← Application Areas

Machine Learning › Application Areas ›

Knowledge Distillation

2907 directly classified papers

Papers per year

Papers

IMKD: Intensity-Aware Multi-Level Knowledge Distillation for Camera-Radar Fusion WACV 2026

D2MoRA: Diversity-Regulated Asymmetric MoE-LoRA Decomposition for Efficient Multi-Task Adaptation AAAI 2026

CLIP-IT: CLIP-based Pairing of Histology Images with Privileged Textual Information WACV 2026

Distilling Offline Action Detection Models into Real-Time Streaming Models WACV 2026

Compensating Distribution Drifts in Continual Learning with Pre-trained Vision Transformers AAAI 2026

Credal Ensemble Distillation for Uncertainty Quantification AAAI 2026

M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data AAAI 2026

End-to-End Knowledge Distillation for Unsupervised Domain Adaptation with Large Vision-language Models AAAI 2026

Rethinking the Dark Knowledge and Kullback-Leibler Divergence Loss in Knowledge Distillation Under Capacity Mismatching AAAI 2026

DivControl: Knowledge Diversion for Controllable Image Generation AAAI 2026

Distilling Future Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection AAAI 2026

Grow-on-Demand: Sparse and Adaptive Expert Expansion for Continual Instruction Tuning AAAI 2026

Bi-Spectrum Distillation: Addressing Spectral Mismatch in ANN-SNN Knowledge Transfer AAAI 2026

Pareto-Based Heterogeneous Knowledge Distillation for MLPs on Graphs AAAI 2026

rMMEA: Robust Multi-Modal Entity Alignment with Missing and Noise Visual Modality AAAI 2026

TuckA: Hierarchical Compact Tensor Experts for Efficient Fine-Tuning AAAI 2026

Distilling Cross-Modal Knowledge via Feature Disentanglement AAAI 2026

OccamVTS: Distilling Vision Models to 1% Parameters for Time Series Forecasting AAAI 2026

Surrogate as Teacher: Distillation-Guided Graph Poisoning Attack AAAI 2026

EASE: Practical and Efficient Safety Alignment for Small Language Models AAAI 2026

No One-Size-Fits-All: Building Systems For Translation to Bashkir, Kazakh, Kyrgyz, Tatar and Chuvash Using Synthetic And Original Data EACL 2026

EM-KD: Distilling Efficient Multimodal Large Language Model with Unbalanced Vision Tokens AAAI 2026

Self-Correction Distillation for Structured Data Question Answering AAAI 2026

Hala Technical Report Building Arabic-Centric Instruction & Translation Models at Scale EACL 2026

DICE: Distilling Classifier-Free Guidance into Text Embeddings AAAI 2026