Everything you care about in one place
Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.
Get Feederbair.berkeley.edu
The Berkeley Artificial Intelligence Research Blog
Get the latest updates from The Berkeley Artificial Intelligence Research Blog directly as they happen.
Follow now 373 followers
Latest posts
Last updated 8 days ago
Gradient-based Planning for World Models at Longer Horizons
9 days ago
GRASP is a new gradient-based planner for learned dynamics (a “world model”)...
Identifying Interactions at Scale for LLMs
about 2 months ago
Understanding the behavior of complex machine learning systems, particularly Large Language Models...
Information-Driven Design of Imaging Systems
4 months ago
An encoder (optical system) maps objects to noiseless images, which noise corrupts...
RL without TD learning
6 months ago
In this post, I’ll introduce a reinforcement learning (RL) algorithm based on...
What exactly does word2vec learn?
8 months ago
What exactly does word2vec learn, and how? Answering this question amounts to...
Whole-Body Conditioned Egocentric Video Prediction
10 months ago
× Predicting Ego-centric Video from human Actions (PEVA). Given past video frames...
Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)
about 1 year ago
Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. However,...
Repurposing Protein Folding Models for Generation with Latent Diffusion
about 1 year ago
PLAID is a multimodal generative model that simultaneously generates protein 1D sequence...
Scaling Up Reinforcement Learning for Traffic Smoothing: A 100-AV Highway Deployment
about 1 year ago
Training Diffusion Models with Reinforcement Learning We deployed 100 reinforcement learning (RL)-controlled...
Virtual Personas for Language Models via an Anthology of Backstories
over 1 year ago
We introduce Anthology, a method for conditioning LLMs to representative, consistent, and...
Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination
over 1 year ago
Sample language model responses to different varieties of English and native speaker...
How to Evaluate Jailbreak Methods: A Case Study with the StrongREJECT Benchmark
over 1 year ago
When we began studying jailbreak evaluations, we found a fascinating paper claiming...