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/imics-lab/positional-encoding-benchmark
공식 코드Positional Encoding in Transformer-Based Time Series Models: A Survey
https://github.com/imirzadeh/Teacher-Assistant-Knowledge-Distillation
공식 코드https://github.com/iml-dkfz/fd-shifts
공식 코드A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
https://github.com/imnearth/autojudger
공식 코드AutoJudger: An Agent-Driven Framework for Efficient Benchmarking of MLLMs
https://github.com/imnotkind/HarmAug
공식 코드HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
https://github.com/impresso/paraphrasus
공식 코드PARAPHRASUS : A Comprehensive Benchmark for Evaluating Paraphrase Detection Models
https://github.com/imrl/gsb-vision-transformer
공식 코드GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples
https://github.com/indobenchmark/indonlu
공식 코드IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding
https://github.com/indyfree/CARLA
공식 코드CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
https://github.com/infiagent/infiagent
공식 코드https://github.com/infinigence/lveval
공식 코드LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K
https://github.com/inigoval/fixmatch
공식 코드https://github.com/ink7-sudo/dependeval
공식 코드DependEval: Benchmarking LLMs for Repository Dependency Understanding
https://github.com/inm-6/bennch
공식 코드A Modular Workflow for Performance Benchmarking of Neuronal Network Simulations
https://github.com/innodatalabs/innodata-llm-safety
공식 코드https://github.com/inouye-lab/feddg_benchmark
공식 코드https://github.com/inspirai/wilderness-scavenger
공식 코드WILD-SCAV: Benchmarking FPS Gaming AI on Unity3D-based Environments
https://github.com/instadeepai/compass
공식 코드Combinatorial Optimization with Policy Adaptation using Latent Space Search
https://github.com/instadeepai/debatellm
공식 코드Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
https://github.com/intel/intel-extension-for-transformers
공식 코드https://github.com/intell-sci-comput/opdf
공식 코드Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation
https://github.com/intellabs/multimodal_cognitive_ai
공식 코드NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge
https://github.com/intelligent-computing-lab-yale/quanitzation-aware-snn-training-and-hardware-evaluation-for-imc-architectures
공식 코드https://github.com/intelligent-computing-research-group/bkdsnn
공식 코드https://github.com/interaction-lab/hribench
공식 코드https://github.com/interactivenlp-team/rolellm-public
공식 코드RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models
https://github.com/intersun/CoDIR
공식 코드Contrastive Distillation on Intermediate Representations for Language Model Compression
https://github.com/intersun/PKD-for-BERT-Model-Compression
공식 코드https://github.com/intmegroup/lmm4lmm
공식 코드LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs
https://github.com/intmegroup/love
공식 코드LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation
https://github.com/iocuydi/amharic-llama-llava
공식 코드Amharic LLaMA and LLaVA: Multimodal LLMs for Low Resource Languages
https://github.com/ioverho/misinfo-general
공식 코드https://github.com/ipl-sharif/kd_survey
공식 코드https://github.com/ipolharvard/ethos-ares
공식 코드Foundation Model of Electronic Medical Records for Adaptive Risk Estimation
https://github.com/ipouyall/benchmarking_chatgpt_for_persian
공식 코드Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.