Change the repository type filter
All
Repositories list
94 repositories
predict-before-execute
PublicCan We Predict Before Executing Machine Learning Agents?SkillNet
PublicCreate, Evaluate, and Connect AI SkillsEasyEdit
Public[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.Chat2Workflow
PublicChat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural LanguageSkills
PublicInnoEval
PublicInnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning ProblemLightMem
Public[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generationbelief
PublicIllusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood ConsistencyData2Behavior
PublicFrom Data to Behavior: Predicting Unintended Model Behaviors Before TrainingMemP
PublicMemP: Exploring Agent Procedural MemoryDataMind
Public[ICLR/AAAI 2026] Open-Source LLM-Based Data Analysis AgentsWorldMind
PublicAligning Agentic World Models via Knowledgeable Experience Learningproject
PublicLLMAgentPapers
PublicMust-read Papers on LLM Agents.LookAheadTuning
Public[WSDM 2026] LookAhead Tuning: Safer Language Models via Partial Answer PreviewsKnowRL
PublicKnowRL: Exploring Knowledgeable Reinforcement Learning for FactualityCaKE
Public[EMNLP 2025] Circuit-Aware Editing Enables Generalizable Knowledge LearnersKnowledgeCircuits
Public[NeurIPS 2024] Knowledge Circuits in Pretrained TransformersKnowledge2Data
Public[TASLP 2025] Spatial Knowledge Graph-Guided Synthesis for Multimodal LLMsxKG
PublicExecutable Knowledge Graphs for Replicating AI ResearchAutoMind
PublicBiasEdit
Public[TrustNLP@NAACL 2025] BiasEdit: Debiasing Stereotyped Language Models via Model Editingunlearn
Public[ACL 2025] Knowledge Unlearning for Large Language ModelsDeco
Public[ICLR 2025] MLLM can see? Dynamic Correction Decoding for Hallucination MitigationChineseHarm-bench
PublicChineseHarm-Bench: A Chinese Harmful Content Detection BenchmarkOmniThink
Public[EMNLP 2025] OmniThink: Expanding Knowledge Boundaries in Machine Writing through ThinkingAutoSteer
Public[EMNLP 2025] AutoSteer: Automating Steering for Safe Multimodal Large Language ModelsOneKE
Public[WWW 2025] A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System.DeepKE
Public[EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and ConstructionDynamicKnowledgeCircuits
Public[ACL 2025] How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training