72 results on '"François Fleuret"'
Search Results
2. LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging.
3. {\sigma}-GPTs: A New Approach to Autoregressive Models.
4. Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences.
5. Localizing Task Information for Improved Model Merging and Compression.
6. DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging.
7. Multi-Lattice Sampling of Quantum Field Theories via Neural Operator-based Flows.
8. Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models.
9. Diffusion for World Modeling: Visual Details Matter in Atari.
10. Efficient World Models with Context-Aware Tokenization.
11. PAUMER: Patch Pausing Transformer for Semantic Segmentation.
12. DeepEMD: A Transformer-based Fast Estimation of the Earth Mover's Distance.
13. Graph Neural Networks Go Forward-Forward.
14. Faster Causal Attention Over Large Sequences Through Sparse Flash Attention.
15. Learning Deformation Trajectories of Boltzmann Densities.
16. SequeL: A Continual Learning Library in PyTorch and JAX.
17. Pareto Manifold Learning: Tackling multiple tasks via ensembles of single-task models.
18. Borrowing from yourself: Faster future video segmentation with partial channel update.
19. Accurate Extrinsic Prediction of Physical Systems Using Transformers.
20. Transformers are Sample Efficient World Models.
21. Flatten the Curve: Efficiently Training Low-Curvature Neural Networks.
22. ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields.
23. SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics.
24. HyperMixer: An MLP-based Green AI Alternative to Transformers.
25. Flowification: Everything is a Normalizing Flow.
26. Deformation Theory of Boltzmann Distributions.
27. The Theoretical Expressiveness of Maxpooling.
28. Agree to Disagree: Diversity through Disagreement for Better Transferability.
29. MineRL Diamond 2021 Competition: Overview, Results, and Lessons Learned.
30. Language Models are Few-Shot Butlers.
31. Structural analysis of an all-purpose question answering model.
32. GeoNeRF: Generalizing NeRF with Geometry Priors.
33. Unsupervised clustering of series using dynamic programming and neural processes.
34. Unsupervised clustering of series using dynamic programming.
35. Priming PCA with EigenGame.
36. Test time Adaptation through Perturbation Robustness.
37. Efficient Wind Speed Nowcasting with GPU-Accelerated Nearest Neighbors Algorithm.
38. Fast Transformers with Clustered Attention.
39. Fair Latency-Aware Metric for real-time video segmentation networks.
40. Gradient Alignment in Deep Neural Networks.
41. On the importance of pre-training data volume for compact language models.
42. Taming GANs with Lookahead.
43. Multi-task Reinforcement Learning with a Planning Quasi-Metric.
44. Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention.
45. Processing Megapixel Images with Deep Attention-Sampling Models.
46. Reducing Noise in GAN Training with Variance Reduced Extragradient.
47. On the Tunability of Optimizers in Deep Learning.
48. Full-Jacobian Representation of Neural Networks.
49. Not All Samples Are Created Equal: Deep Learning with Importance Sampling.
50. Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.