Emanuele Marconato
6 papers · 2022–2025 · 4 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
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
reasoning shortcut
(4)
concept learning
(3)
catastrophic forgetting
(1)
benchmark evaluation
(1)
language modeling
(1)
confidence calibration
(1)
disentangled representation
(1)
next-token prediction
(1)
systematic generalization
(1)
open-set recognition
(1)
linear representation
(1)
neuro-symbolic learning
(1)
identifiability theory
(1)
neuro-symbolic computing
(1)
disentangled representation learning
(1)
semantic ambiguity
(1)
neuro-symbolic model
(1)
neural network
(1)
concept-based model
(1)
concept rehearsal
(1)
Papers
All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling
AISTATS 2025
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
NeurIPS 2024
BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcuts
UAI 2024
Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
ICML 2023
Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts
NeurIPS 2023
GlanceNets: Interpretable, Leak-proof Concept-based Models
NeurIPS 2022