ICML 2024 "sequence modeling" Papers
10 papers found
An Information-Theoretic Analysis of In-Context Learning
Hong Jun Jeon, Jason Lee, Qi Lei et al.
ICML 2024posterarXiv:2401.15530
Efficient World Models with Context-Aware Tokenization
Vincent Micheli, Eloi Alonso, François Fleuret
ICML 2024posterarXiv:2406.19320
From Generalization Analysis to Optimization Designs for State Space Models
Fusheng Liu, Qianxiao Li
ICML 2024oralarXiv:2405.02670
How Transformers Learn Causal Structure with Gradient Descent
Eshaan Nichani, Alex Damian, Jason Lee
ICML 2024posterarXiv:2402.14735
Reinformer: Max-Return Sequence Modeling for Offline RL
Zifeng Zhuang, Dengyun Peng, Jinxin Liu et al.
ICML 2024posterarXiv:2405.08740
Repeat After Me: Transformers are Better than State Space Models at Copying
Samy Jelassi, David Brandfonbrener, Sham Kakade et al.
ICML 2024posterarXiv:2402.01032
Rethinking Decision Transformer via Hierarchical Reinforcement Learning
Yi Ma, Jianye Hao, Hebin Liang et al.
ICML 2024posterarXiv:2311.00267
Timer: Generative Pre-trained Transformers Are Large Time Series Models
Yong Liu, Haoran Zhang, Chenyu Li et al.
ICML 2024posterarXiv:2402.02368
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
Antonio Orvieto, Soham De, Caglar Gulcehre et al.
ICML 2024posterarXiv:2307.11888
Vocabulary for Universal Approximation: A Linguistic Perspective of Mapping Compositions
Yongqiang Cai
ICML 2024spotlightarXiv:2305.12205