arXiv (All)
open access
When Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment Diagnostic
This paper demonstrate that whether masking-based token pruning helps or hurts worst-group robustness can be predicted before deployment, without labels or fine-tuning. A systematic study of semantic masking across 8 spurious-correlation benchmarks shows its effect on worst-group accuracy is highly
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
- Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models#1144101
- Where Does the Watermark Hide? Push-Pull Disentanglement for Invisible Watermark Removal#1115678
- SinoGlyphBench: A Diagnostic Benchmark for Chinese Glyph-Level Obfuscation in Language-Model Moderation#973467
- Can Attack Difficulty Be Characterized Before Optimization? A Study of Pre-optimization Difficulty in Person-Vanishing Attacks#1128769
- Static Context Header Compression (SCHC) Compound Acknowledgement (ACK)#502741
Record · ID 1144671
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