Knowledge Distillation

COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training CVPR 2025 CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models EMNLP 2025 Coupling the Generator with Teacher for Effective Data-Free Knowledge Distillation ICCV 2025 Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence ACL 2025 Cross-Modal Distillation for 2D/3D Multi-Object Discovery from 2D Motion CVPR 2025 CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation ICLR 2025 Curriculum Hierarchical Knowledge Distillation for Bias-Free Survival Prediction IJCAI 2025 CustomKD: Customizing Large Vision Foundation for Edge Model Improvement via Knowledge Distillation CVPR 2025 CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation AACL 2025 daDPO: Distribution-Aware DPO for Distilling Conversational Abilities ACL 2025 DAM: Dynamic Adapter Merging for Continual Video QA Learning WACV 2025 DaMoC: Efficiently Selecting the Optimal Large Language Model for Fine-tuning Domain Tasks Based on Data and Model Compression EMNLP 2025 DARE the Extreme: Revisiting Delta-Parameter Pruning For Fine-Tuned Models ICLR 2025 DART: Distilling Autoregressive Reasoning to Silent Thought EMNLP 2025 DataHacks at PerAnsSumm 2025: LoRA-Driven Prompt Engineering for Perspective Aware Span Identification and Summarization NAACL 2025 Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation ACL 2025 Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-training of Deep Networks ICLR 2025 Dataset Distillation via Vision-Language Category Prototype ICCV 2025 DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models ICCV 2025 DCA: Dividing and Conquering Amnesia in Incremental Object Detection AAAI 2025 DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection AAAI 2025 DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation EMNLP 2025 Debate, Reflect, and Distill: Multi-Agent Feedback with Tree-Structured Preference Optimization for Efficient Language Model Enhancement ACL 2025 Debiased Distillation for Consistency Regularization AAAI 2025 Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks CVPR 2025