arXiv (All)
open access
BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance
Worst-group accuracy (WGA) evaluates a trained predictor but does not characterize how its frozen backbone behaves when a new head is learned. We introduce BiasFlow, a hook-based toolkit for monitoring class-attribute centroid alignment (IBMI), within-class centroid separation (W-IBMI), and feature-
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
- BiasFlow: Geometric Monitoring and Backbone Regularization for Spurious Feature Reliance#1194462
- RoTA-Bench: Evaluating 3D Spatial Reasoning through Interactive Projection Alignment#1344696
- Rotation-Based Subspace Tracking for Robust Kernel PCA on Streaming Data#1109490
- SparkAlign: A Star-Hopping Heuristic for Efficient Unsupervised Plain Graph Alignment#1232601
- Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression#146922
Record · ID 1215925
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