no code implementations • 2 Sep 2024 • Youngseog Chung, Dhruv Malik, Jeff Schneider, Yuanzhi Li, Aarti Singh
The traditional viewpoint on Sparse Mixture of Experts (MoE) models is that instead of training a single large expert, which is computationally expensive, we can train many small experts.
1 code implementation • 22 May 2024 • Sang Keun Choe, Hwijeen Ahn, Juhan Bae, Kewen Zhao, Minsoo Kang, Youngseog Chung, Adithya Pratapa, Willie Neiswanger, Emma Strubell, Teruko Mitamura, Jeff Schneider, Eduard Hovy, Roger Grosse, Eric Xing
Large language models (LLMs) are trained on a vast amount of human-written data, but data providers often remain uncredited.
no code implementations • 18 Apr 2024 • Ian Char, Youngseog Chung, Joseph Abbate, Egemen Kolemen, Jeff Schneider
Although tokamaks are one of the most promising devices for realizing nuclear fusion as an energy source, there are still key obstacles when it comes to understanding the dynamics of the plasma and controlling it.
no code implementations • 12 Feb 2024 • Jacob Tyo, Motolani Olarinre, Youngseog Chung, Zachary C. Lipton
With these datasets and analysis of model limitations, we aim to foster innovations in handling real-world conditions like mud and complex poses to drive progress in robust computer vision.
Optical Character Recognition
Optical Character Recognition (OCR)
+2
1 code implementation • 14 Nov 2023 • Jacob Tyo, Youngseog Chung, Motolani Olarinre, Zachary C. Lipton
RnD represents a valuable new benchmark to drive innovation in real-world OCR capabilities.
Optical Character Recognition
Optical Character Recognition (OCR)
1 code implementation • 14 Nov 2023 • Jacob Tyo, Motolani Olarinre, Youngseog Chung, Zachary C. Lipton
We analyze the impact of real-world factors including mud, pose, lighting, and more.
1 code implementation • 29 May 2023 • Youngseog Chung, Aaron Rumack, Chirag Gupta
In a sequential regression setting, a decision-maker may be primarily concerned with whether the future observation will increase or decrease compared to the current one, rather than the actual value of the future observation.
no code implementations • 27 Mar 2023 • Satoshi Kataoka, Youngseog Chung, Seyed Kamyar Seyed Ghasemipour, Pannag Sanketi, Shixiang Shane Gu, Igor Mordatch
Without manually-designed controller nor human demonstrations, we demonstrate that with careful Sim2Real considerations, our policies trained with RL in simulation enable two xArm6 robots to solve the U-shape assembly task with a success rate of above90% in simulation, and 50% on real hardware without any additional real-world fine-tuning.
no code implementations • 20 May 2022 • Conor Igoe, Youngseog Chung, Ian Char, Jeff Schneider
One critical challenge in deploying highly performant machine learning models in real-life applications is out of distribution (OOD) detection.
1 code implementation • 21 Sep 2021 • Youngseog Chung, Ian Char, Han Guo, Jeff Schneider, Willie Neiswanger
With increasing deployment of machine learning systems in various real-world tasks, there is a greater need for accurate quantification of predictive uncertainty.
2 code implementations • NeurIPS 2021 • Youngseog Chung, Willie Neiswanger, Ian Char, Jeff Schneider
However, this loss restricts the scope of applicable regression models, limits the ability to target many desirable properties (e. g. calibration, sharpness, centered intervals), and may produce poor conditional quantiles.
no code implementations • 23 Jun 2020 • Viraj Mehta, Ian Char, Willie Neiswanger, Youngseog Chung, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider
We introduce Neural Dynamical Systems (NDS), a method of learning dynamical models in various gray-box settings which incorporates prior knowledge in the form of systems of ordinary differential equations.
no code implementations • ICLR Workshop DeepDiffEq 2019 • Viraj Mehta, Ian Char, Willie Neiswanger, Youngseog Chung, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider
We introduce Neural Dynamical Systems (NDS), a method of learning dynamical models which incorporates prior knowledge in the form of systems of ordinary differential equations.
no code implementations • 6 Jan 2020 • Youngseog Chung, Ian Char, Willie Neiswanger, Kirthevasan Kandasamy, Andrew Oakleigh Nelson, Mark D Boyer, Egemen Kolemen, Jeff Schneider
One obstacle in utilizing fusion as a feasible energy source is the stability of the reaction.
1 code implementation • NeurIPS 2019 • Ian Char, Youngseog Chung, Willie Neiswanger, Kirthevasan Kandasamy, Oak Nelson, Mark Boyer, Egemen Kolemen
In black-box optimization, an agent repeatedly chooses a configuration to test, so as to find an optimal configuration.