Olivier Delalleau
7 papers · 2010–2025 · 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 ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (24) π Conference Polyglot Β· Silver π Academic Marathon Β· Full π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π±
Topic Pioneer
π
Keyword Champion
π§
Keyword Pioneer
π
Keyword Trendsetter Combo
(4)
π
Trend Setter
β
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(6)
Machine Learning
(6)
Core AI
(5)
Core Methods
(4)
Deep Learning
(3)
Natural Language Processing
(3)
Architectures
(2)
Learning Types
(2)
Optimization & Theory Β· Machine Learning
(2)
Application Areas
(1)
Applications
(1)
Bayesian & Probabilistic
(1)
Generation
(1)
Models
(1)
Optimization & Theory Β· Deep Learning
(1)
Keywords
language model
(3)
preference learning
(3)
model alignment
(2)
reward model
(2)
reward modeling
(2)
model editing
(1)
deep learning
(1)
reinforcement learning from human feedback
(1)
markov chain monte carlo
(1)
hidden layer
(1)
approximation error
(1)
representational power
(1)
bradley-terry model
(1)
human feedback
(1)
restricted boltzmann machine
(1)
open-ended task
(1)
supervised fine-tuning
(1)
tempered sampling
(1)
persistent contrastive divergence
(1)
alternating gibbs sampling
(1)
Papers
Diverging Preferences: When do Annotators Disagree and do Models Know?
ICML 2025
HelpSteer2-Preference: Complementing Ratings with Preferences
ICLR 2025
HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain Tasks
ACL 2025
HelpSteer 2: Open-source dataset for training top-performing reward models
NeurIPS 2024
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM
NAACL 2024
Shallow vs. Deep Sum-Product Networks
NeurIPS 2011
Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann Machines
AISTATS 2010