IJCV 2026 papers on Architectures and efficiency
15 of the 477 papers published in IJCV 2026 (3.1%) are on Architectures and efficiency, compared with 2.6% at IJCV 2025. They fall into 6 topics.
See IJCV 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Attention and transformers · 5 papers
- Distillation-free Scaling of Large State-Space Models for Images and Videos (6 citations)
- Multi-Head Attention Residual Unfolded Network for Model-Based Pansharpening (5 citations)
- BehaVERT: A Transformer-Based Motion Language Model for Decoding Behavioral Semantics in Mice (1 citation)
- Cascaded Cross-Attention Vision Transformers with Wavelet-Based Encodings for DeepFake Detection (1 citation)
- Entropy-Guided Condensing for Vision Transformer
Pruning and efficient tuning · 4 papers
- Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark (188 citations)
- ASNA: A Novel Adaptive Sparse Neural Architecture for Embedded Systems
- Dynamic MAsk-Pruning Strategy for Source-Free Model Intellectual Property Protection
- Towards Parameter-Efficient Network Pruning with Re-Parameterized Adapter
