This repository is the official code for the paper Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs (CVPR 2026).

An agentic skills framework & software development methodology that works.

Benchmarking Generalized Out-of-Distribution Detection

ECCV24, NeurIPS24, CVPR26*2, Benchmarking Generalized Out-of-Distribution Detection with Vision-Language Models

The source code for the paper "NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection", ICCV 2025.

Official PyTorch Code for Anchor Token Guided Prompt Learning Methods: [ICCV 2025] ATPrompt and [Arxiv 2511.21188] AnchorOPT

Fast Parallel Probabilistic Graphical Model Learning and Inference [IPDPS'22, PPoPP'23, USENIX ATC'24]

[FPGA 2020] A systematic framework for optimizing OpenCL applications on FPGAs

[CVPR 2024] Efficient Hyperparameter Optimization with Adaptive Fidelity Identification

[ACL 2026] Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

On-device AI financial coach for Android — powered by NexaSDK for 100% local LLM inference over your goals, income, investments, and expenses.

Sparse Adapter Fusion for Continual Learning in NLP - EACL 2026

ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing - ACL Findings 2026

Prototype Conditioned Generative Replay for Continual Learning in NLP - NAACL 2025

Real Data is not published, but code can be used if anyone need that. Please use the latest version V1.0.2.

大模型基础: 一文了解大模型基础知识

[TPAMI 2026] CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey.

[NeurIPS 2025] Official PyTorch Code for "Multi-Modal Interactive Agent Layer for Few-Shot Universal Cross-Domain Retrieval and Beyond"

[TCSVT 2024] Official PyTorch Code for "QAConv-MS: Multi-scale explicit matching and mutual subject teacher learning for generalizable person re-identification""

[AAAI2026] Official PyTorch Code for "Intra-Image Mining and Symmetric Maximum Concept Matching for Few Shot Out-of-Distribution Detection"

[ACM CSUR 2025] Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advances

Code for ICCV2025 paper: FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detection

(ACM MM 2025 Oral) Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detection

Parameter-Efficient Fine-Tuning for Foundation Models

Adaptation of vision-language models (CLIP) to downstream tasks using local and global prompts.

This project aims to collect the latest "call for reviewers" links from various top CS/ML/AI conferences/journals