Knowledge Distillation

D$^3$epth: Distilling Diffusion Models For Efficient Depth Estimation Through A Two-Stage Approach ACML 2025 DAM: Dynamic Adapter Merging for Continual Video QA Learning WACV 2025 DART: Distilling Autoregressive Reasoning to Silent Thought EMNLP 2025 DASK: Distribution Rehearsing via Adaptive Style Kernel Learning for Exemplar-Free Lifelong Person Re-Identification AAAI 2025 Data Laundering: Artificially Boosting Benchmark Results through Knowledge Distillation ACL 2025 DCSF-KD: Dynamic Channel-wise Spatial Feature Knowledge Distillation for Object Detection AAAI 2025 Debiased Distillation for Consistency Regularization AAAI 2025 Decoding by Contrasting Knowledge: Enhancing Large Language Model Confidence on Edited Facts ACL 2025 Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks CVPR 2025 Delayed-KD: Delayed Knowledge Distillation based CTC for Low-Latency Streaming ASR Interspeech 2025 Depth Any Event Stream: Enhancing Event-based Monocular Depth Estimation via Dense-to-Sparse Distillation ICCV 2025 Detecting Knowledge Boundary of Vision Large Language Models by Sampling-Based Inference EMNLP 2025 Dianchi at SemEval-2025 Task 11: Multilabel Emotion Recognition via Orthogonal Knowledge Distillation SemEval 2025 DiceHuBERT: Distilling HuBERT with a Self-Supervised Learning Objective Interspeech 2025 Diffusion Model is Effectively Its Own Teacher CVPR 2025 Disentangling Spatio-Temporal Knowledge for Weakly Supervised Object Detection and Segmentation in Surgical Video WACV 2025 Distilling Aggregated Knowledge for Weakly-Supervised Video Anomaly Detection WACV 2025 Distilling a speech and music encoder with task arithmetic Interspeech 2025 Distilling Cross-Modal Knowledge into Domain-Specific Retrievers for Enhanced Industrial Document Understanding EMNLP 2025 Distilling Knowledge from Heterogeneous Architectures for Semantic Segmentation AAAI 2025 Distilling Many-Shot In-Context Learning into a Cheat Sheet EMNLP 2025 Distilling Multi-modal Large Language Models for Autonomous Driving CVPR 2025 Distilling Spatially-Heterogeneous Distortion Perception for Blind Image Quality Assessment CVPR 2025 Distilling Structured Rationale from Large Language Models to Small Language Models for Abstractive Summarization AAAI 2025 DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture CVPR 2025