @Princeton. PhD from @nlpnoah @UW. Ex-visiting researcher @MetaAI & @MosaicML.
Ofir Press
@OfirPress
10K Followers
Luke Zettlemoyer
@LukeZettlemoyer
8K Followers
The NLP group at the University of Washington.
UW NLP
@uwnlp
11K Followers
nonbayesian parameterics, sweet lessons, and random birds. Friend of @srush_nlp
Colin Raffel
@colinraffel
30K Followers
PhD student at @uwcse @uwnlp
Sewon Min
@sewon__min
7K Followers
@ContextualAI CEO, @Stanford Adjunct Prof.
Douwe Kiela
@douwekiela
10K Followers
Llama3 pre-training lead. Partially to blame for things like the Cicero Diplomacy bot, BART, RoBERTa, kNN-LM, top-k sampling & Deal Or No Deal.
Mike Lewis
@ml_perception
6K Followers
Associate professor at @uw_cse; senior director at @allen_ai co-leading @allenNLP; AI/NLP researcher at @uw_nlp
Hanna Hajishirzi
@HannaHajishirzi
6K Followers
Researcher at Scaled Cognition. Formerly at Semantic Machines, @allenai (@ai2_allennlp, #nlphighlights).
Matt Gardner
@nlpmattg
9K Followers