https://github.com/hrlics/lite
공식 코드LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
LITE: Modeling Environmental Ecosystems with Multimodal Large Language Models
Knowledge Graph Completion with Mixed Geometry Tensor Factorization
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
Automated Validation of Textual Constraints Against AutomationML via LLMs and SHACL
Measuring the Influence of Incorrect Code on Test Generation
Chat3GPP: An Open-Source Retrieval-Augmented Generation Framework for 3GPP Documents
Token-wise Influential Training Data Retrieval for Large Language Models
ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning
Removal of Hallucination on Hallucination: Debate-Augmented RAG
Fine-tune the Entire RAG Architecture (including DPR retriever) for Question-Answering
From Interests to Insights: An LLM Approach to Course Recommendations Using Natural Language Queries
Federated Recommendation via Hybrid Retrieval Augmented Generation
HumanOmniV2: From Understanding to Omni-Modal Reasoning with Context
Leveraging LLMs in Scholarly Knowledge Graph Question Answering
Cancer Vaccine Adjuvant Name Recognition from Biomedical Literature using Large Language Models
Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation
Less is More: Making Smaller Language Models Competent Subgraph Retrievers for Multi-hop KGQA
A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs
StoryTeller: Improving Long Video Description through Global Audio-Visual Character Identification
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Query2box: Reasoning over Knowledge Graphs in Vector Space using Box Embeddings
Multimodal Contrastive Representation Learning in Augmented Biomedical Knowledge Graphs
StarGraph: Knowledge Representation Learning based on Incomplete Two-hop Subgraph
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.