← Application Areas
Machine Learning › Application Areas ›

Knowledge Distillation

2907 directly classified papers

Papers per year

Papers

Quantized Can Still Be Calibrated: A Unified Framework to Calibration in Quantized Large Language Models ACL 2025
Dual-Process Image Generation ICCV 2025
LightBSR: Towards Lightweight Blind Super-Resolution via Discriminative Implicit Degradation Representation Learning ICCV 2025
Table-R1: Inference-Time Scaling for Table Reasoning Tasks EMNLP 2025
Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models ACL 2025
SAFE: Schema-Driven Approximate Distance Join for Efficient Knowledge Graph Querying EMNLP 2025
Process-Supervised Reinforcement Learning for Code Generation EMNLP 2025
Alignment with Fill-In-the-Middle for Enhancing Code Generation EMNLP 2025
CIARD: Cyclic Iterative Adversarial Robustness Distillation ICCV 2025
A Survey on Efficient Large Language Model Training: From Data-centric Perspectives ACL 2025
Local Dense Logit Relations for Enhanced Knowledge Distillation ICCV 2025
zFLoRA: Zero-Latency Fused Low-Rank Adapters EMNLP 2025
HFD-Teacher: High-Frequency Depth Distillation from Depth Foundation Models for Enhanced Depth Completion ICCV 2025
Speed Without Sacrifice: Fine-Tuning Language Models with Medusa and Knowledge Distillation in Travel Applications ACL 2025
Inference-Time Diffusion Model Distillation ICCV 2025
cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree EMNLP 2025
LLaVA-KD: A Framework of Distilling Multimodal Large Language Models ICCV 2025
Efficient Speech Translation through Model Compression and Knowledge Distillation ACL 2025
AnnofreeOD: Detecting All Classes at Low Frame Rates Without Human Annotations ICCV 2025
SGC-Net: Stratified Granular Comparison Network for Open-Vocabulary HOI Detection CVPR 2025
DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture CVPR 2025
Towards Universal Dataset Distillation via Task-Driven Diffusion CVPR 2025
Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks CVPR 2025
VL2Lite: Task-Specific Knowledge Distillation from Large Vision-Language Models to Lightweight Networks CVPR 2025
DART: Distilling Autoregressive Reasoning to Silent Thought EMNLP 2025