Sébastien Lachapelle
14 papers · 2020–2026 · 6 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 ↓+5 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (26)
🧬
Topic Evolution
🗃️
Keyword Collector
(55)
💎
Century Club · Bronze
🔥
Unstoppable · Bronze
🚀
Conference Pioneer
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI
(10)
Machine Learning
(9)
Deep Learning
(5)
Core Methods
(5)
Learning Types · Machine Learning
(4)
Knowledge & Reasoning
(3)
Optimization & Theory
(3)
Reasoning
(3)
Learning Types · Deep Learning
(2)
Models
(2)
Data Science & Analytics
(1)
Mathematics & Optimization
(1)
Architectures
(1)
Learning Paradigms
(1)
Keywords
causal discovery
(6)
disentangled representation
(4)
representation learning
(3)
variational autoencoder
(3)
structure learning
(2)
independent component analysis
(2)
observational data
(2)
mechanism sparsity
(2)
causal graph
(2)
causal graphical model
(2)
directed acyclic graph
(2)
identifiability theory
(2)
sparse feature learning
(1)
compositional generalization
(1)
group lasso
(1)
continuous optimization
(1)
transfer learning
(1)
contrastive learning
(1)
language modeling
(1)
image generation
(1)
Papers
Learning a Spatial Partitioning and its Causal Relations from Temporal Data
CLeaR 2026
Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies
JMLR 2026
All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling
AISTATS 2025
Interaction Asymmetry: A General Principle for Learning Composable Abstractions
ICLR 2025
A Sparsity Principle for Partially Observable Causal Representation Learning
ICML 2024
Multi-View Causal Representation Learning with Partial Observability
ICLR 2024
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation
NeurIPS 2023
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
ICML 2023
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
CLeaR 2022
On the Convergence of Continuous Constrained Optimization for Structure Learning
AISTATS 2022
Typing assumptions improve identification in causal discovery
CLeaR 2022
A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
ICLR 2020
Differentiable Causal Discovery from Interventional Data
NeurIPS 2020
Gradient-Based Neural DAG Learning
ICLR 2020