Search Results for author:
Found 11 papers, 6 papers with code
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts.
GPT-4 Technical Report
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.
Ranked #1 on
Legal Reasoning
on LegalBench (Rule-recall)
A Holistic Approach to Undesired Content Detection in the Real World
We present a holistic approach to building a robust and useful natural language classification system for real-world content moderation.
Exploration in Deep Reinforcement Learning: A Survey
This paper reviews exploration techniques in deep reinforcement learning.
Text and Code Embeddings by Contrastive Pre-Training
Similarly to text embeddings, we train code embedding models on (text, code) pairs, obtaining a 20. 8% relative improvement over prior best work on code search.
Ranked #1 on
Passage Ranking
on MS MARCO
Asymmetric self-play for automatic goal discovery in robotic manipulation
We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects.
Automatic Curriculum Learning For Deep RL: A Short Survey
Automatic Curriculum Learning (ACL) has become a cornerstone of recent successes in Deep Reinforcement Learning (DRL). These methods shape the learning trajectories of agents by challenging them with tasks adapted to their capacities.
Solving Rubik's Cube with a Robot Hand
We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot.
ORRB -- OpenAI Remote Rendering Backend
We present the OpenAI Remote Rendering Backend (ORRB), a system that allows fast and customizable rendering of robotics environments.
From GAN to WGAN
This paper explains the math behind a generative adversarial network (GAN) model and why it is hard to be trained.
Learning Dexterous In-Hand Manipulation
We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand.
