Excited to share this program #GStar for global talents by @newturing
. I personally designed the syllabus with our experienced team at NTI and leading AI experts. This would be an intensive 12-week program to train talents not only in state-of-the-art LLM but also in the research
@lmthang
-
GStar Program Trains Global Talents in State-of-the-Art LLM
By
–
-
DeepThink IMO Model Card and Team Announcement
By
–
Check out the model card and a list of all amazing folks from the DeepThink/IMO teams
-
How Much Models Think: The Key Simplification Axis
By
–
I can't share a lot at this point, but clearly how much we we allow the model to think is the main axis of the simplification.
-
IMO 2025 Gold Model Achieves SOTA on Reasoning Tasks
By
–
The IMO 2025 gold model achieved SOTA on many other reasoning tasks by large margins. I couldn't quite believe it when I first saw the results.
-
Deep Think Team Launches AI Product to Production Successfully
By
–
Special thank to the entire Deep Think team who has worked very hard to push this out to production! Amazing to see how far we have gotten from just a thought of having deep thoughts many months ago
-
Production-Ready AI Model Solves IMO Problems with Deep Think Mode
By
–
One very important distinction compared to all other IMO results out there is that our model is production ready, not experimental 🙂 This advanced model together powered by Deep Think mode is quite creative in problem solving. Check out this video of what a mathematician thinks… pic.twitter.com/QwA3aR0iNF
— Thang Luong (@lmthang) 1 août 2025One very important distinction compared to all other IMO results out there is that our model is production ready, not experimental This advanced model together powered by Deep Think mode is quite creative in problem solving. Check out this video of what a mathematician thinks
-
IMO Model Achieves SOTA on Reasoning Tasks Pre-Competition
By
–
Our IMO journey continues: the yolo run model that we trained a week before #imo2025, despite all possible likelihood of failures, magically achieves SOTA across a wide range of reasoning tasks from maths, to coding, and challenging knowledge. I'm very excited that we have now
-
Stanford NLP Researchers Honored with 25-Year Test-of-Time Award
By
–
I'm also proud to be a @stanfordnlp alumni 🙂 congrats to Gildea & @jurafsky on the well-deserved 25-year test-of-time award too!
-
Early LSTM Language Model Architecture Recognition from NLP Community
By
–
Special thanks to the NLP community for the recognition. This was my earliest work in "large" language model at the time , quoted from the paper "Our stacking LSTM models have 4 layers, each with 1000 cells, and 1000-dimensional embeddings" .
-
Test-of-Time Award Paper on Neural Networks Research
By
–
Link to our paper in 02015: https://
arxiv.org/abs/1508.04025. and slide deck of my test-of-time award talk here: https://
drive.google.com/file/d/15SeWBS
iRjQlOBwGz65dO2SuxL6N58Lro/view?usp=sharing
…