Knowledge Distillation

Cross-Architecture Adaptation: Cloud-Edge Continual Test-Time Adaptation with Dynamic Sampling and Heterogeneous Distillation CVPR 2026 Cross-View Distillation and Adaptive Masking for Incomplete Multi-View Multi-Label Classification CVPR 2026 Deep Feature Deformation Weights CVPR 2026 Deformable Gaussian Occupancy: Decoupling Rigid and Nonrigid Motion with Factorized Distillation CVPR 2026 Diffusion Distillation with Direct Preference Optimization for Efficient 3D LiDAR Scene Completion AAAI 2026 Distilling Balanced Knowledge from a Biased Teacher CVPR 2026 Distilling Large Embeddings via Hyperspherical Householder Quantization ACL 2026 DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding CVPR 2026 Domain-Constrained Distillation of DINOv3 into a Lightweight Foundation Model Toward Point-of-Care Ultrasound MIDL 2026 Dual-branch Distilled Transformer for Efficient Asymmetric UAV Tracking CVPR 2026 Dual-Granularity Memory for Efficient Video Generation CVPR 2026 DUDA: Distilled Unsupervised Domain Adaptation for Lightweight Semantic Segmentation WACV 2026 DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolution CVPR 2026 Enhancing Mixture-of-Experts Specialization via Cluster-Aware Upcycling CVPR 2026 Enhancing Reverse Distillation with Core Exemplar Learning for Unified Multi-Class Anomaly Detection WACV 2026 Evaluating the Expressive Appropriateness of Speech in Rich Contexts ACL 2026 Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching CVPR 2026 FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters CVPR 2026 Fast Reasoning Segmentation for Images and Videos CVPR 2026 Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning CVPR 2026 FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing CVPR 2026 Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation ACL 2026 Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation CVPR 2026 Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning CVPR 2026 FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance CVPR 2026