Jason Weston

RESEARCH SCIENTIST | NEW YORK CITY, UNITED STATES

Jason is a Research Scientist at Facebook, NY and a Visiting Research Professor at NYU. He earned his Ph.D. in machine learning at Royal Holloway, University of London and at AT&T Research in Red Bank, NJ. Previously, he was a researcher at Biowulf Technologies, a research scientist at the Max Planck Institute for Biological Cybernetics, Tuebingen, Germany, a research staff member at NEC Labs America, Princeton, and a research scientist at Google, NY. His interests lie in statistical machine learning, with a focus on reasoning, memory, perception, interaction, and communication. Jason has published over 100 papers, including Best Paper awards at ICML and ECML, and received a Test of Time Award for his work, "A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning," (with Ronan Collobert). He was part of the YouTube team that won a National Academy of Television Arts & Sciences Emmy Award for Technology and Engineering for Personalized Recommendation Engines for Video Discovery. Jason was also listed as the 16th most influential machine learning scholar at AMiner and one of the top 50 authors in Computer Science in Science.

Jason's Work

Jason's Publications

December 12, 2024

NLP

Byte Latent Transformer: Patches Scale Better Than Tokens

Artidoro Pagnoni, Ram Pasunuru, Pedro Rodriguez, John Nguyen, Benjamin Muller, Margaret Li, Chunting Zhou, Lili Yu, Jason Weston, Luke Zettlemoyer, Gargi Ghosh, Mike Lewis, Ari Holtzman, Srini Iyer

December 12, 2024

November 19, 2024

NLP

Adaptive Decoding via Latent Preference Optimization

Shehzaad Dhuliawala, Ilia Kulikov, Ping Yu, Asli Celikyilmaz, Jason Weston, Sainbayar Sukhbaatar, Jack Lanchantin

November 19, 2024

July 23, 2024

NLP

Reverse Training to Nurse the Reversal Curse

Olga Golovneva, Zeyuan Allen-Zhu, Jason Weston, Sainbayar Sukhbaatar

July 23, 2024

August 06, 2023

CONVERSATIONAL AI

REINFORCEMENT LEARNING

The Cringe Loss: Learning what language not to model

Leo Adolphs, Tianyu Gao, Jing Xu, Kurt Shuster, Sainbayar Sukhbaatar, Jason Weston

August 06, 2023

December 29, 2022

NLP

Staircase Attention for Recurrent Processing of Sequences

Dexter Ju, Jason Weston, Sainbayar Sukhbaatar, Stephen Roller

December 29, 2022

June 29, 2020

RESEARCH

NLP

Adversarial NLI: A New Benchmark for Natural Language Understanding

Douwe Kiela, Adina Williams, Emily Dinan, Jason Weston, Mohit Bansal, Yixin Nie

June 29, 2020

April 29, 2020

RESEARCH

Image-Chat: Engaging Grounded Conversations

Kurt Shuster, Antoine Bordes, Jason Weston, Samuel Humeau

April 29, 2020

April 28, 2020

RESEARCH

NLP

The Dialogue Dodecathlon: Open-Domain Knowledge and Image Grounded Conversational Agents

Jason Weston, Dexter Ju, Emily Dinan, Kurt Shuster, Stephen Roller, Y-Lan Boureau

April 28, 2020

April 17, 2020

RESEARCH

NLP

Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills

Eric Smith, Jason Weston, Kurt Shuster, Mary Williamson, Y-Lan Boureau

April 17, 2020

March 26, 2020

RESEARCH

NLP

Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring

Kurt Shuster, Jason Weston, Marie-Anne Lachaux, Samuel Humeau

March 26, 2020

December 12, 2019

GRAPHICS

The Second Conversational Intelligence Challenge (ConvAI2)

Emily Dinan, Alexander Miller, Arthur Szlam, Douwe Kiela, Jack Urbanek, Jason Weston, Joelle Pineau, Kurt Shuster, Ryan Lowe, Alan W Black , Alexander Rudnicky, Iulian Servan , Jason Williams, Mikhail Burtsev, Shrimai Prabhumoye, Valentin Malykh, Varvara Logacheva, Yoshua Bengio

December 12, 2019

November 04, 2019

Finding Generalizable Evidence by Learning to Convince Q&A Models

Douwe Kiela, Jason Weston, Kyunghyun Cho, Rob Fergus, Siddharth Karamcheti, Ethan Perez

November 04, 2019

November 02, 2019

RESEARCH

SPEECH & AUDIO

Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack

Emily Dinan, Jason Weston, Samuel Humeau, Bharath Chintagunta

November 02, 2019

October 25, 2019

RESEARCH

NLP

Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue

Anusha Balakrishnan, Jason Weston, Pararth Shah, Paul Crook, Y-Lan Boureau, Dongyeop Kang

October 25, 2019

July 27, 2019

CONVERSATIONAL AI

RESEARCH

Learning from Dialogue after Deployment: Feed Yourself, Chatbot!

Pierre-Emmanuel Mazaré, Antoine Bordes, Jason Weston, Braden Hancock

July 27, 2019

May 29, 2019

CONVERSATIONAL AI

RESEARCH

What makes a good conversation? How controllable attributes affect human judgments

Douwe Kiela, Abi See, Jason Weston, Stephen Roller

May 29, 2019

November 02, 2018

RESEARCH

NLP

Jump to better conclusions: SCAN both left and right

Douwe Kiela, Jason Weston, Kyunghyun Cho, Marco Baroni, Joost Bastings

November 02, 2018

July 15, 2018

RESEARCH

NLP

Personalizing Dialogue Agents: I have a dog, do you have pets too?

Jason Weston, Arthur Szlam, Douwe Kiela, Emily Dinan, Jack Urbanek, Saizheng Zhang

July 15, 2018