← Techniques
Deep Learning › Techniques ›

Knowledge Distillation

623 directly classified papers

Papers per year

Papers

ResidualViT for Efficient Temporally Dense Video Encoding ICCV 2025
Extracting Interpretable Task-Specific Circuits from Large Language Models for Faster Inference AAAI 2025
V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Models ICCV 2025
AlignGuard: Scalable Safety Alignment for Text-to-Image Generation ICCV 2025
Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation ICCV 2025
Dream-to-Recon: Monocular 3D Reconstruction with Diffusion-Depth Distillation from Single Images ICCV 2025
ATAS: Any-to-Any Self-Distillation for Enhanced Open-Vocabulary Dense Prediction ICCV 2025
HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction ICCV 2025
What to Distill? Fast Knowledge Distillation with Adaptive Sampling ICCV 2025
VRM: Knowledge Distillation via Virtual Relation Matching ICCV 2025
Coupling the Generator with Teacher for Effective Data-Free Knowledge Distillation ICCV 2025
SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models NAACL 2025
ChromaDistill : Colorizing Monochrome Radiance Fields with Knowledge Distillation WACV 2025
Dynamic Feature Fusion for Sign Language Translation Using HyperNetworks NAACL 2025
SMDAF: A Scalable Sidewalk Material Data Acquisition Framework with Bidirectional Cross-Modal Knowledge Distillation WACV 2025
Beyond the Mode: Sequence-Level Distillation of Multilingual Translation Models for Low-Resource Language Pairs NAACL 2025
Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks CVPR 2025
MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU NAACL 2025
Comparative Knowledge Distillation WACV 2025
Machine Translation Metrics for Indigenous Languages Using Fine-tuned Semantic Embeddings NAACL 2025
MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity AAAI 2025
Aligning Sizes of Intermediate Layers by LoRA Adapter for Knowledge Distillation NAACL 2025
AIDE: Improving 3D Open-Vocabulary Semantic Segmentation by Aligned Vision-Language Learning WACV 2025
Encoder-Aware Sequence-Level Knowledge Distillation for Low-Resource Neural Machine Translation NAACL 2025
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation ACL 2025