🚨 New Preprint!
Large reasoning models rely on long chain-of-thought generation to solve complex problems, but this comes at a substantial compute cost.
We introduce CoDE-Stop, a simple, training-free method that decides when to stop reasoning by tracking how model confidence evolves over time.
Cool suggestions and results from @AndrewLampinen on how semantic plausibility “shortcuts”/“spurious features” can effectively drive the more difficult learning of human language syntax!
Had fun talking at the @SCSLWorkshop at ICLR! One example I brought up, which I think provides an uncommon perspective: a case where spurious shortcuts can improve generalization... even to out-of-distribution sets where the spurious feature doesn't generalize! Thread:
Had fun talking at the @SCSLWorkshop at ICLR! One example I brought up, which I think provides an uncommon perspective: a case where spurious shortcuts can improve generalization... even to out-of-distribution sets where the spurious feature doesn't generalize! Thread:
✨️📢 Best paper award:
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization
🎉👏 @MMondelli@simone_bombari
🌟📢 Live from ICLR 2025! @iclr_conf
Our Workshop is underway at Singapore EXPO, Garnet 214-215, featuring presentations and rigorous discussions.
Exploring the foundations of robustness and generalization. 🔥
Full schedule here: scslworkshop.github.io/schedule/#ICLR2025
💥 See you tomorrow at the Workshop on Spurious Correlation & Shortcut Learning (SCSL) at #ICLR2025!
@iclr_conf
🗓️ April 28, 2025
📍 Garnet 214-215, Singapore EXPO
🌐 Schedule and More Info: scslworkshop.github.io#ICLR2025
🌟📢 Live from ICLR 2025! @iclr_conf
Our Workshop is underway at Singapore EXPO, Garnet 214-215, featuring presentations and rigorous discussions.
Exploring the foundations of robustness and generalization. 🔥
Full schedule here: scslworkshop.github.io/schedule/#ICLR2025
💥 See you tomorrow at the Workshop on Spurious Correlation & Shortcut Learning (SCSL) at #ICLR2025!
@iclr_conf
🗓️ April 28, 2025
📍 Garnet 214-215, Singapore EXPO
🌐 Schedule and More Info: scslworkshop.github.io#ICLR2025
Heading to #ICLR2025 to present our SCSL workshop paper on understanding how last-layer retraining methods mitigate spurious correlations! openreview.net/pdf?id=B2W51aq…
Stop by on Monday, April 28 to chat and learn more 🙂
Also @iclr_conf and it is going to be a busy week!
1. Today at 10am, Optimal Protocols for Continual Learning via Statistical Physics and Control Theory #342
2. Tomorrow at 10am, A Theory of Initialisation's Impact on Specialisation #342
3. Speaking at @SCSLWorkshop o Monday
Excited to head to ICLR this week! Feel free to reach out if you'll be there and would like to chat. I'll be giving a talk at the workshop on spurious correlations and shortcut learning, and we'll have some posters scattered across various other workshops.
🚀 SCSL Workshop at ICLR 2025 (Singapore, April 28) is seeking sponsors! Join us in tackling spurious correlations & shortcut learning with top researchers from NYU, UdeM, UCLA, UMD, SUT, and Google DeepMind. Support cutting-edge AI research & gain visibility!
🔗 Learn more:
4K Followers 7K FollowingMathematician (algebraic geometry, motives & friends, singularities in statistics and ML).
'Geometry is successful magic' (R. Thom)
University of Essen.
34K Followers 5K FollowingAssociate Professor CS/stats UC Berkeley. Former Research Scientist at Google DeepMind. ML/AI Researcher working on LLMs and deep learning. PhD at Stanford.
328 Followers 5K FollowingAGI Safety researcher (Independent), MARS Fellow(Cambridge AI Safety Hub), BASIS Fellow @UCBerkeley, Get Published or Die Trying.
12K Followers 2K FollowingInterested in cognition and artificial intelligence. MTS at @AnthropicAI. Previously @DeepMind, cognitive science @StanfordPsych. Tweets are mine.
82 Followers 2K FollowingRAGE-KG (RAG Enabled by Knowledge Graphs) is an established academic workshop targeting synergies between #KGs, #RAG and #LLMs, coming to #ISWC 2026 🇮🇹.
12K Followers 2K FollowingInterested in cognition and artificial intelligence. MTS at @AnthropicAI. Previously @DeepMind, cognitive science @StanfordPsych. Tweets are mine.
70 Followers 14 FollowingGeneralization beyond the training distribution in brains and machines Workshop at ICLR 2021. Organized by @drewlinsley, @cm_funke, @judy_borow, & Xavier Boix.
1.5M Followers 278 FollowingThe engine room of @Google. Building AI safely and responsibly to solve the world’s most complex problems. Join us: https://t.co/jUHQA27iBL
1.2M Followers 787 FollowingProfessor at NYU & Executive Chairman at AMI Labs.
Ex-Chief AI Scientist at Meta.
Researcher in AI, Machine Learning, Robotics, etc.
ACM Turing Award Laureate.