Papers with Code 아카이브
Concept Alignment
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Concept Alignment aims to align the learned representations or concepts within a model with the intended or target concepts. It involves adjusting the model's parameters or training process to ensure that the learned concepts accurately reflect the underlying patterns in the data.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/TalnUPF/ConceptExtraction
공식 코드https://github.com/The-FinAI/FinTagging
공식 코드FinTagging: An LLM-ready Benchmark for Extracting and Structuring Financial Information
https://github.com/aryan-jadon/synthetic-data-generation-and-evaluation-using-reasoning-models
공식 코드https://github.com/conceptbed/evaluations
공식 코드ConceptBed: Evaluating Concept Learning Abilities of Text-to-Image Diffusion Models
https://github.com/difeigu/radalign
공식 코드RadAlign: Advancing Radiology Report Generation with Vision-Language Concept Alignment
https://github.com/gpt4vision/OvSGTR
공식 코드https://github.com/nms05/improving-concept-alignment-in-vision-language-concept-bottleneck-models
공식 코드Improving Concept Alignment in Vision-Language Concept Bottleneck Models
https://github.com/roboflow/rf100-vl
공식 코드Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
https://github.com/seilna/CNN-Units-in-NLP
공식 코드Discovery of Natural Language Concepts in Individual Units of CNNs
https://github.com/superhero-7/altdiffuson
공식 코드https://github.com/sxjyjay/lumen
공식 코드Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models
https://github.com/thuan2412/joint-covariate-alignment-and-concept-alignment-for-domain-generalization
공식 코드Joint covariate-alignment and concept-alignment: a framework for domain generalization
https://github.com/tommy-bie/mica
공식 코드MICA: Towards Explainable Skin Lesion Diagnosis via Multi-Level Image-Concept Alignment
https://github.com/yaolinli/capenrich
공식 코드CapEnrich: Enriching Caption Semantics for Web Images via Cross-modal Pre-trained Knowledge
https://github.com/zchoi/glscl
공식 코드Text-Video Retrieval with Global-Local Semantic Consistent Learning
https://github.com/eclipse-t2i/lambda-eclipse-inference
https://github.com/sanchit97/secl
A Self-explaining Neural Architecture for Generalizable Concept Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.