conftrace_
← Authors

Alessandro Achille

38 papers · 2018–2025 · 7 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+9 more ↓ πŸŒ‰ Interdisciplinary Bridge 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (7) πŸƒ Academic Marathon (7) πŸ—ΊοΈ Taxonomy Completionist (59)
🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) 🀝 Dynamic Duo (33) ⚑ Prolific Year (9) πŸ’Ž Century Club (38) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (8) πŸ—ƒοΈ Keyword Collector (116)

Conferences

CVPR (12) NIPS (9) ICLR (8) ICCV (4) ECCV (3) AAAI (1) JMLR (1)

Top co-authors

Stefano Soatto (33) Aditya Golatkar (11) Luca Zancato (11) Avinash Ravichandran (10) Matthew Trager (8) Ashwin Swaminathan (6) Pramuditha Perera (5) Tian Yu Liu (4) Giovanni Paolini (4) Benjamin Bowman (4)

Research topics

Privacy (1)

Keywords

transfer learning (6) representation learning (4) machine unlearning (4) information theory (3) deep neural network (2) weight decay (2) vision-language model (2) transformer architecture (2) fisher information (2) catastrophic forgetting (2) image classification (2) stochastic gradient descent (2) variational autoencoder (2) multi-task learning (2) differential privacy (2) self-supervised learning (2) model adaptation (2) disentangled representation (2) continual learning (2) selective forgetting (2)

Papers

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