John Langford

Researcher, Microsoft

Joined

December 2017

Names

John Langford

Emails

****@hunch.net (Confirmed)

Personal Links

Career & Education History

Researcher

Microsoft (microsoft.com)

2012 – Present

Advisors, Relations & Conflicts

Coauthor

Alina Beygelzimer

2006 – 2006

Expertise

Logarithmic time prediction

,

memory

Present

Reinforcement learning

,

Active Learning

,

Online Learning

Present

Publications

Next-Latent Prediction Transformers Learn Compact World Models
Jayden Teoh, Manan Tomar, Kwangjun Ahn, Edward S. Hu, Pratyusha Sharma, Riashat Islam, Alex Lamb, John Langford
- PLAN-FM Bridge @ AAAI 2026
- Readers: Everyone
When does Predictive Inverse Dynamics Outperform Behavior Cloning? Exploring the Role of Action and State Uncertainty
Lukas Schäfer, Pallavi Choudhury, Abdelhak Lemkhenter, Chris Lovett, Somjit Nath, Luis França, Matheus Ribeiro Furtado de Mendonça, Alex Lamb, Riashat Islam, Siddhartha Sen, John Langford, Katja Hofmann, Sergio Valcarcel Macua
- Submitted to ICLR 2026
- Readers: Everyone
EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?
Aakriti Agrawal, Mucong Ding, Zora Che, Chenghao Deng, Anirudh Satheesh, John Langford, Furong Huang
- SafeGenAi Poster
- Readers: Everyone
EnsemW2S: Can an Ensemble of LLMs be Leveraged to Obtain a Stronger LLM?
Aakriti Agrawal, Mucong Ding, Zora Che, Chenghao Deng, Anirudh Satheesh, John Langford, Furong Huang
- Submitted to ICLR 2025
- Readers: Everyone
The Belief State Transformer
Edward S. Hu, Kwangjun Ahn, Qinghua Liu, Haoran Xu, Manan Tomar, Ada Langford, Dinesh Jayaraman, Alex Lamb, John Langford
- ICLR 2025 Poster
- Readers: Everyone
Towards Principled Representation Learning from Videos for Reinforcement Learning
Dipendra Misra, Akanksha Saran, Tengyang Xie, Alex Lamb, John Langford
- NeurIPS 2024 Workshop Open-World Agents Poster
- Readers: Everyone
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
Mucong Ding, Chenghao Deng, Jocelyn Choo, Zichu Wu, Aakriti Agrawal, Avi Schwarzschild, Tianyi Zhou, Tom Goldstein, John Langford, Anima Anandkumar, Furong Huang
- NeurIPS 2024 Track Datasets and Benchmarks Poster
- Readers: Everyone
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma, Hal Daumé III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Shankar Basu, Furong Huang
- ICML 2024 Poster
- Readers: Everyone
PcLast: Discovering Plannable Continuous Latent States
Anurag Koul, Shivakanth Sujit, Shaoru Chen, Ben Evans, Lili Wu, Byron Xu, Rajan Chari, Riashat Islam, Raihan Seraj, Yonathan Efroni, Lekan P Molu, Miroslav Dudík, John Langford, Alex Lamb
- ICML 2024 Poster
- Readers: Everyone
$\texttt{PREMIER-TACO}$ is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
Ruijie Zheng, Yongyuan Liang, Xiyao Wang, Shuang Ma, Hal Daumé III, Huazhe Xu, John Langford, Praveen Palanisamy, Kalyan Basu, Furong Huang
- FMDM@NeurIPS2023
- Readers: Everyone

View all 80 publications

Co-Authors

View all 130 co-authors