28th April, 2025 | Garnet 214-215 | Singapore EXPO | https://xitter.cf/t.co/aZHShVWnrI | ICLR 2025 @iclr_conf

Joined October 2024
Spurious Correlation & Shortcut Learning Workshop retweeted
How do we scale up the context of LLMs? Agentic search scales to arbitrarily large amounts of info, but can easily miss relevant info. Idea💡: Optimize organization of info for downstream utility. Leads to 30+% gains even on OOD domains Paper + code: librarian-agents.github.io/
LLMs deployed in specialized domains, from enterprise codebases to law firms, dig through a mountain of unstructured context! Our new paper, Librarian Agents, asks: can an agent adapt by curating its own long-context workspace, anticipating queries before they arrive? 🧵⬇️
16
36
2
308
21,969
Spurious Correlation & Shortcut Learning Workshop retweeted
🚨 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.
1
6
2
27
6,164
Spurious Correlation & Shortcut Learning Workshop retweeted
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:
3
19
5,764
Spurious Correlation & Shortcut Learning Workshop retweeted
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:
3
7
2
52
10,254
✨️📢 Best paper award: Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization 🎉👏 @MMondelli @simone_bombari
2
4
17
1,998
Spurious Correlation & Shortcut Learning Workshop retweeted
📢 Now live: Catastrophic overtraining of language models @AdtRaghunathan
🌟📢 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/sched… #ICLR2025
3
6
522
📢 Now live: Catastrophic overtraining of language models @AdtRaghunathan
🌟📢 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/sched… #ICLR2025
3
6
522
Spurious Correlation & Shortcut Learning Workshop retweeted
Looking forward to participating in the #ICLR2025 workshop and the panel. Great speakers!
💥 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
6
19
2,375
🌟📢 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/sched… #ICLR2025
7
1
26
2,519
Spurious Correlation & Shortcut Learning Workshop retweeted
💥 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
9
1
50
6,060
Spurious Correlation & Shortcut Learning Workshop retweeted
See you all at the ICLR SCSL workshop today in Garnet 214-215!
Heading to #ICLR2025 to present our SCSL workshop paper on understanding how last-layer retraining methods mitigate spurious correlations! openreview.net/pdf?id=B2W51a… Stop by on Monday, April 28 to chat and learn more 🙂
3
14
1,316
💥 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
9
1
50
6,060
Spurious Correlation & Shortcut Learning Workshop retweeted
🚨 Join us at the Workshop on Spurious Correlation & Shortcut Learning (SCSL) at #ICLR2025! @iclr_conf 🗓️ April 28, 2025 📍 Garnet 214-215, Singapore EXPO 🌐 More info: scslworkshop.github.io #ICLR2025
16
3
50
9,400
🚨 Join us at the Workshop on Spurious Correlation & Shortcut Learning (SCSL) at #ICLR2025! @iclr_conf 🗓️ April 28, 2025 📍 Garnet 214-215, Singapore EXPO 🌐 More info: scslworkshop.github.io #ICLR2025
16
3
50
9,400
Spurious Correlation & Shortcut Learning Workshop retweeted
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
1
2
13
677
Spurious Correlation & Shortcut Learning Workshop retweeted
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.
1
8
59
4,141
Spurious Correlation & Shortcut Learning Workshop retweeted
🚀 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:
1
5
13
1,251
🚀 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:
1
5
13
1,251