Sanjeev Arora
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 5 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| LLM skills and meta-cognition: scaffolding for new forms of learning? | The Future of Language Models and Transformers 2025 | 2025-03-31 |
Shows that frontier models actually extract and name procedural skills and can compose them: GPT-4o reliably generates novel skill labels and composes up to… | ||
| LLM Metacognition: Understanding and leveraging "Thinking about Thinking" | Emerging Generalization Settings 2024 | 2024-09-09 |
Claim: contemporary LLMs exhibit metacognitive labels that let them name and cluster procedural skills and use those labels to improve other models. Evidence… | ||
| A Theoretical Approach to Semantic Coding and Hashing | Learning, Algorithm Design and Beyond Worst-Case Analysis | 2016-11-14 |
Proposes a log‑linear generative model where a latent discourse vector does a random walk on the sphere, words have vectors VW, and under spatial isotropy the… | ||
| Back to the Future: Going Beyond Worst Case Analysis | KARPfest80 | 2015-10-17 |
Argues that worst-case NP-hardness misses real instances and shows concrete alternatives: assumes separable (anchor) words in topic models, uses convex… | ||
| Adventures in Linear Algebra++ and Unsupervised Learning | Semidefinite Optimization, Approximation and Applications 2014 | 2014-09-24 |
Sanjeev Arora, Princeton University
Semidefinite Optimization, Approximation and Applications
http://simons.berkeley.edu/talks/sanjeev-arora-2014-09-22 | ||
| nothing matches | ||