arXiv AI August 7, 2026 By J. de Curt\`o, Dayani Plasencia, Diego S\'anchez, I. de Zarz\`a

Visual Grounding in Zero-Shot Vision-Language Control

arXiv:2608. 06154v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly used as zero-shot controllers, but successful trajectories do not necessarily show that decisions are grounded in visual input: simulator dynamics and conservative action priors can produce favourable scores without meaningful perception.

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

arXiv AI

Jul 7

Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding

arXiv:2606. 13156v2 Announce Type: replace-cross Abstract: Letting a vision-language model (VLM) think longer at test time has driven much recent progress.

By Animesh Tripathy, Aswanth Krishnan

llms multimodal

arXiv AI

Jul 7

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

arXiv:2509. 25533v2 Announce Type: replace-cross Abstract: As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important.

By Ravikumar Balakrishnan, Mansi Phute

llms multimodal benchmarks safety

arXiv Machine Learning

Jun 3

WildRoadBench: A Wild Aerial Road-Damage Grounding Benchmark for Vision-Language Models and Autonomous Agents

arXiv:2605. 20306v2 Announce Type: replace-cross Abstract: We introduce WildRoadBench, a wild aerial road-damage grounding benchmark that couples direct visual grounding by vision-language models with autonomous research-and-engineering by LLM-driven agents on a single professionally annotated UAV corpus.

By Bingnan Liu, Chenhang Cui, Rui Huang, Jiani Luo, Zhirong Shen, Tinghao Wang, Xiande Huang, Lingbei Meng, Fei Shen, An Zhang

llms agents 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

Aug 5

ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies

arXiv:2608. 02958v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies trained by behavior cloning fail silently: from the action stream alone, a collapsing rollout looks much like one making clean progress, because imitation supplies no notion of progress.

By Inkyu Sa, Konstantin Stulov, Rajat Bhageria

llms agents reinforcement-learning robotics multimodal

arXiv Machine Learning

Jun 15

Gaze Heads: How VLMs Look at What They Describe

arXiv:2606. 14703v1 Announce Type: cross Abstract: How a vision-language model internally solves the task of describing an image is far from obvious.

By Rohit Gandikota, David Bau

llms multimodal

Related stories

Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding

VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models

WildRoadBench: A Wild Aerial Road-Damage Grounding Benchmark for Vision-Language Models and Autonomous Agents

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

ValueFormer: A Causal Transformer Value Function with Stage-Aware Labels for Semi-Autonomous Vision-Language-Action Policies

Gaze Heads: How VLMs Look at What They Describe