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 343 followers
Latest posts
Last updated 30 days ago
RL without TD learning
about 1 month ago
In this post, I’ll introduce a reinforcement learning (RL) algorithm based on...
What exactly does word2vec learn?
3 months ago
What exactly does word2vec learn, and how? Answering this question amounts to...
Whole-Body Conditioned Egocentric Video Prediction
5 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)
8 months ago
Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. However,...
Repurposing Protein Folding Models for Generation with Latent Diffusion
8 months 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
9 months ago
Training Diffusion Models with Reinforcement Learning We deployed 100 reinforcement learning (RL)-controlled...
Virtual Personas for Language Models via an Anthology of Backstories
about 1 year ago
We introduce Anthology, a method for conditioning LLMs to representative, consistent, and...
Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination
about 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...
Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!
over 1 year ago
Humans excel at processing vast arrays of visual information, a skill that...
TinyAgent: Function Calling at the Edge
over 1 year ago
The ability of LLMs to execute commands through plain language (e.g. English)...
Modeling Extremely Large Images with xT
over 1 year ago
As computer vision researchers, we believe that every pixel can tell a...