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/nomiaro/OPA

공식 코드

Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection

https://github.com/nomothings/charge

공식 코드

Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework

https://github.com/northsummer/lgkd

공식 코드

BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detection

https://github.com/novasearch-team/rag-retrieval

공식 코드

Benchmarking the Myopic Trap: Positional Bias in Information Retrieval

https://github.com/novelqa/novelqa.github.io

공식 코드

NovelQA: Benchmarking Question Answering on Documents Exceeding 200K Tokens

https://github.com/novicefodder/os-medseg

공식 코드

Distillation Learning Guided by Image Reconstruction for One-Shot Medical Image Segmentation

https://github.com/noy-sternlicht/debatable-intelligence

공식 코드

Debatable Intelligence: Benchmarking LLM Judges via Debate Speech Evaluation

https://github.com/nphdang/fs-bbt

공식 코드

Black-box Few-shot Knowledge Distillation

https://github.com/nrehush/minknet-tree-species

공식 코드

Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset

https://github.com/ntaylorox/public_clinical_prompt

공식 코드

Clinical Prompt Learning with Frozen Language Models

https://github.com/nttcslab/m2d

공식 코드

Masked Modeling Duo for Speech: Specializing General-Purpose Audio Representation to Speech using Denoising Distillation

https://github.com/nttmdlab-nlp/ToMATO

공식 코드

ToMATO: Verbalizing the Mental States of Role-Playing LLMs for Benchmarking Theory of Mind

https://github.com/ntu-icg/fm-planner

공식 코드

FM-Planner: Foundation Model Guided Path Planning for Autonomous Drone Navigation

https://github.com/nubagcilab/cirrmri600plus

공식 코드

Large Scale MRI Collection and Segmentation of Cirrhotic Liver

https://github.com/nubagcilab/pansegnet

공식 코드

Large-Scale Multi-Center CT and MRI Segmentation of Pancreas with Deep Learning

https://github.com/nubot-nudt/tscm

공식 코드

TSCM: A Teacher-Student Model for Vision Place Recognition Using Cross-Metric Knowledge Distillation

https://github.com/numbbo/coco

공식 코드

COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting

https://github.com/numone01/categorizer

공식 코드

Proxy-Anchor and EVT-Driven Continual Learning Method for Generalized Category Discovery

https://github.com/nuprl/multipl-e

공식 코드

MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation

https://github.com/nvidia/nvflare

공식 코드

ConDistFL: Conditional Distillation for Federated Learning from Partially Annotated Data

https://github.com/nvlabs/bongard-hoi

공식 코드

Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions

https://github.com/nvlabs/hydra-mdp

공식 코드

Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation

https://github.com/nvlabs/minitron

공식 코드

Compact Language Models via Pruning and Knowledge Distillation

https://github.com/nvlabs/nprach_synch

공식 코드

Deep Learning-Based Synchronization for Uplink NB-IoT

https://github.com/nvlabs/perada

공식 코드

PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees

https://github.com/nvlabs/radio

공식 코드

AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One

https://github.com/nvlabs/verilog-eval

공식 코드

VerilogEval: Evaluating Large Language Models for Verilog Code Generation

https://github.com/nxphi47/data_diversification

공식 코드

Data Diversification: A Simple Strategy For Neural Machine Translation

https://github.com/nyu-mlda/openabc

공식 코드

OpenABC-D: A Large-Scale Dataset For Machine Learning Guided Integrated Circuit Synthesis

https://github.com/nyuad-cai/medarabiq

공식 코드

MedArabiQ: Benchmarking Large Language Models on Arabic Medical Tasks

https://github.com/oatmealliu/class-incd

공식 코드

Class-incremental Novel Class Discovery

https://github.com/odabashi/LMs-in-News-Summarization

공식 코드

Unraveling the Capabilities of Language Models in News Summarization

https://github.com/oetu/otis

공식 코드

Towards Generalisable Time Series Understanding Across Domains

https://github.com/ofa-sys/air-bench

공식 코드

AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension

https://github.com/offdynamicsrl/off-dynamics-rl

공식 코드

ODRL: A Benchmark for Off-Dynamics Reinforcement Learning

https://github.com/oleksost/latent_cl

공식 코드

Continual Learning with Foundation Models: An Empirical Study of Latent Replay

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