Nicholas Carlini: The security of LLMs

Yuandong Tian: Inside-out interpretability: training dynamics in multi-layer transformer

Language Models are "Modelling The World" [Nicholas Carlini]

Bill Dally - Trends in Deep Learning Hardware

ACTION AI Institute Distinguished Lecture by Nicholas Carlini

Why do LLMs struggle with Long Context? | Federico Barbero, Google DeepMind | BLISS e.V.

Krysta Svore - Why Quantum, Why Now: The Case for Better Qubits and Better Data

LLM и GPT - как работают большие языковые модели? Визуальное введение в трансформеры

Special: Defeating AI Defenses (with Nicholas Carlini and Nathan Labenz)

Scalable Extraction of Training Data from (Production) Language Models

Ece Kamar - Navigating the AI Horizon: Promises, Perils, and the Power of Collaboration

David Tse: Realizing Nakamoto’s Dream: One-Time Signatures, Garbled Circuits & Zero-Knowledge Proofs

David Bau: Interpretability and model editing

Dina Katabi - Beyond Wearables: The Rise of Invisible AI-Powered Health Tech!

Short-term Safety Matters Most — Nicholas Carlini

Adversarial Attacks on LLMs

Invariance and equivariance in brains and machines

What Can Theory Of Cryptography Tell Us About AI Safety

Tony Yen and Ronald Goossens - EUV: Lithography: History, Latest Results, Technology Roadmap

Николас Карлини – Некоторые уроки состязательного машинного обучения

Automating scientific discovery and hypothesis generation with language model agents