The CDS Monthly Research Feature |
Humans instinctively map out the physical consequences of their actions before taking them, seamlessly predicting that a dropped glass will shatter or a jumped gap might be too wide. In new research, CDS PhD student Ying Wang and her colleagues applied a concept from human neuroscience to help AI systems plan their physical movements with similar intuitive efficiency. The paper, “Temporal Straightening for Latent Planning,” was co-authored by Wang, CDS founding director Yann LeCun, CDS Assistant Professor Mengye Ren, NYU postdoctoral researcher Oumayma Bounou, and colleagues, and has been accepted at ICML 2026.
|
|
|
Most AI agents follow the same rigid playbook no matter the task. ChatGPT’s Deep Research tool asks one round of clarifying questions before beginning a search, and coding assistants like SWE-agent start by reading through an existing codebase regardless of what’s actually being asked. A new paper from Courant PhD student Wenxuan Ding, CDS Faculty Fellow Nicholas Tomlin, and CDS Associate Professor of Computer Science and Data Science Greg Durrett showed that LLMs can reason about when to keep exploring and when to commit, but only when uncertainty estimation is separated from action selection. The paper, “Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents,” addressed a problem that surfaces whenever AI agents operate in environments with incomplete information.
|
Physical systems that look chaotic to the eye — water swirling down a drain, fluids mixing at a boundary, particles drifting in a stirred medium — are usually governed by just a handful of simple equations. Flatiron Institute Research Fellow Helen Qu and her collaborators — including CDS Research Scientist Michael McCabe, CDS Senior Research Scientist Shirley Ho, and CDS founding director and Professor Yann LeCun — have found that machine learning models trained to predict the future in an abstract “latent space,” rather than pixel by pixel, do a noticeably better job of recovering physical information from raw observations.
|
By 10 meters underwater, the red channel of visible light has essentially disappeared, leaving behind the blue-green tint familiar from any reef video. That physical fact — along with turbidity, glare, and the sheer scarcity of clean training footage — turned out to be the central technical obstacle for a team of CDS MS students who built a computer vision system to identify Caribbean reef fish in raw video shot by an underwater robot. The project came together through the CDS Capstone Project, a course in the final year of the MS program that pairs students with industry partners and research labs to apply data science to real-world problems.
|
Attention companies, nonprofits, and research labs! CDS invites project proposals for our Data Science MS students to work on during the Fall 2026 semester through our Capstone Project program. Selected from a highly competitive applicant pool, our students excel academically and have cutting-edge machine learning, NLP, and data analysis skills. Proposals are due August 2, 2026.
|
|
|
Copyright (C) 2026 Center for Data Science. All rights reserved.
|
|
|
|
