Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Zhang, Michael R."'
Autor:
Yang, Blair, Cui, Fuyang, Paster, Keiran, Ba, Jimmy, Vaezipoor, Pashootan, Pitis, Silviu, Zhang, Michael R.
The rapid development and dynamic nature of large language models (LLMs) make it difficult for conventional quantitative benchmarks to accurately assess their capabilities. We propose report cards, which are human-interpretable, natural language summ
Externí odkaz:
http://arxiv.org/abs/2409.00844
Autor:
Jaipersaud, Brandon, Zhang, Paul, Ba, Jimmy, Petersen, Andrew, Zhang, Lisa, Zhang, Michael R.
Publikováno v:
In: Artificial Intelligence in Education. AIED 2023. Communications in Computer and Information Science, vol 1831. Springer, Cham
We propose and evaluate a question-answering system that uses decomposed prompting to classify and answer student questions on a course discussion board. Our system uses a large language model (LLM) to classify questions into one of four types: conce
Externí odkaz:
http://arxiv.org/abs/2407.21170
Recent advancements in large language models (LLMs) have greatly enhanced natural language processing (NLP) applications. Nevertheless, these models often inherit biases from their training data. Despite the availability of various datasets, most are
Externí odkaz:
http://arxiv.org/abs/2406.04220
Machine unlearning is a desirable operation as models get increasingly deployed on data with unknown provenance. However, achieving exact unlearning -- obtaining a model that matches the model distribution when the data to be forgotten was never used
Externí odkaz:
http://arxiv.org/abs/2402.00751
This paper explores the use of foundational large language models (LLMs) in hyperparameter optimization (HPO). Hyperparameters are critical in determining the effectiveness of machine learning models, yet their optimization often relies on manual app
Externí odkaz:
http://arxiv.org/abs/2312.04528
Methods such as chain-of-thought prompting and self-consistency have pushed the frontier of language model reasoning performance with no additional training. To further improve performance, we propose a prompt ensembling method for large language mod
Externí odkaz:
http://arxiv.org/abs/2304.05970
Autor:
Bae, Juhan, Zhang, Michael R., Ruan, Michael, Wang, Eric, Hasegawa, So, Ba, Jimmy, Grosse, Roger
Variational autoencoders (VAEs) are powerful tools for learning latent representations of data used in a wide range of applications. In practice, VAEs usually require multiple training rounds to choose the amount of information the latent variable sh
Externí odkaz:
http://arxiv.org/abs/2212.03905
Publikováno v:
NeurIPS2021
Deep Reinforcement Learning (RL) is successful in solving many complex Markov Decision Processes (MDPs) problems. However, agents often face unanticipated environmental changes after deployment in the real world. These changes are often spurious and
Externí odkaz:
http://arxiv.org/abs/2110.14248
Autor:
Zhang, Michael R., Paine, Tom Le, Nachum, Ofir, Paduraru, Cosmin, Tucker, George, Wang, Ziyu, Norouzi, Mohammad
Standard dynamics models for continuous control make use of feedforward computation to predict the conditional distribution of next state and reward given current state and action using a multivariate Gaussian with a diagonal covariance structure. Th
Externí odkaz:
http://arxiv.org/abs/2104.13877
Linear interpolation between initial neural network parameters and converged parameters after training with stochastic gradient descent (SGD) typically leads to a monotonic decrease in the training objective. This Monotonic Linear Interpolation (MLI)
Externí odkaz:
http://arxiv.org/abs/2104.11044