arXiv AI August 6, 2026 By Mario Leiva, Yue Ma, Qinru Qiu, Gerardo Simari, Paulo Shakarian

Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models

arXiv:2608. 04190v1 Announce Type: new Abstract: Deploying pre-trained perception models in novel environments degrades their accuracy under distributional shift, and assembling them alone does not recover it: combiners such as majority voting trade recall for precision and are brittle to coordinated failures.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 14

Vertical Fusion: Condensing Internal Representations for Robust ViT Classification

arXiv:2607. 10391v1 Announce Type: cross Abstract: Despite exposing rich intermediate representations, Vision Transformers (ViTs) are almost exclusively utilized as black-box feature extractors, where only the last layer is considered for downstream tasks.

By Francesco Di Salvo, Shyam Nandan Rai, Hamed Damirchi, Ignacio Meza De la Jara, Sebastian Doerrich, Marco Lents, Christian Ledig

llms diffusion

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.

By Haolu Liu, Xiyue Wang, Xuanting Xie, Liangjian Wen, Zhao Kang

llms benchmarks

arXiv AI

Aug 5

In-Context Collapse in Vision-Language Models and How to Mitigate it?

arXiv:2608. 02830v1 Announce Type: cross Abstract: Many-shot in-context learning (ICL) lets vision-language models (VLMs) adapt from image--label demonstrations without weight updates, and is widely assumed to improve as more demonstrations are supplied.

By Mohammad Rostami

llms computer-vision multimodal benchmarks

arXiv AI

Jul 1

The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning

arXiv:2606. 30875v1 Announce Type: cross Abstract: Foundation model pseudo-labeling - labeling data strictly via zero-shot inference - enables massive scale, but performance is undermined by hallucinations that evade standard thresholds.

By Brent A. Griffin, Jason J. Corso

llms computer-vision fine-tuning efficiency multimodal benchmarks safety

arXiv AI

Jun 12

Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns

arXiv:2606. 12629v1 Announce Type: cross Abstract: We show that the standard basis of transformer hidden states already provides a training-free, architecture-general feature basis.

By Varun Reddy Nalagatla

llms efficiency safety

arXiv AI

Jul 1

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation

arXiv:2603. 23867v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) have been applied to a wide range of reasoning tasks, yet it remains unclear whether they can reason robustly under distribution shifts.

By Weixin Chen, Antonio Vergari, Han Zhao

llms fine-tuning multimodal

Related stories

Vertical Fusion: Condensing Internal Representations for Robust ViT Classification

Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC

In-Context Collapse in Vision-Language Models and How to Mitigate it?

The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning

Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns

Can VLMs Reason Robustly? A Neuro-Symbolic Investigation