https://github.com/raymondhs/fairseq-extensible-mbart
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
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.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
High-Fidelity Pluralistic Image Completion with Transformers
Track2Vec: fairness music recommendation with a GPU-free customizable-driven framework
Another Diversity-Promoting Objective Function for Neural Dialogue Generation
Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective
AfriSenti: A Twitter Sentiment Analysis Benchmark for African Languages
MambaPupil: Bidirectional Selective Recurrent model for Event-based Eye tracking
CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery
An Axiomatic Analysis of Diversity Evaluation Metrics: Introducing the Rank-Biased Utility Metric
Generating and Adapting to Diverse Ad-Hoc Cooperation Agents in Hanabi
Bayesian Optimisation over Multiple Continuous and Categorical Inputs
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.