[Neurips 2025] Code and experiments for the NeurIPS 2025 paper Mysteries of the Deep, studying how intermediate representations in CLIP, ViT, and SigLIP enable more robust zero-shot OOD detection across datasets.

Code accompanying the WACV 2026 paper "ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora"

accepted at ICMLw '24

Realisitic Out-of-Distribution (OOD) Detection

This is the code repository for the 3D Semantic Novelty Detection via Large-Scale Pre-Trained Models

💠 Essential object oriented design (python, pytest, travisCI)

[ICLR 2024 Spotlight] "Negative Label Guided OOD Detection with Pretrained Vision-Language Models"

(alpha) Web Browser written in Python

A similar game to "Plants Vs. Zombies"

This was the final project for CS5001 (Intensive Foundations in Computer Science) at Northeastern University.

Ten projects on Object Oriented Design in Python.

01076109 Object Oriented Data Structures

We leverage 14 datasets as OOD test data and conduct evaluations on 8 NLU tasks over 21 popularly used models. Our findings confirm that the OOD accuracy in NLP tasks needs to be paid more attention to since the significant performance decay compared to ID accuracy has been found in all settings.

Code for the Paper "A Functional Data Perspective and Baseline on Multi-Layer Out-of-Distribution Detection"

Repository for the paper "Perception Datasets for Anomaly Detection in Autonomous Driving: A Survey"

[ICML 2023] "Unleashing Mask: Explore the Intrinsic Out-of-Distribution Detection Capability"

OOD-CV dataset and data preprocessing tools

Implement the OOD milestone papers with pyotorch template style

[ECCV 2022] Multi-Domain Long-Tailed Recognition, Imbalanced Domain Generalization, and Beyond