knowledge distillation

FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance CVPR 2026 FlashVSR: Towards Real-time Diffusion-Based Streaming Video Super Resolution CVPR 2026 FlowAnyTime: Efficient Fine-tuning with Intra-Inter Frame Distillation for All-Weather Optical Flow Estimation AAAI 2026 Flow-Based Knowledge Transfer for Efficient Large Model Distillation AAAI 2026 Flow Map Distillation Without Data CVPR 2026 Forging a Dynamic Memory: Retrieval-Guided Continual Learning for Generalist Medical Foundation Models CVPR 2026 Foundry: Distilling 3D Foundation Models for the Edge CVPR 2026 FRoD: Full-Rank Efficient Fine-Tuning with Rotational Degrees for Fast Convergence AAAI 2026 From Infusion to Assimilation Distillation for Medical Image Segmentation CVPR 2026 From Passive Perception to Active Memory: A Weakly Supervised Image Manipulation Localization Framework Driven by Coarse-Grained Annotations AAAI 2026 From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation WACV 2026 From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity CVPR 2026 From Static to Active: Knowledge-Aware Node State Selection in Multi-view Graph Learning AAAI 2026 FT-NCFM: An Influence-Aware Data Distillation Framework for Efficient VLA Models AAAI 2026 FuseMine: Robust Multi-Modal Compound-Protein Interaction Prediction via Differential Attention Feature Mining AAAI 2026 FVAR: Next-Focus Prediction for Visual Autoregressive Modeling CVPR 2026 Generalizable and Efficient Automated Scoring with a Knowledge-Distilled Multi-Task Mixture-of-Experts AAAI 2026 Generalizable Heterogeneity-aware Federated Feature and Basic-matrix Consistency Learning AAAI 2026 Generalizable Knowledge Distillation from Vision Foundation Models for Semantic Segmentation CVPR 2026 Gentle Manipulation Policy Learning via Demonstrations from VLM Planned Atomic Skills AAAI 2026 GeoGuide: Hierarchical Geometric Guidance for Open-Vocabulary 3D Semantic Segmentation CVPR 2026 GeoSANE: Learning Geospatial Representations from Models, Not Data CVPR 2026 GrayKD: Distilling Better Knowledge from Black-box LLM via Multi-rationale Injection AAAI 2026 GTR-Turbo: Merged Checkpoint is Secretly a Free Teacher for Agentic VLM Training CVPR 2026 Guided Distillation and Risk Adaptive Evolution for Multi-Robot Navigation AAAI 2026