SOTAVerified

Knowledge Distillation

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 4240 papers

TitleStatusHype
Visual-Language Model Knowledge Distillation Method for Image Quality Assessment—0
Uncertainty-Aware Cross-Modal Knowledge Distillation with Prototype Learning for Multimodal Brain-Computer Interfaces—0
DVFL-Net: A Lightweight Distilled Video Focal Modulation Network for Spatio-Temporal Action RecognitionCode0
HanjaBridge: Resolving Semantic Ambiguity in Korean LLMs via Hanja-Augmented Pre-Training—0
Feature Distillation is the Better Choice for Model-Heterogeneous Federated Learning—0
SFedKD: Sequential Federated Learning with Discrepancy-Aware Multi-Teacher Knowledge Distillation—0
Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift—0
KAT-V1: Kwai-AutoThink Technical Report—0
The Trilemma of Truth in Large Language ModelsCode0
Layer Importance for Mathematical Reasoning is Forged in Pre-Training and Invariant after Post-Training—0
Distilling Normalizing Flows—0
G^2D: Boosting Multimodal Learning with Gradient-Guided DistillationCode0
Continual Self-Supervised Learning with Masked Autoencoders in Remote Sensing—0
Building Lightweight Semantic Segmentation Models for Aerial Images Using Dual Relation Distillation—0
Towards Scalable and Generalizable Earth Observation Data Mining via Foundation Model Composition—0
FedBKD: Distilled Federated Learning to Embrace Gerneralization and Personalization on Non-IID DataCode0
Tackling Data Heterogeneity in Federated Learning through Knowledge Distillation with Inequitable AggregationCode0
Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning—0
Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy—0
Distillation-Enabled Knowledge Alignment for Generative Semantic Communications in AIGC Provisioning Tasks—0
GNN's Uncertainty Quantification using Self-DistillationCode0
PicoSAM2: Low-Latency Segmentation In-Sensor for Edge Vision Applications—0
Efficient and Generalizable Speaker Diarization via Structured Pruning of Self-Supervised ModelsCode3
Multimodal Fusion SLAM with Fourier AttentionCode0
Enhancing Few-shot Keyword Spotting Performance through Pre-Trained Self-supervised Speech Models—0
Fine-grained Image Retrieval via Dual-Vision Adaptation—0
Knowledge Distillation Framework for Accelerating High-Accuracy Neural Network-Based Molecular Dynamics Simulations—0
Factorized RVQ-GAN For Disentangled Speech Tokenization—0
AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes—0
Model compression using knowledge distillation with integrated gradients—0
KDMOS:Knowledge Distillation for Motion SegmentationCode0
Lightweight Task-Oriented Semantic Communication Empowered by Large-Scale AI Models—0
SeqPE: Transformer with Sequential Position EncodingCode1
HKD4VLM: A Progressive Hybrid Knowledge Distillation Framework for Robust Multimodal Hallucination and Factuality Detection in VLMs—0
A Technical Study into Small Reasoning Language Models—0
Ground Reaction Force Estimation via Time-aware Knowledge Distillation—0
A Novel Lightweight Transformer with Edge-Aware Fusion for Remote Sensing Image Captioning—0
Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion RecognitionCode0
SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM ReasoningCode1
Towards Class-wise Fair Adversarial Training via Anti-Bias Soft Label DistillationCode0
Label-Context-Dependent Internal Language Model Estimation for CTC—0
Being Strong Progressively! Enhancing Knowledge Distillation of Large Language Models through a Curriculum Learning FrameworkCode0
StatsMerging: Statistics-Guided Model Merging via Task-Specific Teacher DistillationCode0
Static Word Embeddings for Sentence Semantic Representation—0
hdl2v: A Code Translation Dataset for Enhanced LLM Verilog Generation—0
Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement—0
QA-HFL: Quality-Aware Hierarchical Federated Learning for Resource-Constrained Mobile Devices with Heterogeneous Image Quality—0
Building a Few-Shot Cross-Domain Multilingual NLU Model for Customer Care—0
TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models—0
KDRL: Post-Training Reasoning LLMs via Unified Knowledge Distillation and Reinforcement Learning—0
Show:102550
← PrevPage 1 of 85Next →
All datasetsImageNetCIFAR-100COCO (Common Objects in Context)COCO 2017 valPASCAL VOCKITTI

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ScaleKD (T:BEiT-L S:ViT-B/14)Top-1 accuracy %86.43—Unverified
2ScaleKD (T:Swin-L S:ViT-B/16)Top-1 accuracy %85.53—Unverified
3ScaleKD (T:Swin-L S:ViT-S/16)Top-1 accuracy %83.93—Unverified
4ScaleKD (T:Swin-L S:Swin-T)Top-1 accuracy %83.8—Unverified
5KD++(T: regnety-16GF S:ViT-B)Top-1 accuracy %83.6—Unverified
6VkD (T:RegNety 160 S:DeiT-S)Top-1 accuracy %82.9—Unverified
7SpectralKD (T:Swin-S S:Swin-T)Top-1 accuracy %82.7—Unverified
8ScaleKD (T:Swin-L S:ResNet-50)Top-1 accuracy %82.55—Unverified
9DiffKD (T:Swin-L S: Swin-T)Top-1 accuracy %82.5—Unverified
10DIST (T: Swin-L S: Swin-T)Top-1 accuracy %82.3—Unverified
#ModelMetricClaimedVerifiedStatus
1SRD (T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)79.86—Unverified
2shufflenet-v2(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)78.76—Unverified
3MV-MR (T: CLIP/ViT-B-16 S: resnet50)Top-1 Accuracy (%)78.6—Unverified
4resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)78.28—Unverified
5resnet8x4 (T: resnet32x4 S: resnet8x4 [modified])Top-1 Accuracy (%)78.08—Unverified
6ReviewKD++(T:resnet-32x4, S:shufflenet-v2)Top-1 Accuracy (%)77.93—Unverified
7ReviewKD++(T:resnet-32x4, S:shufflenet-v1)Top-1 Accuracy (%)77.68—Unverified
8resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)77.5—Unverified
9resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.68—Unverified
10resnet8x4 (T: resnet32x4 S: resnet8x4)Top-1 Accuracy (%)76.31—Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP77.16—Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP73.73—Unverified
3ADLIK-Faster (T: Faster R-CNN vit-base S: Faster R-CNN deit-small) box AP47.6—Unverified
4ADLIK-Mask (T: Mask R-CNN vit-base S: Mask R-CNN deit-small)mask AP42.4—Unverified
#ModelMetricClaimedVerifiedStatus
1ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(resnet50))AP@0.561.8—Unverified
2ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(resnet18))AP@0.557.96—Unverified
3ReviewKD++(T: faster rcnn(resnet101), S:faster rcnn(mobilenet-v2))AP@0.555.18—Unverified
#ModelMetricClaimedVerifiedStatus
1LSHFM (T: ResNet101 S: ResNet50)mAP93.17—Unverified
2LSHFM (T: ResNet101 S: MobileNetV2)mAP90.14—Unverified
#ModelMetricClaimedVerifiedStatus
1TIE-KD (T: Adabins S: MobileNetV2)RMSE2.43—Unverified