I am PhD student @ Mila-Quebec working with Laurent Charlin. Currently interested in how we can use active human feedback to improve machine learning models.
Highlights
- Pro
-
tau-bench Public
Forked from Vattikondadheeraj/tau-benchCode and Data for Tau-Bench
Python MIT License UpdatedSep 6, 2025 -
-
-
-
direct-preference-optimization Public
Forked from eric-mitchell/direct-preference-optimizationReference implementation for DPO (Direct Preference Optimization)
-
RLPHF Public
Forked from joeljang/RLPHFPersonalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
Python UpdatedJun 23, 2024 -
-
-
-
-
-
-
Epiclomal Public
Forked from molonc/EpiclomalEpiclomal package, software for clustering of sparse DNA methylation data
R UpdatedMay 13, 2022 -
end-to-end-negotiator Public
Forked from anthonyprinaldi/end-to-end-negotiatorDeal or No Deal? End-to-End Learning for Negotiation Dialogues
-
-
hal9ai Public
Forked from hal9ai/hal9Web-First Composable Data Pipelines
JavaScript MIT License UpdatedFeb 28, 2022 -
-
-
-
-