no code implementations • EAMT 2020 • António Lopes, M. Amin Farajian, Rachel Bawden, Michael Zhang, André F. T. Martins
In this paper we provide a systematic comparison of existing and new document-level neural machine translation solutions.
1 code implementation • 14 Oct 2024 • Michael Zhang, Simran Arora, Rahul Chalamala, Alan Wu, Benjamin Spector, Aaryan Singhal, Krithik Ramesh, Christopher Ré
When compared with prior approaches under the same compute budgets, LoLCATs significantly improves linearizing quality, closing the gap between linearized and original Llama 3. 1 70B and 405B LLMs by 77. 8% and 78. 1% on 5-shot MMLU.
no code implementations • 26 Sep 2024 • Shouwei Hui, Michael Zhang
Despite growing interest in vehicle platooning research, the effect of communication capability between platoons is not investigated to a depth of depth.
no code implementations • 29 May 2024 • Shouwei Hui, Michael Zhang
This paper presents a novel approach to coordinated vehicle platooning, where the platoon followers communicate solely with the platoon leader.
3 code implementations • 28 Feb 2024 • Simran Arora, Sabri Eyuboglu, Michael Zhang, Aman Timalsina, Silas Alberti, Dylan Zinsley, James Zou, Atri Rudra, Christopher Ré
In this work, we explore whether we can improve language model efficiency (e. g. by reducing memory consumption) without compromising on recall.
1 code implementation • 6 Feb 2024 • Michael Zhang, Kush Bhatia, Hermann Kumbong, Christopher Ré
Experiments show Hedgehog recovers over 99% of standard Transformer quality in train-from-scratch and finetuned-conversion settings, outperforming prior linear attentions up to 6 perplexity points on WikiText-103 with causal GPTs, and up to 8. 7 GLUE score points on finetuned bidirectional BERTs.
no code implementations • 5 Feb 2024 • Ammar Haydari, Dongjie Chen, Zhengfeng Lai, Michael Zhang, Chen-Nee Chuah
Then, we constrained the training process via a road connectivity matrix that provides the connectivity of sequences in trajectory generation, thereby keeping generated trajectories in geospatial limits.
no code implementations • 15 Nov 2023 • Yanlin Qi, Jia Li, Michael Zhang
This new data-driven framework provides a cost-effective and adaptable solution that complements the case-specific approaches for CMF estimation, which is particularly beneficial when availability of crash data or time imposes constraints.
no code implementations • 16 Oct 2023 • Xianyue Peng, Hang Gao, Gengyue Han, Hao Wang, Michael Zhang
In this paper, we propose a joint optimization approach for traffic signal control and vehicle routing in signalized road networks.
1 code implementation • 10 Apr 2023 • Yanlin Qi, Gengchen Mai, Rui Zhu, Michael Zhang
Over the past decade, the electric vehicle industry has experienced unprecedented growth and diversification, resulting in a complex ecosystem.
1 code implementation • 16 Mar 2023 • Michael Zhang, Khaled K. Saab, Michael Poli, Tri Dao, Karan Goel, Christopher Ré
For expressivity, we propose a new SSM parameterization based on the companion matrix -- a canonical representation for discrete-time processes -- which enables SpaceTime's SSM layers to learn desirable autoregressive processes.
1 code implementation • 13 Feb 2023 • Daniel Y. Fu, Elliot L. Epstein, Eric Nguyen, Armin W. Thomas, Michael Zhang, Tri Dao, Atri Rudra, Christopher Ré
We find that a key requirement to achieving high performance is keeping the convolution kernels smooth.
no code implementations • 14 Jul 2022 • Michael Zhang, Christopher Ré
We also find that efficient ways to improve model inference (e. g., via adapters, lightweight networks with FM embeddings as inputs) do not consistently improve and can sometimes hurt group robustness compared to zero-shot (e. g., increasing the accuracy gap by 50. 1 pp on CelebA).
1 code implementation • 1 Jul 2022 • Michael Zhang, Samuel Kim, Peter Y. Lu, Marin Soljačić
Symbolic regression is a machine learning technique that can learn the governing formulas of data and thus has the potential to transform scientific discovery.
1 code implementation • 15 Apr 2022 • Mayee F. Chen, Daniel Y. Fu, Avanika Narayan, Michael Zhang, Zhao Song, Kayvon Fatahalian, Christopher Ré
We first prove that adding a weighted class-conditional InfoNCE loss to SupCon controls the degree of spread.
1 code implementation • 24 Mar 2022 • Mayee F. Chen, Daniel Y. Fu, Dyah Adila, Michael Zhang, Frederic Sala, Kayvon Fatahalian, Christopher Ré
Despite the black-box nature of foundation models, we prove results characterizing how our approach improves performance and show that lift scales with the smoothness of label distributions in embedding space.
no code implementations • ICLR 2022 • Justin Y. Chen, Talya Eden, Piotr Indyk, Honghao Lin, Shyam Narayanan, Ronitt Rubinfeld, Sandeep Silwal, Tal Wagner, David P. Woodruff, Michael Zhang
We propose data-driven one-pass streaming algorithms for estimating the number of triangles and four cycles, two fundamental problems in graph analytics that are widely studied in the graph data stream literature.
1 code implementation • 3 Mar 2022 • Michael Zhang, Nimit S. Sohoni, Hongyang R. Zhang, Chelsea Finn, Christopher Ré
As ERM models can be good spurious attribute predictors, CNC works by (1) using a trained ERM model's outputs to identify samples with the same class but dissimilar spurious features, and (2) training a robust model with contrastive learning to learn similar representations for same-class samples.
no code implementations • 29 Sep 2021 • Daniel Yang Fu, Mayee F Chen, Michael Zhang, Kayvon Fatahalian, Christopher Ré
Supervised contrastive learning optimizes a loss that pushes together embeddings of points from the same class while pulling apart embeddings of points from different classes.
