François Fleuret
- Papers
- 13
Cite
Notes
Only stored in your browser.
Authored papers
13Diffusion for World Modeling: Visual Details Matter in Atari
arXiv 2024
Efficient World Models with Context-Aware Tokenization
arXiv 2024
LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
arXiv 2024
Solvation Free Energies from Neural Thermodynamic Integration
arXiv 2024
σ-GPTs: A New Approach to Autoregressive Models
arXiv 2024
Localizing Task Information for Improved Model Merging and Compression
arXiv 2024
Faster Causal Attention Over Large Sequences Through Sparse Flash Attention
arXiv 2023
SequeL: A Continual Learning Library in PyTorch and JAX
arXiv 2023
HyperMixer: An MLP-based Low Cost Alternative to Transformers
arXiv 2022
Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models
arXiv 2022
Language Models are Few-Shot Butlers
EMNLP 2021 11
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
ICML 2020 1
Full-Gradient Representation for Neural Network Visualization
full-gradient-representation-for-neural
Affiliations
Frequent co-authors
10from 13 papers