https://github.com/akakzia/decstr
공식 코드Grounding Language to Autonomously-Acquired Skills via Goal Generation
Papers with Code 아카이브
Diversity
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Diversity in data sampling is crucial across various use cases, including search, recommendation systems, and more. Ensuring diverse samples means capturing a wide range of variations and perspectives, which leads to more robust, unbiased, and comprehensive models. In search use cases, for instance, diversity helps avoid redundancy, ensuring that users are exposed to a broader set of relevant information rather than repeated similar results.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/akashsengupta1997/humaniflow
공식 코드https://github.com/akaxlh/mb-gmn
공식 코드https://github.com/akoksal/muri
공식 코드MURI: High-Quality Instruction Tuning Datasets for Low-Resource Languages via Reverse Instructions
https://github.com/alaleh/pdbo
공식 코드Pareto Front-Diverse Batch Multi-Objective Bayesian Optimization
https://github.com/alanlusun/openkd
공식 코드OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection
https://github.com/albietz/cb_bakeoff
공식 코드https://github.com/albu/albumentations
공식 코드https://github.com/aleju/gan-error-avoidance
공식 코드Learning to Avoid Errors in GANs by Manipulating Input Spaces
https://github.com/alelicciardi99/whalenet
공식 코드https://github.com/alexander-hagg/ExpressivityGECCO2021
공식 코드Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search
https://github.com/alexandervnikitin/tsgm
공식 코드TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series
https://github.com/alexandrosstergiou/Leaping-Into-Memories
공식 코드https://github.com/alexfanw/cochpl
공식 코드Chain-of-Choice Hierarchical Policy Learning for Conversational Recommendation
https://github.com/alexhernandezgarcia/co2ml
공식 코드Counting Carbon: A Survey of Factors Influencing the Emissions of Machine Learning
https://github.com/alexrame/diwa
공식 코드Diverse Weight Averaging for Out-of-Distribution Generalization
https://github.com/alexrame/rewardedsoups
공식 코드https://github.com/alexthebad/ap10k
공식 코드https://github.com/alexverine/pr-4-llm
공식 코드Exploring Precision and Recall to assess the quality and diversity of LLMs
https://github.com/alfredslapkovskis/multimodalplantclassifier
공식 코드Automatic Fused Multimodal Deep Learning for Plant Identification
https://github.com/algoprog/icat
공식 코드https://github.com/alibaba-damo-academy/3D-Speaker
공식 코드Pushing the limits of self-supervised speaker verification using regularized distillation framework
https://github.com/alibaba/MNN
공식 코드https://github.com/alibaba/cloudeval-yaml
공식 코드CloudEval-YAML: A Practical Benchmark for Cloud Configuration Generation
https://github.com/alibaba/eigenscore
공식 코드INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
https://github.com/alibabaresearch/damo-convai
공식 코드https://github.com/alihassanijr/DISCERN
공식 코드DISCERN: Diversity-based Selection of Centroids for k-Estimation and Rapid Non-stochastic Clustering
https://github.com/alinlab/M2m
공식 코드M2m: Imbalanced Classification via Major-to-minor Translation
https://github.com/alirezagharahi/d_SBRS
공식 코드https://github.com/alirezaghods/t2p-time-to-pattern
공식 코드Time-to-Pattern: Information-Theoretic Unsupervised Learning for Scalable Time Series Summarization
https://github.com/alisawuffles/wanli
공식 코드WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation
https://github.com/allenai/lila
공식 코드https://github.com/allenai/olmocr
공식 코드olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models
https://github.com/allenai/scirepeval
공식 코드SciRepEval: A Multi-Format Benchmark for Scientific Document Representations
https://github.com/allenai/specter2
공식 코드SciRepEval: A Multi-Format Benchmark for Scientific Document Representations
https://github.com/allenai/tailor
공식 코드Tailor: Generating and Perturbing Text with Semantic Controls
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.