Lists (3)
Starred repositories
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…
InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem
Can We Predict Before Executing Machine Learning Agents?
Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
From Data to Behavior: Predicting Unintended Model Behaviors Before Training
3
Updated Feb 4, 2026
Aligning Agentic World Models via Knowledgeable Experience Learning
POME: Post Optimization Model Edit via Muon-style Projection
Text2Mem: A Unified Memory Operation Language for Memory Operating System
An open-source, self-hosted note-taking service. Your thoughts, your data, your control — no tracking, no ads, no subscription fees.
A curated list of resources on Reinforcement Learning with Verifiable Rewards (RLVR) and the reasoning capability boundary of Large Language Models (LLMs).
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill memory for cross-task skill reuse and evolution.
OceanGym: A Benchmark Environment for Underwater Embodied Agents
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
[EMNLP 2025] AutoSteer: Automating Steering for Safe Multimodal Large Language Models
AutoMind: Adaptive Knowledgeable Agent for Automated Data Science
Context-Robust Knowledge Editing for Language Models (ACL 2025 Findings)
[ACL 2025] Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms
UltraEdit: Training-, Subject-, and Memory-Free Lifelong Editing in Large Language Models
[ICLR/AAAI 2026] Open-Source LLM-Based Data Analysis Agents
ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark
[AAAI 2026] ReCode: Reinforced Code Knowledge Editing for API Updates