2 code implementations • 16 Aug 2021 • Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch, Dallas Card, Rodrigo Castellon, Niladri Chatterji, Annie Chen, Kathleen Creel, Jared Quincy Davis, Dora Demszky, Chris Donahue, Moussa Doumbouya, Esin Durmus, Stefano Ermon, John Etchemendy, Kawin Ethayarajh, Li Fei-Fei, Chelsea Finn, Trevor Gale, Lauren Gillespie, Karan Goel, Noah Goodman, Shelby Grossman, Neel Guha, Tatsunori Hashimoto, Peter Henderson, John Hewitt, Daniel E. Ho, Jenny Hong, Kyle Hsu, Jing Huang, Thomas Icard, Saahil Jain, Dan Jurafsky, Pratyusha Kalluri, Siddharth Karamcheti, Geoff Keeling, Fereshte Khani, Omar Khattab, Pang Wei Koh, Mark Krass, Ranjay Krishna, Rohith Kuditipudi, Ananya Kumar, Faisal Ladhak, Mina Lee, Tony Lee, Jure Leskovec, Isabelle Levent, Xiang Lisa Li, Xuechen Li, Tengyu Ma, Ali Malik, Christopher D. Manning, Suvir Mirchandani, Eric Mitchell, Zanele Munyikwa, Suraj Nair, Avanika Narayan, Deepak Narayanan, Ben Newman, Allen Nie, Juan Carlos Niebles, Hamed Nilforoshan, Julian Nyarko, Giray Ogut, Laurel Orr, Isabel Papadimitriou, Joon Sung Park, Chris Piech, Eva Portelance, Christopher Potts, aditi raghunathan, Rob Reich, Hongyu Ren, Frieda Rong, Yusuf Roohani, Camilo Ruiz, Jack Ryan, Christopher Ré, Dorsa Sadigh, Shiori Sagawa, Keshav Santhanam, Andy Shih, Krishnan Srinivasan, Alex Tamkin, Rohan Taori, Armin W. Thomas, Florian Tramèr, Rose E. Wang, William Wang, Bohan Wu, Jiajun Wu, Yuhuai Wu, Sang Michael Xie, Michihiro Yasunaga, Jiaxuan You, Matei Zaharia, Michael Zhang, Tianyi Zhang, Xikun Zhang, Yuhui Zhang, Lucia Zheng, Kaitlyn Zhou, Percy Liang
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
3 code implementations • ICLR 2021 • Michael Zhang, Karan Sapra, Sanja Fidler, Serena Yeung, Jose M. Alvarez
While federated learning traditionally aims to train a single global model across decentralized local datasets, one model may not always be ideal for all participating clients.
no code implementations • 13 Dec 2020 • Michael Zhang, Xiaotian Cheng, Daniel Copeland, Arjun Desai, Melody Y. Guan, Gabriel A. Brat, Serena Yeung
A state-of-the-art convolutional neural network architecture for object detection was used to detect operating hands in open surgery videos.
no code implementations • 9 Oct 2020 • Michael Zhang
Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to personalized settings.
1 code implementation • 20 Apr 2020 • Michael Zhang, Yayaati Chachan, Eliza M. -R. Kempton, Heather Knutson, Wenjun, Chang
Recently, we introduced PLanetary Atmospheric Tool for Observer Noobs (PLATON), a Python package that calculates model transmission spectra for exoplanets and retrieves atmospheric characteristics based on observed spectra.
Earth and Planetary Astrophysics Instrumentation and Methods for Astrophysics
no code implementations • 24 Nov 2019 • Haipeng Xing, Yingru Wu, Yong Chen, Michael Zhang
Background: The nucleus of eukaryotic cells spatially packages chromosomes into a hierarchical and distinct segregation that plays critical roles in maintaining transcription regulation.
Applications Methodology
no code implementations • 1 Jun 2019 • Li-Fang Cheng, Bianca Dumitrascu, Michael Zhang, Corey Chivers, Michael Draugelis, Kai Li, Barbara E. Engelhardt
However, capturing the short-term effects of drugs and therapeutic interventions on patient physiological state remains challenging.
1 code implementation • 28 Nov 2018 • Michael Zhang, Yayaati Chachan, Eliza M. -R. Kempton, Heather A. Knutson
It also has less commonly included features, such as a Mie scattering cloud model and unocculted starspot corrections.
Earth and Planetary Astrophysics Instrumentation and Methods for Astrophysics
2 code implementations • 6 Nov 2018 • Dallas Card, Michael Zhang, Noah A. Smith
Recent advances in deep learning have achieved impressive gains in classification accuracy on a variety of types of data, including images and text.
1 code implementation • 19 Jan 2018 • Lisa Dang, Nicolas B. Cowan, Joel C. Schwartz, Emily Rauscher, Michael Zhang, Heather A. Knutson, Michael Line, Ian Dobbs-Dixon, Drake Deming, Sudarsan Sundararajan, Jonathan J. Fortney, Ming Zhao
The peculiar infrared flux map of CoRoT-2b may result from westward winds due to non-synchronous rotation magnetic effects, or partial cloud coverage, that obscures the emergent flux from the planet's eastern hemisphere.
Earth and Planetary Astrophysics
no code implementations • 17 Jul 2017 • Carlos Florensa, David Held, Markus Wulfmeier, Michael Zhang, Pieter Abbeel
The robot is trained in reverse, gradually learning to reach the goal from a set of start states increasingly far from the goal.
no code implementations • 15 May 2017 • David Held, Zoe McCarthy, Michael Zhang, Fred Shentu, Pieter Abbeel
Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy.