1k citations · 1.4k across the 12 of their papers we have counts for
13 papers
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38
AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known A…
Balancing Knowledge Delivery and Emotional Comfort in Healthcare Conversational Systems
Shang-Chi Tsai, Yun-Nung Chen
With the advancement of large language models, many dialogue systems are now capable of providing reasonable and informative responses to patients' medical conditions. However, whe…
Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation
Bowen Baker, Joost Huizinga, Leo Gao +6
Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned mo…
GPT-4o System Card
OpenAI, :, Aaron Hurst +416
GPT-4o is an autoregressive omni model that accepts as input any combination of text, audio, image, and video, and generates any combination of text, audio, and image outputs. It's…
Towards Artwork Explanation in Large-scale Vision Language Models
Kazuki Hayashi, Yusuke Sakai, Hidetaka Kamigaito +2
Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating capabilities in text generation and comprehension. However, it has not been clari…
GPT-4 Technical Report
OpenAI, Josh Achiam, Steven Adler +278
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-wor…
Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Greg Yang, Edward J. Hu, Igor Babuschkin +7
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovere…
Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft
Ingmar Kanitscheider, Joost Huizinga, David Farhi +9
An important challenge in reinforcement learning is training agents that can solve a wide variety of tasks. If tasks depend on each other (e.g. needing to learn to walk before lear…
Dota 2 with Large Scale Deep Reinforcement Learning
OpenAI, :, Christopher Berner +24
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game. The game of Dota 2 presents novel challenges for AI systems such as lo…
Precision decay rate calculations in quantum field theory
Anders Andreassen, David Farhi, William Frost +1
Tunneling in quantum field theory is worth understanding properly, not least because it controls the long term fate of our universe. There are however, a number of features of tunn…
A direct approach to quantum tunneling
Anders Andreassen, David Farhi, William Frost +1
The decay rates of quasistable states in quantum field theories are usually calculated using instanton methods. Standard derivations of these methods rely in a crucial way upon def…
Streamlining resummed QCD calculations using Monte Carlo integration
David Farhi, Ilya Feige, Marat Freytsis +1
Some of the most arduous and error-prone aspects of precision resummed calculations are related to the partonic hard process, having nothing to do with the resummation. In particul…
Quantifying the power of multiple event interpretations
Yang-Ting Chien, David Farhi, David Krohn +3
A number of methods have been proposed recently which exploit multiple highly-correlated interpretations of events, or of jets within an event. For example, Qjets reclusters a jet…