https://github.com/chrismcclurg/fscil-acs
공식 코드Active Class Selection for Few-Shot Class-Incremental Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Active Class Selection for Few-Shot Class-Incremental Learning
Dynamic Network Reconfiguration for Entropy Maximization using Deep Reinforcement Learning
Explicit Planning Helps Language Models in Logical Reasoning
Explicit Planning Helps Language Models in Logical Reasoning
Personalized Federated Learning via Feature Distribution Adaptation
IGDrivSim: A Benchmark for the Imitation Gap in Autonomous Driving
Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation
Learning to Track Dynamic Targets in Partially Known Environments
Evaluating Language Models for Mathematics through Interactions
SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation
PoxVerifi: An Information Verification System to Combat Monkeypox Misinformation
Informative Language Representation Learning for Massively Multilingual Neural Machine Translation
Demo Abstract: Real-Time Out-of-Distribution Detection on a Mobile Robot
Leveraging Language Foundation Models for Human Mobility Forecasting
Learning from Unlabeled 3D Environments for Vision-and-Language Navigation
Navigating the Fragrance space Via Graph Generative Models And Predicting Odors
L3DMC: Lifelong Learning using Distillation via Mixed-Curvature Space
Natural Language Inference in Context -- Investigating Contextual Reasoning over Long Texts
GLoRE: Evaluating Logical Reasoning of Large Language Models
Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4
Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects
A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
Neuro-Symbolic Integration Brings Causal and Reliable Reasoning Proofs
Unlocking Temporal Question Answering for Large Language Models with Tailor-Made Reasoning Logic
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.