Cvpr 2026 Streamlined Knowledge Distillation

[CVPR 2026] Streamlined Knowledge Distillation

[CVPR 2026] Pluggable Pruning with Contiguous Layer Distillation for Diffusion Transformers

Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement.

ICMR 2026 Adaptive Spatial-Channel Masked Reconstruction Knowledge Distillation for Dense Prediction

[

Youtube video presentation of

CVPR 2026

MUST: Modality-Specific Representation-Aware Transformer for Diffusion-Enhanced Survival Prediction with Missing Modality.

[

Despite significant progress has been made in image deraining, we note that most existing methods are often developed for only ...

[CVPR 2026 paper] HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning

Despite the impressive performance of diffusion models such as Stable Diffusion (SD) in image generation, their slow inference ...

This paper introduces a novel architecture for trajectory-conditioned forecasting of future 3D scene occupancy. In contrast to ...