https://github.com/thomassutter/mmvmvae
공식 코드Unity by Diversity: Improved Representation Learning in Multimodal VAEs
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/thomlake/investigating-alignment
공식 코드From Distributional to Overton Pluralism: Investigating Large Language Model Alignment
https://github.com/thompsonb/prism
공식 코드https://github.com/threestudio-project/threestudio
공식 코드ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation
https://github.com/thu-coai/miniplm
공식 코드MiniPLM: Knowledge Distillation for Pre-Training Language Models
https://github.com/thu-coai/tailr
공식 코드Tailoring Language Generation Models under Total Variation Distance
https://github.com/thu-cs-pi/mmpd_rppg_dataset
공식 코드https://github.com/thu-ml/diffusionbridge
공식 코드https://github.com/thu-ml/gft
공식 코드https://github.com/thudm/longalign
공식 코드LongAlign: A Recipe for Long Context Alignment of Large Language Models
https://github.com/thukelab/mixedit
공식 코드MixEdit: Revisiting Data Augmentation and Beyond for Grammatical Error Correction
https://github.com/thuml/CompilerDream
공식 코드CompilerDream: Learning a Compiler World Model for General Code Optimization
https://github.com/thuml/TrajWorld
공식 코드https://github.com/thuml/multi-embedding
공식 코드On the Embedding Collapse when Scaling up Recommendation Models
https://github.com/thuml/videodg
공식 코드VideoDG: Generalizing Temporal Relations in Videos to Novel Domains
https://github.com/thunlp/ultrachat
공식 코드Enhancing Chat Language Models by Scaling High-quality Instructional Conversations
https://github.com/thunlp/unifiedinstructiontuning
공식 코드https://github.com/tiancigao/diffppo
공식 코드https://github.com/tianhongdai/div-hindsight
공식 코드Diversity-based Trajectory and Goal Selection with Hindsight Experience Replay
https://github.com/tianyi-lab/mosaic-it
공식 코드Mosaic-IT: Free Compositional Data Augmentation Improves Instruction Tuning
https://github.com/tigerchen52/pearl
공식 코드Learning High-Quality and General-Purpose Phrase Representations
https://github.com/tigvarts/ucm
공식 코드https://github.com/tigvarts/vaeac
공식 코드https://github.com/timjaspers0801/surgenet
공식 코드Exploring the Effect of Dataset Diversity in Self-Supervised Learning for Surgical Computer Vision
https://github.com/tiosisai/bioac-active-learning-eusipco-2025
공식 코드Hybrid Disagreement-Diversity Active Learning for Bioacoustic Sound Event Detection
https://github.com/titubeta/EnsembleImputation
공식 코드Bootstrapping and Multiple Imputation Ensemble Approaches for Missing Data
https://github.com/tjubiit/TJU-DHD
공식 코드TJU-DHD: A Diverse High-Resolution Dataset for Object Detection
https://github.com/tjunlp-lab/cmoraleval
공식 코드CMoralEval: A Moral Evaluation Benchmark for Chinese Large Language Models
https://github.com/tjy1423317192/PLF
공식 코드Less is More: Pseudo-Label Filtering for Continual Test-Time Adaptation
https://github.com/tl-qz/trajdiffuse
공식 코드TrajDiffuse: A Conditional Diffusion Model for Environment-Aware Trajectory Prediction
https://github.com/toloka/u-math
공식 코드U-MATH: A University-Level Benchmark for Evaluating Mathematical Skills in LLMs
https://github.com/tom192180/Generate_then_Refine
공식 코드Generate then Refine: Data Augmentation for Zero-shot Intent Detection
https://github.com/tomasLiesting/HAABSADA
공식 코드Data Augmentation in a Hybrid Approach for Aspect-Based Sentiment Analysis
https://github.com/tomerwul/MegaSpeech
공식 코드Towards Hate Speech Detection at Large via Deep Generative Modeling
https://github.com/tomhosking/hrq-vae
공식 코드https://github.com/tomiinek/aargh
공식 코드AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.