https://github.com/liamdugan/question_generation
Simplifying Paragraph-level Question Generation via Transformer 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.
Simplifying Paragraph-level Question Generation via Transformer Language Models
Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers
Learning Approximate Inference Networks for Structured Prediction
Learning Approximate Inference Networks for Structured Prediction
CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
Hungry Hungry Hippos: Towards Language Modeling with State Space Models
Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
Selecting Large Language Model to Fine-tune via Rectified Scaling Law
OneRef: Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling
HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training
Mixture-of-Agents Enhances Large Language Model Capabilities
Retentive Network: A Successor to Transformer for Large Language Models
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
DesCo: Learning Object Recognition with Rich Language Descriptions
Joint Source-Target Self Attention with Locality Constraints
Identifying Interpretable Subspaces in Image Representations
Language Model Council: Democratically Benchmarking Foundation Models on Highly Subjective Tasks
Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving
On the Cross-lingual Transferability of Monolingual Representations
CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.