Papers with Code 아카이브

Knowledge Distillation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/zhangzef/ot-mel

공식 코드

Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking

https://github.com/zhangzjn/ader

공식 코드

A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection

https://github.com/zhanheshen/pointcmt

공식 코드

Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis

https://github.com/zhao-ht/biomaze

공식 코드

BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning

https://github.com/zhao-zy15/pmc-patients

공식 코드

PMC-Patients: A Large-scale Dataset of Patient Summaries and Relations for Benchmarking Retrieval-based Clinical Decision Support Systems

https://github.com/zhaoshan2/earthextreme-bench

공식 코드

ExEBench: Benchmarking Foundation Models on Extreme Earth Events

https://github.com/zhaoshiji123/absld

공식 코드

Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation

https://github.com/zhaoshiji123/mtard-extension

공식 코드

Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation

https://github.com/zhaoshuyuan0246/stkdrec

공식 코드

STKDRec: Spatial-Temporal Knowledge Distillation for Takeaway Recommendation

https://github.com/zhaowei-wang-nlp/divscene

공식 코드

DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects

https://github.com/zhaoyu-li/g4satbench

공식 코드

G4SATBench: Benchmarking and Advancing SAT Solving with Graph Neural Networks

https://github.com/zhchen18/tombench

공식 코드

ToMBench: Benchmarking Theory of Mind in Large Language Models

https://github.com/zhehengluoK/eval_empec

공식 코드

Are Large Language Models True Healthcare Jacks-of-All-Trades? Benchmarking Across Health Professions Beyond Physician Exams

https://github.com/zhen6618/obbinstancesegmentation

공식 코드

OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box Prompts

https://github.com/zhengli427/OKDHP

공식 코드

Online Knowledge Distillation for Efficient Pose Estimation

https://github.com/zhengli97/ctkd

공식 코드

Curriculum Temperature for Knowledge Distillation

https://github.com/zhengli97/dm-kd

공식 코드

Is Synthetic Data From Diffusion Models Ready for Knowledge Distillation?

https://github.com/zhengli97/promptkd

공식 코드

PromptKD: Unsupervised Prompt Distillation for Vision-Language Models

https://github.com/zhengyuan-jiang/videomarkbench

공식 코드

VideoMarkBench: Benchmarking Robustness of Video Watermarking

https://github.com/zhenwen-nlp/mathchat

공식 코드

MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions

https://github.com/zhenzhiwang/humanvid

공식 코드

HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation

https://github.com/zhichaoxu-shufe/rankmamba

공식 코드

RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers

https://github.com/zhichengg/stabletoolbench

공식 코드

StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models

https://github.com/zhihelu/ending_iss

공식 코드

Evolving Knowledge Mining for Class Incremental Segmentation

https://github.com/zhimin-c/bridge3d

공식 코드

Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models

https://github.com/zhiqiangzhongddu/llmamol

공식 코드

Benchmarking Large Language Models for Molecule Prediction Tasks

https://github.com/zhiqic/keyposs

공식 코드

KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration

https://github.com/zhonghuayi/optical_flow_robustness_benchmark

공식 코드

Benchmarking the Robustness of Optical Flow Estimation to Corruptions

https://github.com/zhongtiand/eqnn

공식 코드

$\mathbb{Z}_2\times \mathbb{Z}_2$ Equivariant Quantum Neural Networks: Benchmarking against Classical Neural Networks

https://github.com/zhou-hangyu/allclear

공식 코드

AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery

https://github.com/zhou-zoey/rmb-reward-model-benchmark

공식 코드

RMB: Comprehensively Benchmarking Reward Models in LLM Alignment

https://github.com/zhouchunpong/multi-view-3DGPR

공식 코드

Multi-View Fusion and Distillation for Subgrade Distresses Detection based on 3D-GPR

https://github.com/zhoujiahuan1991/aaai2025-lreid-dask

공식 코드

DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification

https://github.com/zhourobotics/llm-mrs-survey

공식 코드

Large Language Models for Multi-Robot Systems: A Survey

https://github.com/zhoutianxun/data_free_kd_regression

공식 코드

Synthetic data generation method for data-free knowledge distillation in regression neural networks

https://github.com/zhouweixiao/KGDS

공식 코드

What are they talking about? Benchmarking Large Language Models for Knowledge-Grounded Discussion Summarization

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.