- Montréal, Québec, Canada
- https://orcid.org/0000-0003-0475-1197
Highlights
- Pro
Stars
[ICLR 2025] BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
Asynchronous Distributed Hyperparameter Optimization.
Python Implementation of MUVERA (Multi-Vector Retrieval via Fixed Dimensional Encodings)
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
MTEB: Massive Text Embedding Benchmark
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
Retrieval and Retrieval-augmented LLMs
Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint
The fast python bm25 algorithm implemented with reverted index
Temperature Schedules for self-supervised contrastive methods on long-tail data (ICLR'23)
pfevaluator: A library for evaluating performance metrics of Pareto fronts in multiple/many objective optimization problems
Estimate/count FLOPS for a given neural network using pytorch
Tree edit distance using the Zhang Shasha algorithm
Code for the paper titled "Recursive Top-Down Production for Sentence Generation with Latent Trees"
Simple, Elegant, Typed Argument Parsing with argparse
Pytorch library for fast transformer implementations
Ladder Variational Autoencoders (LVAE) in PyTorch
Vector Quantized VAEs - PyTorch Implementation
PyTorch code to run synthetic experiments.
Pytorch implementation of Hyperspherical Variational Auto-Encoders
Simple language-driven navigation tasks for studying compositional learning
Compositional Obverter Communication Learning From Raw Visual Input - Pytorch Implementation