Stars
Latent Adversarial Regularization for Offline Preference Optimization
Implementation of Paper: Latent Reasoning with Supervised Thinking States
Training Large Language Model to Reason in a Continuous Latent Space
A framework for few-shot evaluation of language models.
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations
Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
a Large-Scale Multi-Modal Dataset Containing 20 Million Descriptions
A fast + lightweight implementation of the GCG algorithm in PyTorch
Implementation of the 2023 CVPR Award Candidate: On Distillation of Guided Diffusion Models
[ICLR 2020] Code for paper "Robustness Verification for Transformers"
Towards Universal Certified Robustness with Multi-Norm Training
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
CVPR and NeurIPS poster examples and templates
Collection of advice for prospective and current PhD students
A curated list of Large Language Model (LLM) Interpretability resources.
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…
A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
Representation Engineering: A Top-Down Approach to AI Transparency
alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, 2024, 2025)
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Master Federated Learning in 2 Hours—Run It on Your PC!
Efficient and general syntactical decoding for Large Language Models
arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv