https://github.com/lishangyu-hkust/osvbench
공식 코드OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification
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/litesslhub/disco
공식 코드DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining
https://github.com/littlepenguin89106/mgcac
공식 코드A Recipe for CAC: Mosaic-based Generalized Loss for Improved Class-Agnostic Counting
https://github.com/liu-hy/genotex
공식 코드GenoTEX: An LLM Agent Benchmark for Automated Gene Expression Data Analysis
https://github.com/liu-yushan/PoLo
공식 코드Neural Multi-Hop Reasoning With Logical Rules on Biomedical Knowledge Graphs
https://github.com/liu00222/open-prompt-injection
공식 코드Formalizing and Benchmarking Prompt Injection Attacks and Defenses
https://github.com/liudan193/Fairness-Benchmark-for-Face-Forgery-Detection
공식 코드Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations
https://github.com/liugangcode/Llamole
공식 코드Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning
https://github.com/liuh127/FSCIL-via-Entropy-regularized-DF-Replay
공식 코드Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay
https://github.com/liujing1023/graph-based-knowledge-distillation
공식 코드Graph-based Knowledge Distillation: A survey and experimental evaluation
https://github.com/liukidar/pcax
공식 코드https://github.com/liuliuyuan6/POCL
공식 코드https://github.com/liuqidong07/leader-pytorch
공식 코드Large Language Model Distilling Medication Recommendation Model
https://github.com/liuvvvvv1/feddw
공식 코드FedDW: Distilling Weights through Consistency Optimization in Heterogeneous Federated Learning
https://github.com/liuxiaoxuanpku/osd
공식 코드https://github.com/liuxingbin/dbot
공식 코드https://github.com/liuxy1103/GIDBIS
공식 코드Graph Relation Distillation for Efficient Biomedical Instance Segmentation
https://github.com/liuxy1103/grdbis
공식 코드Graph Relation Distillation for Efficient Biomedical Instance Segmentation
https://github.com/liuyuaa/SurvUnc
공식 코드SurvUnc: A Meta-Model Based Uncertainty Quantification Framework for Survival Analysis
https://github.com/liuyugeng/ml-doctor
공식 코드ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
https://github.com/liuzey/CheckGPT
공식 코드https://github.com/liuzuxin/dsrl
공식 코드Datasets and Benchmarks for Offline Safe Reinforcement Learning
https://github.com/liuzuxin/fsrl
공식 코드Datasets and Benchmarks for Offline Safe Reinforcement Learning
https://github.com/liuzuxin/osrl
공식 코드Datasets and Benchmarks for Offline Safe Reinforcement Learning
https://github.com/livingingroups/animal2vec
공식 코드https://github.com/lize-alberts/llm_prag_benchmark
공식 코드CURATe: Benchmarking Personalised Alignment of Conversational AI Assistants
https://github.com/lizixing23/AMBOKD
공식 코드https://github.com/lizzyhku/TP
공식 코드Efficient Traffic Prediction Through Spatio-Temporal Distillation
https://github.com/ljcleo/agent_sense
공식 코드AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios
https://github.com/ljrprocc/datafree
공식 코드Dynamic Data-Free Knowledge Distillation by Easy-to-Hard Learning Strategy
https://github.com/ljungang/rtv-bench
공식 코드https://github.com/lkopf/cosy
공식 코드https://github.com/lkpengcs/rvms
공식 코드https://github.com/ll0ruc/AutoMIR
공식 코드AutoMIR: Effective Zero-Shot Medical Information Retrieval without Relevance Labels
https://github.com/ll0ruc/divsr
공식 코드Leave No One Behind: Enhancing Diversity While Maintaining Accuracy in Social Recommendation
https://github.com/llcresearch/genception
공식 코드GenCeption: Evaluate Multimodal LLMs with Unlabeled Unimodal Data
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.