← Application Areas
Machine Learning › Application Areas ›

Knowledge Distillation

2907 directly classified papers

Papers per year

Papers

MTVHunter: Smart Contracts Vulnerability Detection Based on Multi-Teacher Knowledge Translation AAAI 2025
DCA: Dividing and Conquering Amnesia in Incremental Object Detection AAAI 2025
Learning Occlusion-Robust Vision Transformers for Real-Time UAV Tracking CVPR 2025
Distilled Prompt Learning for Incomplete Multimodal Survival Prediction CVPR 2025
Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves CVPR 2025
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement CVPR 2025
Sim4Rec: Data-Free Model Extraction Attack on Sequential Recommendation AAAI 2025
Teach Small Models to Reason by Curriculum Distillation EMNLP 2025
DART: Distilling Autoregressive Reasoning to Silent Thought EMNLP 2025
Improving Reasoning Capabilities in Small Models through Mixture-of-layers Distillation with Stepwise Attention on Key Information EMNLP 2025
ToDi: Token-wise Distillation via Fine-Grained Divergence Control EMNLP 2025
Dynamic Contrastive Knowledge Distillation for Efficient Image Restoration AAAI 2025
The Gemma Sutras: Fine-Tuning Gemma 3 for Sanskrit Sandhi Splitting EMNLP 2025
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval CVPR 2025
When Big Models Train Small Ones: Label-Free Model Parity Alignment for Efficient Visual Question Answering using Small VLMs EMNLP 2025
Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster EMNLP 2025
Adaptive Dual Guidance Knowledge Distillation AAAI 2025
MergeNet: Knowledge Migration Across Heterogeneous Models, Tasks, and Modalities AAAI 2025
Multi-label Self Knowledge Distillation AAAI 2025
TinySAM: Pushing the Envelope for Efficient Segment Anything Model AAAI 2025
From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations EMNLP 2025
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performance EMNLP 2025
Efficient Federated Learning via Clients-to-Server Knowledge Distillation (Student Abstract) AAAI 2025
CLIP-CID: Efficient CLIP Distillation via Cluster-Instance Discrimination AAAI 2025
Confound from All Sides, Distill with Resilience: Multi-Objective Adversarial Paths to Zero-Shot Robustness ICCV 2025