https://github.com/axiomlab/Cable
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
Muse: Text-To-Image Generation via Masked Generative Transformers
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
LADDER: Language Driven Slice Discovery and Error Rectification
EL Embeddings: Geometric construction of models for the Description Logic EL ++
Investigating Pretrained Language Models for Graph-to-Text Generation
In Search of Needles in a 11M Haystack: Recurrent Memory Finds What LLMs Miss
Decomposed Prompting to Answer Questions on a Course Discussion Board
Benchmarking and Explaining Large Language Model-based Code Generation: A Causality-Centric Approach
Learning Sequence Encoders for Temporal Knowledge Graph Completion
GraphTeam: Facilitating Large Language Model-based Graph Analysis via Multi-Agent Collaboration
MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
The Geometry of Categorical and Hierarchical Concepts in Large Language Models
Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
Quest: Query-centric Data Synthesis Approach for Long-context Scaling of Large Language Model
Ragnarök: A Reusable RAG Framework and Baselines for TREC 2024 Retrieval-Augmented Generation Track
AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection
Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes
Open Graph Benchmark: Datasets for Machine Learning on Graphs
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.