arXiv AI
When Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment Diagnostic
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
3d ago
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...
arXiv Machine Learning
Jun 4
Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC
arXiv:2606. 04857v1 Announce Type: new Abstract: Standard IMVC evaluation retrains separate models for different missing-data configurations.
arXiv AI
Jul 2
ForAug: Mitigating Biases in Image Classification via Controlled Image Compositions
arXiv:2503. 09399v4 Announce Type: replace-cross Abstract: Large-scale image classification datasets exhibit strong compositional biases: objects tend to be centered, appear at characteristic scales, and co-occur with class-specific context.
arXiv Computer Vision
3d ago
Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models
arXiv:2609.39134v1 Announce Type: new Abstract: Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study a...
arXiv Machine Learning
Aug 21
Clustering and Token Denoising for Faster and More Robust VLMs
arXiv:2608. 19285v1 Announce Type: cross Abstract: Recent Visual-Language Models (VLMs) have enhanced the capabilities of pre-trained LLMs by adding vision tokens alongside text, with approaches like LLaVA showing impressive results.
arXiv Statistics ML
2d ago
The hidden advantage of mask resampling: a theory of masked autoencoders
arXiv:2610. 01578v1 Announce Type: new Abstract: Why can masked prediction learn useful representations that unmasked reconstruction misses?