A temperature-perturbed black-box attack infers video training membership in VideoLLMs with 0.68 AUC by exploiting sharper generation behavior on member samples.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
method 1polarities
use method 1representative citing papers
A sequential-to-global SSL method based on DINO pretrains iterative foveal-inspired vision transformers to achieve competitive ImageNet-1K performance with constant compute regardless of input resolution.
LLaBIT is a single instruction-finetuned LLM that performs report generation, VQA, segmentation, and translation on brain MRI images while outperforming task-specific models.
Bias mitigation reduces gender-occupation disparities in the embedding spaces of both encoder-only and decoder-only foundation models, producing more neutral internal representations.
citing papers explorer
-
Membership Inference Attacks Against Video Large Language Models
A temperature-perturbed black-box attack infers video training membership in VideoLLMs with 0.68 AUC by exploiting sharper generation behavior on member samples.
-
Self-supervised pretraining for an iterative image size agnostic vision transformer
A sequential-to-global SSL method based on DINO pretrains iterative foveal-inspired vision transformers to achieve competitive ImageNet-1K performance with constant compute regardless of input resolution.
-
Visual Instruction-Finetuned Language Model for Versatile Brain MR Image Tasks
LLaBIT is a single instruction-finetuned LLM that performs report generation, VQA, segmentation, and translation on brain MRI images while outperforming task-specific models.
-
A Representation-Level Assessment of Bias Mitigation in Foundation Models
Bias mitigation reduces gender-occupation disparities in the embedding spaces of both encoder-only and decoder-only foundation models, producing more neutral internal representations.