https://github.com/cloudcjf/ccl
공식 코드CCL: Continual Contrastive Learning for LiDAR Place Recognition
Papers with Code 아카이브
Knowledge Distillation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 11
- 보존된 평가 기록
- 90
Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/cloudy1225/hg2m
공식 코드https://github.com/clovaai/ECLIPSE
공식 코드ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning
https://github.com/clovaai/SSUL
공식 코드SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning
https://github.com/clovaai/attention-feature-distillation
공식 코드Show, Attend and Distill:Knowledge Distillation via Attention-based Feature Matching
https://github.com/clovaai/overhaul-distillation
공식 코드https://github.com/clovaai/textual-kd-slu
공식 코드Two-stage Textual Knowledge Distillation for End-to-End Spoken Language Understanding
https://github.com/clvoloshin/COBS
공식 코드Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
https://github.com/clvoloshin/OPE-tools
공식 코드Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
https://github.com/cmavro/grad
공식 코드Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs
https://github.com/cmrxrecon/cmrxrecon2024
공식 코드https://github.com/cnap/grammaticality-metrics
공식 코드There's No Comparison: Reference-less Evaluation Metrics in Grammatical Error Correction
https://github.com/codalab/codabench
공식 코드Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform
https://github.com/codalab/competitions-v2
공식 코드Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform
https://github.com/codectr/refinectr
공식 코드A Comprehensive Summarization and Evaluation of Feature Refinement Modules for CTR Prediction
https://github.com/codeeff/ecco
공식 코드ECCO: Can We Improve Model-Generated Code Efficiency Without Sacrificing Functional Correctness?
https://github.com/coder-jzq/radka-css
공식 코드Retrieval-Augmented Dialogue Knowledge Aggregation for Expressive Conversational Speech Synthesis
https://github.com/codereef-ai/client
공식 코드https://github.com/coderj-one/giraffe-bench
공식 코드Benchmarking Sequential Visual Input Reasoning and Prediction in Multimodal Large Language Models
https://github.com/codestar12/Parallel-Independent-Blockwise-Distillation
공식 코드Parallel Blockwise Knowledge Distillation for Deep Neural Network Compression
https://github.com/codestar12/pruning-distilation-bias
공식 코드Simon Says: Evaluating and Mitigating Bias in Pruned Neural Networks with Knowledge Distillation
https://github.com/cognaclee/dpm-ot
공식 코드DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport
https://github.com/cogsys-tuebingen/Distilling-Stereo-Networks
공식 코드Distilling Stereo Networks for Performant and Efficient Leaner Networks
https://github.com/coir-team/coir
공식 코드CoIR: A Comprehensive Benchmark for Code Information Retrieval Models
https://github.com/cola-laboratory/omnigenbench
공식 코드OmniGenBench: A Modular Platform for Reproducible Genomic Foundation Models Benchmarking
https://github.com/collinskatie/structured_flexible_and_robust
공식 코드https://github.com/columbia-icsl/tdbench
공식 코드TDBench: Benchmarking Vision-Language Models in Understanding Top-Down Images
https://github.com/commit-0/commit0
공식 코드https://github.com/compl-ai/compl-ai
공식 코드https://github.com/computationalprivacy/mia_llms_benchmark
공식 코드SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)
https://github.com/computernetworks-ufrgs/aedes_detector_smartphone_app_paper
공식 코드https://github.com/conglu1997/v-d4rl
공식 코드Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations
https://github.com/constraint-solvers/benchmark-corruptions
공식 코드Benchmarking Popular Classification Models' Robustness to Random and Targeted Corruptions
https://github.com/continual-nesy/LTLZinc
공식 코드A Neuro-Symbolic Framework for Sequence Classification with Relational and Temporal Knowledge
https://github.com/continual-nesy/kandybenchmark
공식 코드The KANDY Benchmark: Incremental Neuro-Symbolic Learning and Reasoning with Kandinsky Patterns
https://github.com/copenlu/scientific-exaggeration-detection
공식 코드Semi-Supervised Exaggeration Detection of Health Science Press Releases
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.