arXiv AI September 2, 2026 By Teresa DiMeola, Charles Walter, Hong Xiao

Restrict, Don't Retrain: Inference-Time VLM Guidance for Zero-Shot Aerial Segmentation

The paper proposes a method called Restrict, Don't Retrain that enhances zero-shot aerial segmentation by using inference-time guidance from a vision‑language model (VLM). It combines a frozen foundation model that labels every pixel with two VLM queries: one to select relevant classes and another to locate small objects missed by the base model. Experiments on four aerial datasets show consistent performance gains at each stage where the base model is competent.

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 Computation and Language

Aug 25

Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models

arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image...

By Jinchang Zhu, Rong Fu, Yi Ding, Chenghao Wu, Ying Liu, Menglin Yang

llms computer-vision multimodal benchmarks

arXiv Computer Vision

Sep 7

Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding

IVSGround introduces a lightweight view selector that learns to choose the most informative camera views for vision‑language model (VLM) based 3D visual grounding, replacing heuristic view selection. The selector is trained via a two‑stage rejection sampling process that uses feedback from a reasoning VLM to generate supervision signals. Experiments on ScanRefer and NR3D demonstrate that IVSGround consistently improves grounding accuracy over existing zero‑shot pipelines, underscoring the importance of selecting where to look for effective 3D visual grounding.

By Tsung-Chih Chiang, Hsuan-Kung Yang, Jou-Min Liu, Ting-Ru Liu, Chun-Wei Huang, Quan Kong, Chun-Yi Lee

llms multimodal

arXiv AI

Jul 7

Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models

arXiv:2607. 02718v1 Announce Type: cross Abstract: Recent advances in large-scale image generative models enable photorealistic scene synthesis with controllable attributes.

By Stanislav Panev, Minhyek Jeon, Vaishnavi Khindkar, Ahish Deshpande, Celso M de Melo, Shuowen Hu, Shayok Chakraborty, Fernando De la Torre

llms multimodal

Hugging Face Trending Papers

Jul 7

AVA-VLM: Adaptive Visual Attention-Vision Language Model for In-the-Wild Construction Site Monitoring

Vision-Language Models (VLMs) are promising for construction-site monitoring, and recent construction-tailored VLMs have primarily adapted pretrained VLMs through direct QA-style fine-tuning from a single global image. We argue that this direct paradigm remains limited for in-the-wild deployment in terms of operational range, reliability under reduced-resolution inputs, and inference efficiency.

llms fine-tuning multimodal

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 Computer Vision

Sep 11

Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real World Conditions

The paper investigates using Vision Language Models (VLMs) to accelerate verification and validation (V&V) of classification models by automatically detecting systematic errors. It introduces a VLM-based error slice detection (ESD) method that groups and labels errors, demonstrating its ability to identify perturbations in a non-military dataset and to cluster images by surroundings in a military context. The study highlights challenges such as underrepresentation of defence data in VLM training and limited contextual diversity, and suggests that while fully automated V&V is not yet feasible, VLMs could speed up the process in the future.

By Dieuwertje Alblas, Alma M. Liezenga, Jan Erik van Woerden, Fedor Taggenbrock, Dalia Aljawaheri, Klamer Schutte

llms rag multimodal benchmarks