Knowledge Distillation

LegalDrill: Diagnosis-Driven Synthesis for Legal Reasoning in Small Language Models ACL 2026 LightRR: A Lightweight Network for Single Image Reflection Removal CVPR 2026 LogCD: Local-to-global Consistency Distillation for Few-step Image Generation CVPR 2026 LOREAL: Mitigating Low-Resolution Challenges in Vision-Language Models with Attribute-driven Prompt Self-Distillation CVPR 2026 Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens CVPR 2026 Masked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning CVPR 2026 MeanFlow Transformers with Representation Autoencoders CVPR 2026 Memory-Efficient Transfer Learning with Fading Side Networks via Masked Dual Path Distillation CVPR 2026 MGDHand: Multi-Granularity Prior-to-Inertial Distillation Framework for Sequential 3D Hand Pose Estimation from Sparse IMUs CVPR 2026 Mobile-VTON: High-Fidelity On-Device Virtual Try-On CVPR 2026 Modeling Cross-vision Synergy for Unified Large Vision Model CVPR 2026 MSRL: Scaling Generative Multimodal Reward Modeling via Multi-Stage Reinforcement Learning CVPR 2026 Multimodal Distribution Matching for Vision-Language Dataset Distillation CVPR 2026 MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection WACV 2026 PAGET: Hierarchical Multi-Teacher Knowledge Distillation for Comprehensive Tumor Microenvironment Segmentation MIDL 2026 PDD: Manifold-Prior Diverse Distillation for Medical Anomaly Detection CVPR 2026 PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference ACL 2026 Personalized Image Privacy Advisors via Federated Daisy-Chaining WACV 2026 Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals CVPR 2026 Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers CVPR 2026 POUR: A Provably Optimal Method for Unlearning Representation via Neural Collapse CVPR 2026 Preserving Compositionality for Robust Multi-Subject Personalization in Text-to-Image Generation UAI 2026 Progressive Mask Distillation for Self-supervised Video Representation CVPR 2026 Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning CVPR 2026 RADAR: VQ-VAE Decoder of VAR is a Good Student for Restoring Against Degradation by Acceleration CVPR 2026