Denny Zhou

A Pretrainer’s Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity NAACL 2024 Chain of Thought Empowers Transformers to Solve Inherently Serial Problems ICLR 2024 Chain-of-Thought Reasoning Without Prompting NeurIPS 2024 FreshLLMs: Refreshing Large Language Models with Search Engine Augmentation ACL 2024 Large Language Models as Analogical Reasoners ICLR 2024 Large Language Models as Optimizers ICLR 2024 Large Language Models as Tool Makers ICLR 2024 Large Language Models Cannot Self-Correct Reasoning Yet ICLR 2024 Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models ICLR 2024 Premise Order Matters in Reasoning with Large Language Models ICML 2024 Scaling Instruction-Finetuned Language Models JMLR 2024 SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures NeurIPS 2024 Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models ICLR 2024 Teaching Large Language Models to Self-Debug ICLR 2024 Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them ACL 2023 Compositional Semantic Parsing with Large Language Models ICLR 2023 Language models are multilingual chain-of-thought reasoners ICLR 2023 Large Language Models Can Be Easily Distracted by Irrelevant Context ICML 2023 Least-to-Most Prompting Enables Complex Reasoning in Large Language Models ICLR 2023 Mind's Eye: Grounded Language Model Reasoning through Simulation ICLR 2023 Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization ICML 2023 PaLM: Scaling Language Modeling with Pathways JMLR 2023 Recitation-Augmented Language Models ICLR 2023 Self-Consistency Improves Chain of Thought Reasoning in Language Models ICLR 2023 Symbol tuning improves in-context learning in language models EMNLP 2023 TEMPERA: Test-Time Prompt Editing via Reinforcement Learning ICLR 2023 The Flan Collection: Designing Data and Methods for Effective Instruction Tuning ICML 2023 Transcending Scaling Laws with 0.1% Extra Compute EMNLP 2023 UL2: Unifying Language Learning Paradigms ICLR 2023 ​​What learning algorithm is in-context learning? Investigations with linear models ICLR 2023 A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation ECCV 2022 Auto-scaling Vision Transformers without Training ICLR 2022 Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropagation NeurIPS 2022 Chain-of-Thought Prompting Elicits Reasoning in Large Language Models NeurIPS 2022 DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection CVPR 2022 Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance ICML 2022 Token Dropping for Efficient BERT Pretraining ACL 2022 Extremely Small BERT Models from Mixed-Vocabulary Training EACL 2021 Fast WordPiece Tokenization EMNLP 2021 LEGO: Latent Execution-Guided Reasoning for Multi-Hop Question Answering on Knowledge Graphs ICML 2021 SpreadsheetCoder: Formula Prediction from Semi-structured Context ICML 2021 Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning ICLR 2020 Compositional Generalization via Neural-Symbolic Stack Machines NeurIPS 2020 Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection ICML 2020 Go Wide, Then Narrow: Efficient Training of Deep Thin Networks ICML 2020 MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices ACL 2020 Neural Symbolic Reader: Scalable Integration of Distributed and Symbolic Representations for Reading Comprehension ICLR 2020 Neural Logic Machines ICLR 2019