How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
- Hongkang Li
- Meng Weng
- et al.
- 2024
- ICML 2024
Conference paper
Publications
54 results at ICML 2024
Representing Molecules as Random Walks Over Interpretable Grammars
- Michael Sun
- Minghao Guo
- et al.
- 2024
- ICML 2024
Conference paperA Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
- Mohammed Nowaz Rabbani Chowdhury
- Meng Wang
- et al.
- 2024
- ICML 2024
Conference paperDistributed Bilevel Optimization with Communication Compression
- Yutong He
- Jie Hu
- et al.
- 2024
- ICML 2024
Conference paperLaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits
- Chen-chia Chang
- Yikang Shen
- et al.
- 2024
- ICML 2024
Conference paperGraph2Tac: Online Representation Learning of Formal Math Concepts
- Lasse Blaauwbroek
- Miroslav Olšák
- et al.
- 2024
- ICML 2024
Conference paperSF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
- Shuai Zhang
- Heshan Fernando
- et al.
- 2024
- ICML 2024
Conference paperLearning Optimal Projection for Forecast Reconciliation of Hierarchical Time Series
- Asterios Tsiourvas
- Wei Sun
- et al.
- 2024
- ICML 2024
Conference paperLarimar: Large Language Models with Episodic Memory Control
- 2024
- ICML 2024
Conference paperWhat Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
- Hongkang Li
- Meng Wang
- et al.
- 2024
- ICML 2024
Conference paper