All articles from Berkeley AI Research aggregated on DeepTrendLab — AI news, research, and announcements in one place.
Berkeley AI Research
10 articles
🐻 Research
Berkeley AI Research
14 min read
GRASP is a new gradient-based planner for learned dynamics (a “world model”) that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity directly to the state iterates for exploration, and (3) reshaping gradients so actions get clean signals while we avoid brittle “state-input” gradients through high-dimensional vision models.…
🐻 Research
Berkeley AI Research
7 min read
Understanding the behavior of complex machine learning systems, particularly Large Language Models (LLMs), is a critical challenge in modern artificial intelligence. Interpretability research aims to make the decision-making process more…
🐻 Research
Berkeley AI Research
6 min read
An encoder (optical system) maps objects to noiseless images, which noise corrupts into measurements. Our information estimator uses only these noisy measurements and a noise model to quantify how well…
🐻 Research
Berkeley AI Research
9 min read
In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference…
🐻 Research
Berkeley AI Research
6 min read
What exactly does word2vec learn, and how? Answering this question amounts to understanding representation learning in a minimal yet interesting language modeling task. Despite the fact that word2vec is a…
🐻 Research
Berkeley AI Research
7 min read
× Predicting Ego-centric Video from human Actions (PEVA) . Given past video frames and an action specifying a desired change in 3D pose, PEVA predicts the next video frame. Our…
🐻 Research
Berkeley AI Research
4 min read
Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. However, as LLMs have improved, so have the attacks against them. Prompt injection attack is listed as the #1…
🐻 Research
Berkeley AI Research
6 min read
PLAID is a multimodal generative model that simultaneously generates protein 1D sequence and 3D structure, by learning the latent space of protein folding models. The awarding of the 2024 Nobel…
🐻 Research
Berkeley AI Research
9 min read
Training Diffusion Models with Reinforcement Learning We deployed 100 reinforcement learning (RL)-controlled cars into rush-hour highway traffic to smooth congestion and reduce fuel consumption for everyone. Our goal is to…
🐻 Research
Berkeley AI Research
5 min read
We introduce Anthology , a method for conditioning LLMs to representative, consistent, and diverse virtual personas by generating and utilizing naturalistic backstories with rich details of individual values and experience.…