Alberto Cazzaniga
5 papers · 2023–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (3) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (14)
🗺️
Taxonomy Completionist
(10)
Conferences
ACL (2)
NIPS (2)
ICML (1)
Top co-authors
Keywords
representation learning
(2)
few-shot learning
(1)
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)
interpretability research
(1)
mechanism competition
(1)
logit inspection
(1)
attention modification
(1)
cross-modal conflict
(1)
layer analysis
(1)
large language model
(1)
knowledge conflict resolution
(1)
mechanism analysis
(1)
probability landscape
(1)
Papers
When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models
ACL 2026
Persistent Topological Features in Large Language Models
ICML 2025
The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models
NIPS 2024
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals
ACL 2024
The geometry of hidden representations of large transformer models
NIPS 2023