Aviral Kumar
Aviral Kumar is an Assistant Professor in the Computer Science Department and Machine Learning Department at Carnegie Mellon University, where he leads the CMU AI & Reinforcement Learning (AIRe) Lab. He completed his PhD at UC Berkeley in 2023, where he received the CV Ramamoorthy Distinguished Research Award, an Apple PhD Fellowship, and a Facebook PhD Fellowship. His research focuses on reinforcement learning and decision-making, with emphasis on offline reinforcement learning, scaling RL methods, and the intersection of reinforcement learning with foundation models. He is also a courtesy faculty member at CMU's Robotics Institute and has affiliations with Google DeepMind.
“The paper's core contribution is demonstrating that a VLM can be trained to produce free-form natural language reasoning before issuing high-level instructions to a frozen low-level robot policy”
Source→“The work is supported by ONR, Schmidt Sciences AI2050 Early Career Fellowship, and a TRI U3.0 project”
Source→“Aviral Kumar... Recipient of Schmidt Sciences AI2050 Early Career Fellowship. Has prior work on test-time compute optimization for LLMs”
Source→“Aviral Kumar - Lab/Institution: Carnegie Mellon University (CMU AIRe Lab) - Co-senior author with equal advising”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.