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/corentin-ryr/multimedeval

공식 코드

MultiMedEval: A Benchmark and a Toolkit for Evaluating Medical Vision-Language Models

https://github.com/corl-team/CORL

공식 코드

CORL: Research-oriented Deep Offline Reinforcement Learning Library

https://github.com/corsteging/parameterizedargumentationbasedreasoningtasks

공식 코드

Parameterized Argumentation-based Reasoning Tasks for Benchmarking Generative Language Models

https://github.com/cosmoimd/deeplearningexamples

공식 코드

REAL-Colon: A dataset for developing real-world AI applications in colonoscopy

https://github.com/cosmoimd/real-colon-dataset

공식 코드

REAL-Colon: A dataset for developing real-world AI applications in colonoscopy

https://github.com/craftjarvis/mcu

공식 코드

Towards Evaluating Generalist Agents: An Automated Benchmark in Open World

https://github.com/cranken/cpd

공식 코드

Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression

https://github.com/craston/object_detection_cib

공식 코드

Class Imbalance in Object Detection: An Experimental Diagnosis and Study of Mitigation Strategies

https://github.com/cripac-dig/balanced-multimodal-rec

공식 코드

Modality-Balanced Learning for Multimedia Recommendation

https://github.com/crisisltlsum/crisistimelines

공식 코드

CrisisLTLSum: A Benchmark for Local Crisis Event Timeline Extraction and Summarization

https://github.com/crispianm/st-mfnet-mini

공식 코드

ST-MFNet Mini: Knowledge Distillation-Driven Frame Interpolation

https://github.com/crosszamirski/ws-dino

공식 코드

Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels

https://github.com/crowdbotp/OpenTraj

공식 코드

OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets

https://github.com/cruiseresearchgroup/dief_bts

공식 코드

BTS: Building Timeseries Dataset: Empowering Large-Scale Building Analytics

https://github.com/cruiseresearchgroup/massive-steps

공식 코드

Massive-STEPS: Massive Semantic Trajectories for Understanding POI Check-ins -- Dataset and Benchmarks

https://github.com/crusnic-corp/BN-AuthProf

공식 코드

BN-AuthProf: Benchmarking Machine Learning for Bangla Author Profiling on Social Media Texts

https://github.com/crystalsixone/vln-magic

공식 코드

MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation

https://github.com/csebuetnlp/BanglaSocialBias

공식 코드

Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias

https://github.com/cseeyangchen/c2vl

공식 코드

Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning

https://github.com/csguoh/kd-ltr

공식 코드

One-stage Low-resolution Text Recognition with High-resolution Knowledge Transfer

https://github.com/cshaitao/lexrag

공식 코드

LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation

https://github.com/csiro-robotics/sdcl

공식 코드

Subspace Distillation for Continual Learning

https://github.com/csu-jpg/v-mage

공식 코드

V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models

https://github.com/csu-signal/llama_cdcr

공식 코드

Okay, Let's Do This! Modeling Event Coreference with Generated Rationales and Knowledge Distillation

https://github.com/ctplab/iid_representation_learning

공식 코드

Towards IID representation learning and its application on biomedical data

https://github.com/ctrl-gaurav/llmthinkbench

공식 코드

LLMThinkBench: Towards Basic Math Reasoning and Overthinking in Large Language Models

https://github.com/ctuning/cbench

공식 코드

The Collective Knowledge project: making ML models more portable and reproducible with open APIs, reusable best practices and MLOps

https://github.com/ctuning/ck

공식 코드

Collective Knowledge: organizing research projects as a database of reusable components and portable workflows with common APIs

https://github.com/cty1934/efsa

공식 코드

EFSA: Towards Event-Level Financial Sentiment Analysis

https://github.com/cubenlp/BIBench

공식 코드

FinDABench: Benchmarking Financial Data Analysis Ability of Large Language Models

https://github.com/cuhk-arise/psychobench

공식 코드

Who is ChatGPT? Benchmarking LLMs' Psychological Portrayal Using PsychoBench

https://github.com/cuibaby/dpk

공식 코드

Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation

https://github.com/cuong-pv/FAM-KD

공식 코드

Frequency Attention for Knowledge Distillation

https://github.com/currentf/lowrankclone

공식 코드

A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone

https://github.com/curryyuan/x-trans2cap

공식 코드

X-Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning

https://github.com/cvblab/AI4SkIN_leaderboard

공식 코드

Benchmarking histopathology foundation models in a multi-center dataset for skin cancer subtyping

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