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/nitishgupta/nmn-drop
공식 코드https://github.com/nivgold/dfpe
공식 코드DFPE: A Diverse Fingerprint Ensemble for Enhancing LLM Performance
https://github.com/niwanli/semifl_iot
공식 코드Semi-Federated Learning for Collaborative Intelligence in Massive IoT Networks
https://github.com/nju-websoft/KG2RAG
공식 코드https://github.com/njucckevin/ads-cap
공식 코드ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic Corpora
https://github.com/nlpcode/cbart
공식 코드Parallel Refinements for Lexically Constrained Text Generation with BART
https://github.com/nlpyang/geval
공식 코드G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment
https://github.com/nnnnai/ego4d_nlq_2022_1st_place_solution
공식 코드ReLER@ZJU-Alibaba Submission to the Ego4D Natural Language Queries Challenge 2022
https://github.com/noagarcia/explain-paintings
공식 코드Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation
https://github.com/noahstier/vortx
공식 코드VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion
https://github.com/nobuo-namura/mbo-epbii-srva
공식 코드https://github.com/nogu-atsu/small-dataset-image-generation
공식 코드Image Generation From Small Datasets via Batch Statistics Adaptation
https://github.com/norakassner/mlama
공식 코드Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models
https://github.com/norlab-ulaval/perceptreev1
공식 코드Training Deep Learning Algorithms on Synthetic Forest Images for Tree Detection
https://github.com/nouhadziri/DialogEntailment
공식 코드https://github.com/nrasajski/behave
공식 코드https://github.com/nrel/buildingsbench
공식 코드https://github.com/nrt2024/spidersim
공식 코드https://github.com/nschor/CompoNet
공식 코드CompoNet: Learning to Generate the Unseen by Part Synthesis and Composition
https://github.com/nttcslab/eval-audio-repr
공식 코드Towards Pre-training an Effective Respiratory Audio Foundation Model
https://github.com/ntunlplab/fecs
공식 코드https://github.com/nus-hpc-ai-lab/infogrowth
공식 코드https://github.com/nus-tim/dems
공식 코드https://github.com/nust-machine-intelligence-laboratory/anti-collapse-loss
공식 코드Anti-Collapse Loss for Deep Metric Learning Based on Coding Rate Metric
https://github.com/nust-machine-intelligence-laboratory/torchsemiseg2
공식 코드https://github.com/nuster1128/memsim
공식 코드MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
https://github.com/nv-tlabs/GET3D
공식 코드GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images
https://github.com/nvlabs/partpacker
공식 코드Efficient Part-level 3D Object Generation via Dual Volume Packing
https://github.com/nvlabs/protcomposer
공식 코드ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids
https://github.com/nvsclub/ensemblingneuralnetworks
공식 코드Towards a Systematic Approach to Design New Ensemble Learning Algorithms
https://github.com/nwbarendregt/SequentialRewardInfo
공식 코드Information-Seeking Decision Strategies Mitigate Risk in Dynamic, Uncertain Environments
https://github.com/nweir127/COD3S
공식 코드https://github.com/nxphi47/multiagent_crosstranslate
공식 코드Cross-model Back-translated Distillation for Unsupervised Machine Translation
https://github.com/nzilberstein/Repulsive-score-distillation-RSD-
공식 코드Repulsive Latent Score Distillation for Solving Inverse Problems
https://github.com/oaimli/hgsum
공식 코드Compressed Heterogeneous Graph for Abstractive Multi-Document Summarization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.