knowledge distillation

Distilling Rule-based Knowledge into Large Language Models COLING 2025 Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment CVPR 2025 Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation CVPR 2025 Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization AAAI 2025 Distilling the Knowledge in Data Pruning ICML 2025 Distill Visual Chart Reasoning Ability from LLMs to MLLMs EMNLP 2025 DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models ACL 2025 Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation ICLR 2025 DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts ACL 2025 Divergence-enhanced Knowledge-guided Context Optimization for Visual-Language Prompt Tuning ICLR 2025 Diversity-Rewarded CFG Distillation ICLR 2025 Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning ICCV 2025 DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture CVPR 2025 DL-KDD: Dual-Lightness Knowledge Distillation for Action Recognition in the Dark IJCAI 2025 DM-Codec: Distilling Multimodal Representations for Speech Tokenization EMNLP 2025 Does Rationale Quality Matter? Enhancing Mental Disorder Detection via Selective Reasoning Distillation ACL 2025 Does Training with Synthetic Data Truly Protect Privacy? ICLR 2025 DOLLAR: Few-Step Video Generation via Distillation and Latent Reward Optimization ICCV 2025 Don’t Half-listen: Capturing Key-part Information in Continual Instruction Tuning ACL 2025 Don’t Reinvent the Wheel: Efficient Instruction-Following Text Embedding based on Guided Space Transformation ACL 2025 DPED: Multi-Layer Noise Distillation for Privacy-Preserving Text Embeddings EMNLP 2025 DPMamba: Distillation Prompt Mamba for Multimodal Remote Sensing Image Classification with Missing Modalities IJCAI 2025 DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation ACL 2025 DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers ACL 2025 Drawing Developmental Trajectory from Cortical Surface Reconstruction ICCV 2025