chandar-lab ORG

No description.

No description.

No description.

Recall to Imagine, a model-based RL algorithm with superhuman memory. Oral (1.2%) @ ICLR 2024

repository for training action-conditioned latent diffusion world models for robot video generation

No description.

Fine-Tuning Code Language Models for Text-Driven Sequential CAD Design

A Continual Multi-agent RL testbed based on Hanabi

IIRC: Incremental Implicitly Refined Classification

Code for the paper "NovoMolGen: Rethinking Molecular Language Model Pretraining"

No description.

No description.

A Gymnasium environment for generating crystalline materials.

Code for paper Sub-goal Distillation: A Method to Improve Small Language Agents, accepted at CoLLAs 2024.

No description.

No description.

No description.

No description.

Benchmark to evaluate the capability of language models to consolidate and recall information from multiple training documents.

Codebase for "A systematic analysis of machine learning pipelines for robust antimicrobial resistance prediction"

Streaming setup with representation learning for RL

Code for our world modeling workshop paper.

We study the effect of attention head pruning on fairness in large language models

Reinforcement Learning for Crystal Structure Design

Critical Gradient Optimization.

Reduce gender bias in machine learning models.

A toolkit for running text-generation-inference on Mila and Compute Canada

No description.

No description.

No description.

No description.

We explain why fairness metrics don't correlate and propose CAIRO to make them correlate.

No description.

Code for “Calibration Fine-Tuning”: training and evaluating language models as calibrated stochastic generators, with soft-target and hard-target fine-tuning methods and benchmarks beyond mathematical sampling.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

verl for RL exploration

The simplest, fastest repository for training/finetuning medium-sized GPTs.

No description.

Code to relax crystal structures in .cif format using parallel processing

No description.

Increasing Robustness to Spurious Correlations using Attention Regularization

Building modular LMs with parameter-efficient fine-tuning.

A fork of AMPLIFY for testing of new architectures for protein language modeling.

No description.

Implementation of Lookbehind-SAM: k steps back, 1 step forward (ICML 2024)

No description.

No description.