user avatar
Daniel Fried
@dan_fried
Assistant prof. @LTIatCMU @SCSatCMU. Working on NLP: LLM agents, language-to-code, applied pragmatics, grounding.
Pittsburgh, PA
dpfried.github.io
Joined August 2013
908
Following
4,076
Followers
Posts
  • user avatar
    Daniel Fried
    @dan_fried
    Apr 13, 2022
    I’m excited to release a paper (and model weights!) for InCoder: a generative code model that can infill as well as do left-to-right generation. Project page: sites.google.com/view/incoder-c… Demo: huggingface.co/spaces/faceboo… Paper: github.com/dpfried/incode… Thread (1/n):
    GIF
  • user avatar
    Daniel Fried
    @dan_fried
    Jun 3, 2021
    Thrilled to be starting as an assistant professor at Carnegie Mellon's LTI @LTIatCMU @SCSatCMU in Fall 2022! In the meantime I'll be a visiting researcher at FAIR Seattle starting August 2021. I'm grateful to many mentors, collaborators, and friends for support over the years!
  • user avatar
    Daniel Fried
    @dan_fried
    Oct 25, 2021
    I'm recruiting grad students starting Fall '22! Particular areas of interest: language grounding, interaction, pragmatics, and multi-agent NLP. Want to help people do things with words and computers? Apply to CMU SCS by December 9!
    cs.cmu.edu
    SCS Graduate Admissions
  • user avatar
    Daniel Fried
    @dan_fried
    May 23, 2023
    New(ish) preprint: a survey and position paper on the role of *pragmatics* in grounded NLP. People use language in context to achieve goals, and to interact more successfully and efficiently with people, our NLP models should too. Preprint: arxiv.org/abs/2211.08371 (1/)
    24K
  • user avatar
    Daniel Fried
    @dan_fried
    Jul 3, 2024
    I'm excited to be working on agents at @Meta, along with continuing my work at CMU!
    user avatar
    Russ Salakhutdinov
    @rsalakhu
    Jul 3, 2024
    I am very excited to start working with GenAI team at @Meta, focusing on multimodal LLM agents, joining together with my amazing CMU colleagues Jing Yu Koh @kohjingyu and Daniel Fried @dan_fried!
    25K
  • user avatar
    Daniel Fried
    @dan_fried
    Sep 14, 2021
    We built a pragmatic, grounded dialogue system that improves pretty substantially in interactions with people in a challenging grounded coordination game. Real system example below! Work with Justin Chiu and Dan Klein, upcoming at #EMNLP2021. Paper: arxiv.org/abs/2109.05042
  • user avatar
    Daniel Fried
    @dan_fried
    Apr 5, 2019
    Neural text generation systems sometimes drop content or are underinformative, but can be improved by pragmatic inference methods. #naacl2019 paper by Sheng Shen, me, @jacobandreas and Dan Klein: arxiv.org/abs/1904.01301. Helps for summarization (CNN/Daily Mail) and the E2E task!
  • user avatar
    Daniel Fried
    @dan_fried
    May 13, 2020
    Upcoming at #acl2020nlp: identifying action segments ("pour milk") in videos of high-level tasks ("make a latte"), with weak supervision: arxiv.org/abs/2005.03684. Work with JB Alayrac, Phil Blunsom, @redpony, Stephen Clark, and @aidanematzadeh. (1/4)
  • user avatar
    Daniel Fried
    @dan_fried
    Apr 18, 2022
    I’m very excited about this work on interactively grounding language to rewards (preferences), via pragmatic reasoning and inverse RL. Reward learning can help NLP systems do what people want even in settings the people haven’t yet described (or seen!)
    user avatar
    Jessy Lin
    @realJessyLin
    Apr 18, 2022
    How can agents infer what people want from what they say? In our new paper at #acl2022nlp w/ @dan_fried, Dan Klein, and @ancadianadragan, we learn preferences from language by reasoning about how people communicate in context. Paper: arxiv.org/abs/2204.02515 [1/n]
  • user avatar
    Daniel Fried
    @dan_fried
    Aug 7, 2024
    We built a benchmark to test whether LLMs can optimize Python code (in runtime and memory) through algorithmic rewrites while ensuring the semantics stay correct. I'm excited about the task -- there's a lot of headroom here!
    user avatar
    Vishruth Veerendranath
    @viishruth
    Aug 6, 2024
    Can current code LMs generate sufficiently efficient programs? 🤔 More importantly, Can these LMs improve code efficiency without sacrificing correctness? Check out ECCO, our code-gen benchmark for correctness-preserving program optimizations! 🧵 1/n
    5.7K
  • user avatar
    Daniel Fried
    @dan_fried
    Apr 8, 2022
    Call for papers --- we'd love to see your work on implicit / underspecified language at the UnImplicit workshop @ NAACL 2022! Apr 14th (extended deadline): papers that haven't yet been reviewed Apr 21st: papers that already have ARR reviews
    user avatar
    Valentina Pyatkin
    @valentina__py
    Mar 17, 2022
    If you are interested in implicit and underspecified language consider submitting to the UnImplicit workshop #NAACL2022! With @meanwhileina, @complingy and Judith Degen as invited speakers. Info: unimplicit2022.github.io
  • user avatar
    Daniel Fried
    @dan_fried
    Jan 2, 2024
    Send us your papers on LLM agents, and join us at ICLR!
    user avatar
    L
    @LLMAgents
    Jan 2, 2024
    📣 CALL FOR PAPERS 📣 Join us at the #ICLR2024 Workshop on LLM Agents! @iclr_conf 🙋‍♂️We welcome both research papers and demos with technical reports. For more details, visit: llmagents.github.io #LLM #LLMAgents
    7.8K
  • user avatar
    Daniel Fried
    @dan_fried
    May 4, 2023
    Very excited that these models are released! In our evals, these are currently the strongest open-access (weights released) code models, and I'm looking forward to using them in research. Models, demos, paper, VSCode extension, and more: huggingface.co/bigcode
    user avatar
    BigCode
    @BigCodeProject
    May 4, 2023
    Introducing: 💫StarCoder StarCoder is a 15B LLM for code with 8k context and trained only on permissive data in 80+ programming languages. It can be prompted to reach 40% pass@1 on HumanEval and act as a Tech Assistant. Try it here: shorturl.at/cYZ06r Release thread🧵
    6.5K
  • user avatar
    Daniel Fried
    @dan_fried
    Jan 25, 2024
    We're excited to release VisualWebArena, with > 900 challenging, visually-grounded examples to evaluate multimodal web agents. jykoh.com/vwa Has self-contained web environments, and execution-based evaluation! And headroom: GPT-4V gets 16% success; people get 89%.
    user avatar
    Jing Yu Koh
    @kohjingyu
    Jan 25, 2024
    Computer interfaces are inherently visual. To build general autonomous agents, we will need strong vision language models. To assess the performance of multimodal agents, we introduce VisualWebArena (VWA): a benchmark for evaluating multimodal web agents on realistic visually
    5.4K