Asli Celikyilmaz (@real

Asli Celikyilmaz

713 posts

Asli Celikyilmaz

@real_asli

Sr. Director of Research @ms_aifrontiers @MSFTResearch & Affl Faculty @uwcse | IEEE Fellow | TACL editor-in-chief | Prev: FAIR @MetaAI @MSFTResearch @UCBerkeley

Washington, USA

Joined December 2012

Pinned
Asli Celikyilmaz
@real_asli
Jan 14
Excited to speak at the Lifelong Agents: Learning, Aligning, Memory, Evolving Workshop at #ICLR2026 in Rio alongside awesome speakers! Submit papers by Feb 15! Huge thanks to the organizers.
Emre Can Acikgoz
@emrecanacikgoz
Jan 6
📣 Happy to announce our "Lifelong Agents: Learning, Aligning, Evolving Workshop" at ICLR 2026 (@iclr_conf)! We are organizing a workshop on "lifelong agents" that can continuously learn, adapt, and evolve — excited to see what our community will build for next generation
3.5K
Asli Celikyilmaz
@real_asli
Sep 23, 2024
🚀💡We're hiring interns for 2025 at FAIR @ @AIatMeta Work on cutting-edge projects: social reasoning, alignment, interaction, multi-agent communication & more with text/multimodal LLMs. Apply now! 🔗metacareers.com/jobs/119904986…
42K
Asli Celikyilmaz
@real_asli
Sep 27, 2024
We are looking for Research Engineers to join our Fundamental AI Research (FAIR) Team and focus on LLMs reasoning, alignment, memory and specifically advance communication, interaction and social reasoning. Please apply now! metacareers.com/jobs/763579312…
35K
Asli Celikyilmaz
@real_asli
Jul 17, 2024
We have a postdoc and a research engineer position at FAIR to work on LLM+reasoning/alignment with specific focus on social reasoning, metacognition, interaction and others. Please reach out directly to me if you are interested.
40K
Asli Celikyilmaz
@real_asli
Apr 22, 2024
Our team in FAIR (at Meta) is hiring researchers (RS & PostDoc) to work on the broad topics of text and multimodal LLMs. Location: NY, Seattle or Menlo Park for RS, and Seattle for PostDocs. PostDoc: metacareers.com/jobs/968496244… Research Scientist, AI (PhD): metacareers.com/jobs/752169417…
19K
Asli Celikyilmaz
@real_asli
Apr 26, 2019
Just got some really good news! I am now an Affiliate Associate Professor at the Paul G. Allen School of Computer Science & Engineering at University of Washington @uwcse. Thank you @YejinChoinka and @nlpnoah , i really appreciate your support!
Asli Celikyilmaz
@real_asli
Feb 16, 2023
We surveyed works where LMs are augmented with better reasoning and tools: Exploring integration of reasoning and tool-based augmentation in a fully self-supervised manner can lead to more advanced systems for human-machine interaction.
AK
@_akhaliq
Feb 16, 2023
Augmented Language Models: a Survey abs: arxiv.org/abs/2302.07842
20K
Asli Celikyilmaz
@real_asli
Dec 13, 2024
Our new work: 🚨 Explore Theory-of-Mind: Program-Guided Adversarial Data Generation for Theory of Mind Reasoning 🚨 -- New framework for generating diverse & challenging ToM data -- A*-powered algorithm creates complex story structures & novel scenarios
ai.meta.com
Sharing new research, models, and datasets from Meta FAIR
Meta FAIR is releasing new research artifacts that highlight our recent innovations in developing agents, robustness and safety, and architectures that facilitate machine learning.
9.9K
Asli Celikyilmaz
@real_asli
May 28, 2024
Excited to share our new resource, 'An Introduction to Vision-Language Modeling'! 📘 Dive into the mechanics of VLMs, from mapping images to language to extending to videos. A collaborative effort to boost understanding and innovation in this promising field. 🚀
AI at Meta
@AIatMeta
May 28, 2024
📝 New from FAIR: An Introduction to Vision-Language Modeling. Vision-language models (VLMs) are an area of research that holds a lot of potential to change our interactions with technology, however there are many challenges in building these types of models. Together with a set
10K
Asli Celikyilmaz
@real_asli
Jun 18, 2019
Our paper has just received Best Student Paper award at #CVPR2019. Another fabulous MSR intern work! Congratulations @xwang_lk Qiuyuan Huang @JianfengGao0217 Lei Zhang @shendinghan . Read the blog post microsoft.com/en-us/research… for details! @MSFTResearch
Microsoft Research
@MSFTResearch
Jun 18, 2019
Natural language is tied to how humans interact with their environment. Can we build intelligent agents that can learn to communicate in different modalities as do humans? Microsoft researchers are using Vision-Language Navigation to find out: aka.ms/AA5d4zw #CVPR2019
microsoft.com
Visually grounded natural language navigation is going places
Overall, there are two central questions facing current Vision Language Navigation models. Firstly, should we backtrack? And if so, where should we backtrack to? And secondly, when do we terminate a...
Asli Celikyilmaz
@real_asli
Dec 16, 2022
Our new work on evaluating step-by-step reasoning of LMs is on arxiv. This was really hard! So we introduce a suite of metrics that can score LM’s reasoning in an unsupervised way (reference free) with @OlgaNLP, @moyapchen, @spencerpoff, @LukeZettlemoyer, @CMacota99, Maryam F.
AI at Meta
@AIatMeta
Dec 16, 2022
ROSCOE is a first-of-its-kind suite of metrics for scoring step-by-step reasoning. By publishing this study we hope to provide a foundation that enables scalable systematic evaluation and benchmarking of new language models. See the paper on arXiv ⬇️ arxiv.org/abs/2212.07919
7.3K
Asli Celikyilmaz
@real_asli
Jul 14, 2020
We have a paper @icmlconf on Transformers for Reinforcement Learning! Talk to us live on Tuesday: icml.cc/virtual/2020/p… arxiv.org/abs/1911.07141…
Asli Celikyilmaz
@real_asli
May 14, 2019
🎉4 / 4 papers accepted at @ACL2019_Italy ! Thank you incredible @ABosselut , @shendinghan , @eaclark07 and collaborators @JianfengGao0217, Yizhe Zhang from @MSFTResearch , and @YejinChoinka , @nlpnoah from @uwnlp , @ai2_allennlp . Details to follow!
Asli Celikyilmaz
@real_asli
Nov 15, 2024
🚀 Our new work on Improving text generation! Adaptive decoding optimizes creativity & factuality via Latent Preference Optimization.
Jason Weston
@jaseweston
Nov 15, 2024
🚨 Adaptive Decoding via Latent Preference Optimization 🚨 - New layer added to Transformer, selects decoding params automatically *per token* - Learnt via new method, Latent Preference Optimization - Outperforms any fixed temperature decoding method, choosing creativity or
4.7K