Alberto Cazzaniga

5 papers · 2023–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ACL (2) NeurIPS (2) ICML (1)

Top co-authors

Diego Doimo (4) Alessio Ansuini (3) Zhijing Jin (2) Francesco Ortu (2) Giada Panerai (1) Bernhard Schölkopf (1) Alessandro Laio (1) Mrinmaya Sachan (1) Alessandro Serra (1) Matteo Biagetti (1)

Research topics

Artificial Intelligence (4) Machine Learning (3) Core AI (3) Core Methods (3) Deep Learning (2) Natural Language Processing (2) Models (2) Resources & Methods (2) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Optimization & Theory (1)

Keywords

large language model (2) representation learning (2) in-context learning (1) semantic analysis (1) factual knowledge (1) intrinsic dimension (1) semantic information (1) language model (1) supervised fine-tuning (1) hidden representation (1) representation space (1) topological feature (1) layer pruning (1) interpretability research (1) mechanism competition (1) logit inspection (1) attention modification (1) cross-modal conflict (1) layer analysis (1) knowledge conflict resolution (1)

Papers

When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models ACL 2026 Persistent Topological Features in Large Language Models ICML 2025 Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals ACL 2024 The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models NeurIPS 2024 The geometry of hidden representations of large transformer models NeurIPS 2023