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/lliai/DisWOT-CVPR2023

공식 코드

DisWOT: Student Architecture Search for Distillation WithOut Training

https://github.com/llllly26/complexbench-edit

공식 코드

ComplexBench-Edit: Benchmarking Complex Instruction-Driven Image Editing via Compositional Dependencies

https://github.com/llm-eval-mental-health/counselbench

공식 코드

CounselBench: A Large-Scale Expert Evaluation and Adversarial Benchmark of Large Language Models in Mental Health Counseling

https://github.com/lloongx/diki

공식 코드

Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models

https://github.com/llyx97/Marginal-Utility-Diminishes

공식 코드

Marginal Utility Diminishes: Exploring the Minimum Knowledge for BERT Knowledge Distillation

https://github.com/llyx97/Rosita

공식 코드

ROSITA: Refined BERT cOmpreSsion with InTegrAted techniques

https://github.com/lmquan2000/mask-mixup

공식 코드

GUNNEL: Guided Mixup Augmentation and Multi-View Fusion for Aquatic Animal Segmentation

https://github.com/lnairgt/clip-distillation

공식 코드

CLIP-Embed-KD: Computationally Efficient Knowledge Distillation Using Embeddings as Teachers

https://github.com/lnsmith54/cfl

공식 코드

General Cyclical Training of Neural Networks

https://github.com/locuslab/open-unlearning

공식 코드

OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics

https://github.com/lofrienger/endodepthbenchmark

공식 코드

Benchmarking Robustness of Endoscopic Depth Estimation with Synthetically Corrupted Data

https://github.com/longkukuhi/lacvit

공식 코드

LaCViT: A Label-aware Contrastive Fine-tuning Framework for Vision Transformers

https://github.com/longman-stan/skindistilvit

공식 코드

SkinDistilViT: Lightweight Vision Transformer for Skin Lesion Classification

https://github.com/lookuz/vidhal

공식 코드

VidHal: Benchmarking Temporal Hallucinations in Vision LLMs

https://github.com/lordog/r-judge

공식 코드

R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

https://github.com/loreley99/syntheval_checklist

공식 코드

SYNTHEVAL: Hybrid Behavioral Testing of NLP Models with Synthetic CheckLists

https://github.com/lorjul/sgbench

공식 코드

A Review and Efficient Implementation of Scene Graph Generation Metrics

https://github.com/lostanlen/lostanlen2023waspaa

공식 코드

Fitting Auditory Filterbanks with Multiresolution Neural Networks

https://github.com/louisanity/cuphastlearn

공식 코드

Multi-GPU-Enabled Hybrid Quantum-Classical Workflow in Quantum-HPC Middleware: Applications in Quantum Simulations

https://github.com/lovelyqian/ME-D2N_for_CDFSL

공식 코드

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

https://github.com/lpd-epfl/byzfl

공식 코드

ByzFL: Research Framework for Robust Federated Learning

https://github.com/lsibabnikz/ai-kd

공식 코드

AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation

https://github.com/ltdung/snt-sentry

공식 코드

Semantic Knowledge Distillation for Onboard Satellite Earth Observation Image Classification

https://github.com/ltecot/rand_bench_opt_quantum

공식 코드

Randomized Benchmarking of Local Zeroth-Order Optimizers for Variational Quantum Systems

https://github.com/ltgoslo/noreval

공식 코드

NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmark

https://github.com/ltkong218/mdflow

공식 코드

MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation

https://github.com/lttm/cl-pcss

공식 코드

Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Data

https://github.com/lucagioacchini/auto-pen-bench

공식 코드

AutoPenBench: Benchmarking Generative Agents for Penetration Testing

https://github.com/lucagioacchini/genai-pentest-paper

공식 코드

AutoPenBench: Benchmarking Generative Agents for Penetration Testing

https://github.com/lucapodo/evallm

공식 코드

Vi(E)va LLM! A Conceptual Stack for Evaluating and Interpreting Generative AI-based Visualizations

https://github.com/lucianoavinas/lowrank-gnn-kernels

공식 코드

Simple GNNs with Low Rank Non-parametric Aggregators

https://github.com/lucius-lsr/nuteprune

공식 코드

NutePrune: Efficient Progressive Pruning with Numerous Teachers for Large Language Models

https://github.com/luciusssss/milic-eval

공식 코드

MiLiC-Eval: Benchmarking Multilingual LLMs for China's Minority Languages

https://github.com/luckyos-code/mia-covid

공식 코드

Privacy in Practice: Private COVID-19 Detection in X-Ray Images (Extended Version)

https://github.com/ludwig-ai/ludwig

공식 코드

Personalized Benchmarking with the Ludwig Benchmarking Toolkit

https://github.com/lufan31/comprecap

공식 코드

Benchmarking Large Vision-Language Models via Directed Scene Graph for Comprehensive Image Captioning

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