deep dive

In healthcare settings where patients use LLMs as a medical assistant, LLM performance differs between evaluation and deployment. (a) Bean et al. (2025) find a 61 percentage point difference between evaluation and deployment. (b) We argue this gap arises not from poorly designed benchmarks, but from implicit assumptions embedded in evaluation protocols that fail to […]

Task construction as the control surface in continued pretraining. A construction rule maps each unlabeled example into a self-supervised prediction problem , such as one-hot next-token prediction in language modeling or paired views and targets in DINO-style vision SSL. Standard continued pretraining fixes this rule before training, whereas V-pretraining replaces it with a feedback-trained designer

.apr-fig { text-align: center; margin: 1.35em 0; line-height: 1.4; } .apr-fig–wide img { display: inline-block; width: 100%; max-width: 100%; height: auto; vertical-align: middle; } .apr-fig–wide-0-8 { max-width: 80%; margin-left: auto; margin-right: auto; } .apr-fig–tall img { display: inline-block; max-height: 300px; width: auto; max-width: 100%; height: auto; object-fit: contain; vertical-align: middle; } .apr-fig–tall-1-2x img { display:

By Stephan Xie, Ben Cohen, Mononito Goswami, Junhong Shen, Emaad Khwaja, Chenghao Liu, David Asker, Othmane Abou-Amal, Ameet Talwalkar More than a trillion dollars are lost every year due to system failures. To resolve them, engineers must troubleshoot outages quickly. An important task in incident response involves analyzing observability metrics, or time series data that

By Michael Psenka, Mike Rabbat, Aditi Krishnapriyan, Yann LeCun, Amir Bar 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