Alessandro Achille

PICASO: Permutation-Invariant Context Composition with State Space Models ICLR 2025 B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory NeurIPS 2024 CPR: Retrieval Augmented Generation for Copyright Protection CVPR 2024 Critical Learning Periods Emerge Even in Deep Linear Networks ICLR 2024 Diffusion Soup: Model Merging for Text-to-Image Diffusion Models ECCV 2024 Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encoding CVPR 2024 Meaning Representations from Trajectories in Autoregressive Models ICLR 2024 Multi-Modal Hallucination Control by Visual Information Grounding CVPR 2024 A-La-Carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting CVPR 2023 A Meta-Learning Approach to Predicting Performance and Data Requirements CVPR 2023 Critical Learning Periods for Multisensory Integration in Deep Networks CVPR 2023 Gacs-Korner Common Information Variational Autoencoder NeurIPS 2023 Leveraging sparse and shared feature activations for disentangled representation learning NeurIPS 2023 Linear Spaces of Meanings: Compositional Structures in Vision-Language Models ICCV 2023 SAFE: Machine Unlearning With Shard Graphs ICCV 2023 Train/Test-Time Adaptation With Retrieval CVPR 2023 Your representations are in the network: composable and parallel adaptation for large scale models NeurIPS 2023 DIVA: Dataset Derivative of a Learning Task ICLR 2022 Mixed Differential Privacy in Computer Vision CVPR 2022 On Leave-One-Out Conditional Mutual Information For Generalization NeurIPS 2022 Task Adaptive Parameter Sharing for Multi-Task Learning CVPR 2022 Adversarial Training Reduces Information and Improves Transferability AAAI 2021 Estimating informativeness of samples with Smooth Unique Information ICLR 2021 LayoutTransformer: Layout Generation and Completion With Self-Attention ICCV 2021 LQF: Linear Quadratic Fine-Tuning CVPR 2021 Mixed-Privacy Forgetting in Deep Networks CVPR 2021 On Plasticity, Invariance, and Mutually Frozen Weights in Sequential Task Learning NeurIPS 2021 Structured Prediction as Translation between Augmented Natural Languages ICLR 2021 Usable Information and Evolution of Optimal Representations During Training ICLR 2021 Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks CVPR 2020 Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations ECCV 2020 Incremental Few-Shot Meta-Learning via Indirect Discriminant Alignment ECCV 2020 Predicting Training Time Without Training NeurIPS 2020 Critical Learning Periods in Deep Networks ICLR 2019 Task2Vec: Task Embedding for Meta-Learning ICCV 2019 Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence NeurIPS 2019 Emergence of Invariance and Disentanglement in Deep Representations JMLR 2018 Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies NeurIPS 2018