We introduce PiCSAR (Probabilistic Confidence Selection And Ranking)💡: A simple training-free method for scoring samples based on probabilistic confidence, selecting a reasoning chain with the highest confidence from multiple sampled responses.
✏️PiCSAR is generalisable across…
🚀 Excited to see our work on PiCSAR out!
Thrilled to have Joshua as a co-author — and even more thrilled that he’ll be joining my group this academic year. Big things ahead!
🚀 Excited to see our work on PiCSAR out!
Thrilled to have Joshua as a co-author — and even more thrilled that he’ll be joining my group this academic year. Big things ahead!
Building on what @lmthang shared, here's another fun fact from our final push: we finalized the model checkpoint selection just 5 hours before the IMO problems were released! It's incredible to see the model we were babysitting over that final weekend now demonstrating…
Building on what @lmthang shared, here's another fun fact from our final push: we finalized the model checkpoint selection just 5 hours before the IMO problems were released! It's incredible to see the model we were babysitting over that final weekend now demonstrating…
Our paper "Do Large Language Models Perform Latent Multi-Hop Reasoning without exploiting shortcuts?" will be presented at #ACL2025 today.
📍 Mon 18:00-19:30 Findings Posters (Hall X4 X5)
Please visit our poster if you are interested! ✨
Our paper "Do Large Language Models Perform Latent Multi-Hop Reasoning without exploiting shortcuts?" will be presented at #ACL2025 today.
📍 Mon 18:00-19:30 Findings Posters (Hall X4 X5)
Please visit our poster if you are interested! ✨
Notable mention -- Joshua Ong (@joshuaongg21), main author of "Theorem Prover as a Judge for Synthetic Data Generation" (arxiv.org/abs/2502.13137), just finished his BSc in Maths at Edinburgh, and he is now starting a PhD with @e_giunchiglia at Imperial! Keep him on your radar 🚀
Notable mention -- Joshua Ong (@joshuaongg21), main author of "Theorem Prover as a Judge for Synthetic Data Generation" (arxiv.org/abs/2502.13137), just finished his BSc in Maths at Edinburgh, and he is now starting a PhD with @e_giunchiglia at Imperial! Keep him on your radar 🚀
Slides for my lecture “LLM Reasoning” at Stanford CS 25: dennyzhou.github.io/LLM-Reasoning-…
Key points:
1. Reasoning in LLMs simply means generating a sequence of intermediate tokens before producing the final answer. Whether this resembles human reasoning is irrelevant. The crucial…
Lovely to see the impressive performance of the Seed Prover developed by the ByteDance Seed team at IMO 2025 — achieving a silver-level score (30 out of 42) within three days, and reaching (35 out of 42) with extended compute time. leanprover.zulipchat.com/#narrow/channe…
148 Followers 3K FollowingEconomist, Emerging Markets and Central Bank observer. Likes a good chart. Dislikes the limelight. "I never learned anything while I was talking."
83K Followers 8K FollowingCompiling in real-time, the race towards AGI.
🗞️ Don't miss my daily top 1% AI analysis newsletter directly to your inbox 👉 https://t.co/6LBxO8215l
2K Followers 914 FollowingHiring: resume to [email protected]
to love math is to see the face of God
Morgan Prize, Rhodes Scholar
Math PhD@Stanford; Neuro@Oxford; Math+Physics@MIT
112 Followers 5K FollowingGuiding @Elonmusk’s vision for a better future through SpaceX, Tesla, Neuralink and more 🚀 I teach enthusiasts, dream chaser and innovation advocate 🌟
110 Followers 3K FollowingPart of the innovation journey with @elonmusk I Pushing the boundaries of technology and exploring the cosmos | Committed to a sustainable future 🌿
817 Followers 518 FollowingAssistant Professor at Imperial College London | EEE Department and I-X.
Previously: Post-doc at TU Wien, DPhil student at the University of Oxford.
83K Followers 8K FollowingCompiling in real-time, the race towards AGI.
🗞️ Don't miss my daily top 1% AI analysis newsletter directly to your inbox 👉 https://t.co/6LBxO8215l
2K Followers 266 FollowingResearcher in #MachineLearning and #NLProc, working on representation learning and language. Lecturer at @imperialcollege, visiting researcher at @Cambridge_Uni
9K Followers 865 Followingmts @ openai |
cs phd @ 🌁 uc berkeley |
building @vllm_project |
machine learning system |
the real agi is the friends we made along the way
637K Followers 35 FollowingWe're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant @claudeai on https://t.co/FhDI3KQh0n.
763 Followers 86 FollowingMegagon Labs advances state-of-the-art research in AI and builds technologies that impact the world through online services. #NLP #AI #ML #NLP4HR #LLM #RAG
817 Followers 518 FollowingAssistant Professor at Imperial College London | EEE Department and I-X.
Previously: Post-doc at TU Wien, DPhil student at the University of Oxford.
8K Followers 198 FollowingAssistant Prof at Stanford CS, member of @stanfordnlp and statsml groups; Formerly at Microsoft / postdoc at Stanford CS / Stats.