ADP is an intelligent data platform that bridges the gap between heterogeneous data sources and AI agents. It abstracts data complexity through business knowledge networks, provides unified data ac…

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技能生态

Awesome Remote Sensing Vision-Language Datasets

The official implementation of the paper: H-Neurons: On the Existence, Impact, and Origin of Hallucination-Associated Neurons in LLMs

Official Implementation of MetaDefense (NeurIPS 2025)

[ACL 2025 Findings] Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models

Accepted to ACL'25 (main)

Fine-Grained Detoxification via Instance-Level Prefixes for Large Language Models (accepted by Nurocomputing)

[ACL 2025 Main] Code and data for paper "Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation?"

A list of recent papers about adversarial learning

A curated list of safety-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights i…

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

This is the official code for the paper "Vaccine: Perturbation-aware Alignment for Large Language Models" (NeurIPS2024)

Code for paper "Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion"

Curated list of datasets and tools for post-training.

Restore safety in fine-tuned language models through task arithmetic

记录个人的学习历程。包括但不限于算法、机器学习、论文写作等。

Code for "Goodtriever: Toxicity Mitigation with Retrieval-augmented Language Models"

NLP deep learning model for multilingual toxicity detection in text 📚

Paper list about multimodal and large language models, only used to record papers I read in the daily arxiv for personal needs.

This is a code repository for PaCo (Preconditions Attributed to Commonsense Knowledge) @EMNLP-Findings 2022

Repo for outstanding paper@ACL 2023 "Do PLMs Know and Understand Ontological Knowledge?"

[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition

This code accompanies the paper DisentQA: Disentangling Parametric and Contextual Knowledge with Counterfactual Question Answering.