arXiv AI September 28, 2026 By Drandreb Earl O. Juanico, Rowel O. Atienza

FLIP: Final Layer Inference-Time Probing for Vision-Language Models

FLIP is a final‑layer inference‑time probe designed to test whether a logit‑facing intervention site in an open‑weight vision‑language model (VLM) supports structured, task‑linked computation rather than generic perturbation. The probe applies elementwise flooring to the final normalized hidden state before logit computation, leaving other model components unchanged. By sweeping intervention strength on a controlled detection/counting task, FLIP identifies three regimes—negligible change, a bounded interior regime with improved detection recall and reduced counting error, and over‑suppression—while a four‑criterion protocol ensures the observed effects are mechanistically interpretable.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 30

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift

arXiv:2606. 29699v1 Announce Type: cross Abstract: Vision Language Action models combine perception, language grounding, and control in a single policy, but their failures are hard to diagnose once visual conditions shift.

By Dipesh Tharu Mahato, Rachel Ren

robotics benchmarks

arXiv AI

Aug 24

Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation

The study investigates whether open‑weight language models can introspect on their own internal computations. Using the Open‑Weight Masked Introspection (OWMI) framework, researchers intervened on various internal components of eight models and asked them to report whether changes had occurred. Across 78,000 measurements, none of the models reliably distinguished real interventions from sham ones, with AUROC values essentially at chance. Why It Matters: The findings suggest that current open‑weight models lack the ability to audit their own internal states, highlighting a limitation for oversight that relies on a model’s self‑reporting.

By Emilio Ferrara

llms fine-tuning

arXiv AI

Jun 29

Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?

arXiv:2606. 27755v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized language backbones from pretrained VLMs whose capacity far exceeds what is needed for short robotic instructions.

By Guoheng Sun, Kaixi Feng, Shwai He, Xiaochuan Gong, Yexiao He, Ziyao Wang, Zheyu Shen, Wanghao Ye, Ramana Rao Kompella, Gaowen Liu, Ang Li

llms robotics fine-tuning multimodal 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 3

Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration

arXiv:2603. 06001v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models enable robots to perform manipulation tasks directly from natural language instructions and are increasingly viewed as a foundation for generalist robotic policies.

By Ninghao Zhang, Bin Zhu, Shijie Zhou, Jingjing Chen

robotics multimodal benchmarks safety

arXiv Machine Learning

Sep 15

GroundBench: A Factorized, Counterfactual Benchmark for Locating VLM Affordance Failures

arXiv:2609.13308v1 Announce Type: cross Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language...

By Sarthak Sattigeri

llms robotics multimodal benchmarks

One email a morning, machine-written

Related stories

Early Warning Signals for OpenVLA Failure under Visual Distribution Shift

Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation

Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?

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

Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration

GroundBench: A Factorized, Counterfactual Benchmark for Locating VLM Affordance Failures