arXiv (All)
open access
Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery
Subliminal learning lets a student inherit a teacher's behavioral trait from semantically unrelated data, yet published demonstrations typically require tens of thousands of carrier examples. We ask where this data requirement comes from. Our testbed is subliminal steering: the teacher trait is a kn
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
- Learning Perceptual Rules in a Fragmented Visual World#1324589
- Perception Is Not Always and Everywhere Inferential#740059
- On the Properties of Feature Attribution for Supervised Contrastive Learning#134551
- Evidence-Aligned Multimodal On-Policy Self-Distillation for Fine-Grained Visual Understanding#1128931
- DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention#200470
Record · ID 1200558
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