π£ New paper!
We observe that reasoning language models finetuned only on English data are capable of zero-shot cross-lingual reasoning through a "quote-and-think" pattern.
However, this does not mean they reason the same way across all languages or in new domains.
[1/N]
09.05.2025 19:53 β π 11 π 3 π¬ 2 π 2
π’ Calling all SEA-passionate individuals!
SEACrowd is excited to launch our contributor call for SEA-VL Phase 2: Building Visual Language Models for Southeast Asia! π
After the success of Phase 1, we're now taking on a bigger mission (see thread)π
08.05.2025 09:41 β π 2 π 2 π¬ 1 π 1
SEA-VL: Building AI for Southeast Asian Research π
We release SEA-VL, the largest vision-language dataset tailored for SEAβs diverse culture.
π arXiv: arxiv.org/abs/2503.07920
π€ Data: huggingface.co/collections/...
Check the thread π§΅
13.03.2025 11:36 β π 4 π 3 π¬ 1 π 1
LMs need linguistics! New paper, with @futrell.bsky.social, on LMs and linguistics that conveys our excitement about what the present moment means for linguistics and what linguistics can do for LMs. Paper: arxiv.org/abs/2501.17047. π§΅below.
29.01.2025 16:07 β π 99 π 30 π¬ 3 π 2
π£ Calling #NeurIPS2024 participants!
While everyone enjoys the last day of the beautiful Vancouver ποΈπ¨π¦, consider join our initiative and contribute to building models with more inclusivity and diversity, and mitigating implicit and explicit bias.
βΌοΈCuz we are in the post-training era nowβΌοΈ
16.12.2024 02:25 β π 2 π 0 π¬ 0 π 0
Grassroots Science
A global initiative focused on developing state-of-the-art multilingual language models through grassroots efforts.
βοΈ We're going to launch Grassroots Science, a year-long ambitious, massive-scale, fully open-source initiative aimed at developing multilingual LLMs aligned to diverse and inclusive human preferences in Feb 2025.
π Check our website: grassroots.science.
#NLProc #GrassrootsScience
09.12.2024 05:02 β π 7 π 5 π¬ 1 π 3
First bsky post about tinlab at #EMNLP2024! A few highlights:
* Presentations from Aditya Yedetore and Hayley Ross on neural network generalizations!
* I'm giving a keynote at GenBench & organizing BlackboxNLP
* Ask me about our faculty hiring & PhD/postdoc positions at Boston University!
08.11.2024 16:59 β π 32 π 8 π¬ 1 π 0
NLP & ML research @cohereforai.bsky.social
Advancing Southeast Asian (SEA) NLP Research
https://seacrowd.github.io/
CS PhD student @ Brown | Multimodal Interpretability
Post-doc @ Harvard. PhD UMich. Spent time at FAIR and MSR. ML/NLP/Interpretability
The National Deep Inference Fabric, an NSF-funded computational infrastructure to enable research on large-scale Artificial Intelligence.
π NDIF: https://ndif.us
π§° NNsight API: https://nnsight.net
πΈ GitHub: https://github.com/ndif-team/nnsight
Postdoc at ETH. Formerly, PhD student at the University of Cambridge :)
Postdoc at the interpretable deep learning lab at Northeastern University, deep learning, LLMs, mechanistic interpretability
AI/ML Researcher | Assistant Professor at UT Austin | Postdoc at Princeton PLI | PhD, Machine Learning Department, CMU. Research goal: Building controllable machine intelligence that serves humanity safely. leqiliu.github.io
ELLIS PhD, University of TΓΌbingen | Data-centric Vision and Language @bethgelab.bsky.social
Website: adhirajghosh.github.io
Twitter: https://x.com/adhiraj_ghosh98
Director of ML and DE at the Wikimedia Foundation. We host Wikipedia.
PhD @ MBZUAI π¦πͺ β’ Multilingual + Low-resource NLP β’ Prev: Samsung Research, DLSU Manila π΅π β’ photographer and speed typist β’ he/him β’ blaisecruz.com
NLP/Machine Translation/NLG/Deep Learning
Researcher at NICT, Japan
Adjunct Faculty at IIT Madras
Visiting Professor at IIT Bombay
Ex Kyoto University
prajdabre.github.io
PhD @ltiatcmu.bsky.social
previously @eleutherai.bsky.social
π lintang.sutawika.com
Faculty @MBZUAI, visiting scientist @Google
PhD student at the University of Cambridge
https://ljvmiranda921.github.io
Research Scientist at Capital One. Organizing https://grassroots.science
AI, philosophy, spirituality
Head of interpretability research at EleutherAI, but posts are my own views, not Eleutherβs.
Computers can be understood!
https://blog.nelhage.com/
machine learning, science & society @anthropic.com | recently: Clio, Anthropic Economic Index, Claude Artifacts | prev: phd, stanford nlp. alextamkin.com