pith. sign in

Luca Zancato

Identifiers

  • name variant Luca Zancato 0.60 · backfill

Papers (24)

  1. Priming: Hybrid State Space Models From Pre-trained Transformers cs.LG · 2026 · author #6
  2. Learning When to Attend: Conditional Memory Access for Long-Context LLMs cs.CL · 2026 · author #3
  3. Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression cs.LG · 2025 · author #3
  4. Maximally-Informative Retrieval for State Space Model Generation cs.CL · 2025 · author #5
  5. PICASO: Permutation-Invariant Context Composition with State Space Models cs.CL · 2025 · author #5
  6. Descriminative-Generative Custom Tokens for Vision-Language Models cs.CV · 2025 · author #3
  7. Expansion Span: Combining Fading Memory and Retrieval in Hybrid State Space Models cs.CL · 2024 · author #2
  8. Marconi: Prefix Caching for the Era of Hybrid LLMs cs.DC · 2024 · author #5
  9. Long-context Protein Language Modeling Using Bidirectional Mamba with Shared Projection Layers q-bio.BM · 2024 · author #4
  10. Compositional Structures in Neural Embedding and Interaction Decompositions cs.LG · 2024 · author #4
  11. B'MOJO: Hybrid State Space Realizations of Foundation Models with Eidetic and Fading Memory cs.LG · 2024 · author #1
  12. CPR: Retrieval Augmented Generation for Copyright Protection cs.CR · 2024 · author #3
  13. Multi-Modal Hallucination Control by Visual Information Grounding cs.CV · 2024 · author #2
  14. SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes cs.CV · 2023 · author #3
  15. Meaning Representations from Trajectories in Autoregressive Models cs.CL · 2023 · author #5
  16. Prompt Algebra for Task Composition cs.CV · 2023 · author #3
  17. Leveraging sparse and shared feature activations for disentangled representation learning cs.LG · 2023 · author #3
  18. Train/Test-Time Adaptation with Retrieval cs.CV · 2023 · author #1
  19. Your representations are in the network: composable and parallel adaptation for large scale models cs.LG · 2023 · author #5
  20. Linear Spaces of Meanings: Compositional Structures in Vision-Language Models cs.LG · 2023 · author #3
  21. \`A-la-carte Prompt Tuning (APT): Combining Distinct Data Via Composable Prompting cs.LG · 2023 · author #3
  22. A novel Deep Neural Network architecture for non-linear system identification cs.LG · 2021 · author #1
  23. A linearized framework and a new benchmark for model selection for fine-tuning cs.CV · 2021 · author #5
  24. Predicting Training Time Without Training cs.LG · 2020 · author #1

Mentions

  • 2603.17484 #3 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2506.12149 #5 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2412.13328 #2 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2411.19379 #5 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2411.08909 #4 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2502.17605 #5 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2502.12095 #3 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2407.08934 #4 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2407.06324 #1 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2403.18920 #3 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2403.14003 #2 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2302.14383 #3 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2304.07939 #3 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2310.18348 #5 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2311.01646 #3 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2303.04105 #5 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2306.00310 #3 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2303.14333 #1 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2302.07994 #3 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2106.03078 #1 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2102.00084 #5 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2008.12478 #1 · arxiv_oai · confidence 0.70 Luca Zancato
  • 2511.21016 #3 · arxiv_oai · confidence 0.70 Luca Zancato

Frequent Coauthors