📡 Signal & Communications

📷 CVPR2026 · 2 paper notes

📌 Same area in other venues: 🔬 ICLR2026 (8) · 🧪 ICML2026 (2) · 🤖 AAAI2026 (3) · 🧠 NeurIPS2025 (5) · 📹 ICCV2025 (3) · 🧪 ICML2025 (3)

AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation

This paper proposes AcTTA, a test-time adaptation framework based on dynamic activation function modulation. By reparameterizing traditional fixed activation functions into a learnable form—incorporating activation center shifts and asymmetric gradient slopes—the model adaptively adjusts activation behavior during inference to handle distribution shifts. AcTTA consistently outperforms normalization-based TTA methods on CIFAR10-C, CIFAR100-C, and ImageNet-C.

CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space

CLAY proposes a training-free method for conditional visual similarity calculation, which modulates similarity by constructing a text-conditioned subspace within the VLM embedding space. This approach adapts to different retrieval conditions without recomputing database features and supports multi-condition retrieval.