https://github.com/nec-research/agentquest
공식 코드AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents
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/neclow/serab
공식 코드SERAB: A multi-lingual benchmark for speech emotion recognition
https://github.com/neeleshg23/packd
공식 코드PaCKD: Pattern-Clustered Knowledge Distillation for Compressing Memory Access Prediction Models
https://github.com/neergaard/deep-sleep-pytorch
공식 코드Automatic sleep stage classification with deep residual networks in a mixed-cohort setting
https://github.com/neheller/kits19
공식 코드https://github.com/nengo/nengo-dl
공식 코드NengoDL: Combining deep learning and neuromorphic modelling methods
https://github.com/neon-jing/guider
공식 코드https://github.com/nerses28/bBSARD
공식 코드Bilingual BSARD: Extending Statutory Article Retrieval to Dutch
https://github.com/nervjack2/speech-ssl-compression
공식 코드Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers
https://github.com/nesl/llm_sensor_processing
공식 코드SensorBench: Benchmarking LLMs in Coding-Based Sensor Processing
https://github.com/nesl/stark_benchmark
공식 코드Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges
https://github.com/networkgeometry/hyperbolic-benchmark-gnn
공식 코드Hyperbolic Benchmarking Unveils Network Topology-Feature Relationship in GNN Performance
https://github.com/neuir/m2rag
공식 코드Benchmarking Retrieval-Augmented Generation in Multi-Modal Contexts
https://github.com/neulab/prompt2model
공식 코드Prompt2Model: Generating Deployable Models from Natural Language Instructions
https://github.com/neurobench/neurobench
공식 코드NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems
https://github.com/neurocomplab-psu/spikingbert
공식 코드SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation
https://github.com/neuroevobench/neuroevobench
공식 코드NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications
https://github.com/neurosim/DNN_NeuroSim_V2.0
공식 코드https://github.com/neuspeech/eeg-to-text
공식 코드https://github.com/newbeeyoung/video-corruption-robustness
공식 코드Benchmarking the Robustness of Spatial-Temporal Models Against Corruptions
https://github.com/nexaai/awesome-llms-on-device
공식 코드https://github.com/nfyfamr/mf-nerf
공식 코드MF-NeRF: Memory Efficient NeRF with Mixed-Feature Hash Table
https://github.com/nguyentthong/CrossSummOptimalTransport
공식 코드https://github.com/nhathoang2002/toxcl
공식 코드ToXCL: A Unified Framework for Toxic Speech Detection and Explanation
https://github.com/nheist/caligraph-for-semrec
공식 코드https://github.com/nice-x/dfgc-2022
공식 코드https://github.com/nicola-bastianello/tvopt
공식 코드https://github.com/nicolas-bzrd/llm-recipes
공식 코드Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs
https://github.com/nicolas-hbt/pygraft
공식 코드PyGraft: Configurable Generation of Synthetic Schemas and Knowledge Graphs at Your Fingertips
https://github.com/nicolas1203/mkd_ocl
공식 코드Rethinking Momentum Knowledge Distillation in Online Continual Learning
https://github.com/nicolemeister/benchmarking-distributional-alignment
공식 코드Benchmarking Distributional Alignment of Large Language Models
https://github.com/nicomeyer96/qrl-benchmark
공식 코드https://github.com/nii-yamagishilab/xfever
공식 코드https://github.com/nikhil-garg/EMG_exp
공식 코드Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition
https://github.com/niklasrisse/usenix_2024
공식 코드Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection
https://github.com/niklasrisse/vpp
공식 코드Uncovering the Limits of Machine Learning for Automatic Vulnerability Detection
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.