arXiv (OAI Expanded)
open access
DRDN: Decoupled Representation Dynamic Network for From-Scratch ViT Class-Incremental Learning
Dynamic expansion methods for class-incremental learning (CIL) protect task-specific knowledge by growing dedicated tokens or subnetworks, yet our analyses suggest that classification supervision alone does not sufficiently preserve task-agnostic shared backbone representations over long incremental
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning#819120
- One Adapter, Many Tasks: Task-Conditioned Feature Transformations for Continual Learning#809128
- Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate Representations#1013703
- Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs#997322
- Beyond Forgetting: Diagnosing and Harnessing Shared Reasoning in Continual RLVR#1077935
Record · ID 1056362
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive