Yuanzhi Li

papers

758

total citations

papers (14)

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

ICLR 2025arXiv

100

citations

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

NEURIPS 2023arXiv

citations

The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning

NEURIPS 2022arXiv

citations

When Is Generalizable Reinforcement Learning Tractable?

NEURIPS 2021arXiv

citations

How Does Adaptive Optimization Impact Local Neural Network Geometry?

NEURIPS 2023arXiv

citations

Mixture of Parrots: Experts improve memorization more than reasoning

ICLR 2025arXiv

citations

Learning (Very) Simple Generative Models Is Hard

NEURIPS 2022arXiv

citations

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning

AAAI 2024arXiv

citations

Towards Understanding the Mixture-of-Experts Layer in Deep Learning

NEURIPS 2022

citations

Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels

NEURIPS 2021

citations

SPRING: Studying Papers and Reasoning to play Games

NEURIPS 2023

citations

Yuanzhi Li

papers (14)

Physics of Language Models: Part 3.1, Knowledge Storage and Extraction

The probability flow ODE is provably fast

Vision Transformers provably learn spatial structure

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning

When Is Generalizable Reinforcement Learning Tractable?

How Does Adaptive Optimization Impact Local Neural Network Geometry?

Mixture of Parrots: Experts improve memorization more than reasoning

Learning (Very) Simple Generative Models Is Hard

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning

Towards Understanding the Mixture-of-Experts Layer in Deep Learning

Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels

SPRING: Studying Papers and Reasoning to play Games

papers (14)

Physics of Language Models: Part 3.1, Knowledge Storage and Extraction

The probability flow ODE is provably fast

Vision Transformers provably learn spatial structure

Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning Process

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

The Mechanism of Prediction Head in Non-contrastive Self-supervised Learning

When Is Generalizable Reinforcement Learning Tractable?

How Does Adaptive Optimization Impact Local Neural Network Geometry?

Mixture of Parrots: Experts improve memorization more than reasoning

Learning (Very) Simple Generative Models Is Hard

Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning

Towards Understanding the Mixture-of-Experts Layer in Deep Learning

Local Signal Adaptivity: Provable Feature Learning in Neural Networks Beyond Kernels

SPRING: Studying Papers and Reasoning to play Games