🧑‍🔬 Tengyu Ma — all works

33 works · ← Tengyu Ma

1. Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetWenxuan Zhou et al.2021 · 407 citations
2. A Latent Variable Model Approach to PMI-based Word EmbeddingsTransactions of the Association for Computational Linguistics (TACL)Sanjeev Arora, Yuanzhi Li, Yingyu Liang, et al.2016 · 372 citations
3. An Explanation of In-context Learning as Implicit Bayesian InferencearXiv:2111.02080Sang Michael Xie, Aditi Raghunathan, Percy Liang, et al.2021 · 286 citations
4. Larger language models do in-context learning differentlyarXiv:2303.03846Jerry Wei, Jason Wei, Yi Tay, et al.2023 · 285 citations
5. MOPO: Model-based Offline Policy Optimization ↗arXiv (Cornell University) · no summary yetTianhe Yu et al.2020 · 260 citations
6. Linear Algebraic Structure of Word Senses, with Applications to PolysemyTransactions of the Association for Computational Linguistics (TACL)Sanjeev Arora, Yuanzhi Li, Yingyu Liang, et al.2018 · 254 citations
7. Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution ↗arXiv (Cornell University) · no summary yetAnanya Kumar et al.2022 · 248 citations
8. What learning algorithm is in-context learning? Investigations with linear modelsarXiv:2211.15661Ekin Akyürek, Dale Schuurmans, Jacob Andreas, et al.2022 · 236 citations
9. Verified Uncertainty Calibration ↗arXiv:1909.10155 · no summary yetAnanya Kumar, Percy Liang, Tengyu Ma2019 · 172 citations
10. DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining ↗arXiv:2305.10429 · no summary yetSang Michael Xie et al.2023 · 156 citations
11. Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks ↗arXiv (Cornell University) · no summary yetYuanzhi Li, Colin Wei, Tengyu Ma2019 · 138 citations
12. Data Selection for Language Models via Importance Resampling ↗arXiv:2302.03169 · no summary yetSang Michael Xie et al.2023 · 137 citations
13. A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors ↗Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetMikhail Khodak et al.2018 · 128 citations
14. Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees ↗arXiv (Cornell University) · no summary yetYuping Luo et al.2018 · 125 citations
15. Large Language Models as Tool Makers ↗arXiv:2305.17126 · no summary yetTianle Cai et al.2023 · 123 citations
16. Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training ↗arXiv:2305.14342 · no summary yetHong Liu et al.2023 · 70 citations
17. Symbol tuning improves in-context learning in language models ↗Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing · no summary yetJerry Wei et al.2023 · 68 citations
18. STP: Self-play LLM Theorem Provers with Iterative Conjecturing and Proving ↗arXiv:2502.00212 · no summary yetKefan Dong, Tengyu Ma2025 · 43 citations
19. Understanding Self-Training for Gradual Domain Adaptation ↗arXiv (Cornell University) · no summary yetAnanya Kumar, Tengyu Ma, Percy Liang2020 · 39 citations
20. Algorithmic Regularization in Over-parameterized Matrix Sensing and Neural Networks with Quadratic Activations ↗arXiv (Cornell University) · no summary yetYuanzhi Li, Tengyu Ma, Hongyang Zhang2017 · 38 citations
21. Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK ↗arXiv (Cornell University) · no summary yetYuanzhi Li, Tengyu Ma, Hongyang Zhang2020 · 33 citations
22. Individual Calibration with Randomized Forecasting ↗arXiv (Cornell University) · no summary yetShengjia Zhao, Tengyu Ma, Stefano Ermon2020 · 24 citations
23. Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation ↗arXiv (Cornell University) · no summary yetKendrick Shen et al.2022 · 23 citations
24. One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention ↗arXiv:2307.03576 · no summary yetArvind Mahankali, Tatsunori B. Hashimoto, Tengyu Ma2023 · 22 citations
25. RAND-WALK: A Latent Variable Model Approach to Word Embeddings ↗arXiv (Cornell University) · no summary yetSanjeev Arora et al.2015 · 21 citations
26. Understanding Warmup-Stable-Decay Learning Rates: A River Valley Loss Landscape Perspective ↗arXiv (Cornell University) · no summary yetKaiyue Wen et al.2024 · 18 citations
27. In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness ↗arXiv (Cornell University) · no summary yetSang Michael Xie et al.2020 · 18 citations
28. Calibrating Predictions to Decisions: A Novel Approach to Multi-Class Calibration ↗arXiv (Cornell University) · no summary yetShengjia Zhao et al.2021 · 12 citations
29. Fantastic Pretraining Optimizers and Where to Find Them ↗arXiv (Cornell University) · no summary yetKaiyue Wen et al.2025 · 11 citations
30. Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift ↗arXiv (Cornell University) · no summary yetAnanya Kumar et al.2022 · 10 citations
31. Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization ↗arXiv (Cornell University) · no summary yetKaiyue Wen et al.2026 · 2 citations
32. Simplifying Models with Unlabeled Output Data ↗arXiv (Cornell University) · no summary yetSang Michael Xie, Tengyu Ma, Percy Liang2021 · 1 citation
33. Priced Guidance: Can Language Models Generate Future Research Ideas? ↗arXiv (Cornell University) · no summary yetKaiyue Wen, Tengyu Ma, Percy Liang2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/tengyu-ma/works/