arXiv AI October 19, 2026 By Zilin Du, Haoxin Li, Jianfei Yu, Boyang Li

Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding

The paper introduces POBF (Paint Outside the Box and Filter), a framework designed to improve visual grounding in data-scarce settings. POBF synthesizes images by inpainting outside the bounding box to correct label misalignment and employs a filtering scheme that balances hardness and overfitting scores to select the most effective training data. Experiments on four benchmark datasets show that POBF consistently boosts performance, achieving an average 5.83% gain over real-data-only baselines and surpassing leading methods by 2.29%–3.85% in accuracy, while also demonstrating robustness across different generative models, data sizes, and architectures.

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.

benchmarks

arXiv Machine Learning

Sep 25

Let Training Guide Selection: Online Synthetic Data Filtering via Real-Anchored Utility

The paper introduces FROST, an online framework that filters synthetic training data by estimating its utility through gradient feedback anchored in real data. FROST calibrates batch utility against recent history to decide when to filter, removing 20–30% of synthetic samples while improving performance on image classification and LLM fine-tuning tasks. The method is also applied to a large‑scale industrial ads re‑ranking system, yielding significant gains over an optimized production baseline.

By Yanran Wu, Sana Lakdawala, Renzo Tassara Miller, Chongyang Bai, Sharath Ciddu, Shivendra Pratap Singh, Kungang Li, Sandeep Pandey, Chunwei Liu

llms computer-vision fine-tuning benchmarks data-engineering

arXiv AI

Sep 30

From Unity Simulation to Diffusion-Based Augmentation: Quantifying Dataset Balance for Robust Object Detection

arXiv:2609.38010v1 Announce Type: cross Abstract: Modern computer vision models achieve high accuracy when trained on large-scale annotated datasets. In critical domains such as construction safety m...

By Mohamed Benkedadra, Aissa Saoudi, Maxime Gloesener, Sidi Ahmed Mahmoudi, Matei Mancas

diffusion computer-vision safety

arXiv Computation and Language

Sep 17

RankGround: Efficient High-Resolution GUI Grounding via Lightweight Reranker-Guided Crop Selection

RankGround is a two‑stage framework for GUI grounding that uses a single Vision‑Language Model call per query. It introduces GroundRanker, a lightweight multimodal reranker that selects the most promising crop from a dense candidate set, trained with a two‑stage curriculum on ranking supervision data derived from existing grounding datasets. Experiments show RankGround outperforms strong baselines, achieving 1.4× faster inference and a 5.5% average improvement in localization accuracy over the second‑best method across all backbones and screen scales.

By Liyang Fan, Xinping Bi, Yitai Li, Shuaimin Li, Hui Li, Min Yang

llms agents multimodal safety

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

Jun 2

CLIP Tricks You: Training-free Token Pruning for Efficient Pixel Grounding in Large VIsion-Language Models

arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.

By Sangin Lee, Yukyung Choi

llms fine-tuning efficiency multimodal

arXiv Computer Vision

Oct 2

VIEScore2: Unified Image Evaluation with Spatially Grounded Explanations

arXiv:2610.00994v1 Announce Type: new Abstract: Existing synthetic image evaluators typically provide only a scalar quality score and do not identify the image regions that support it. We introduce V...

By Xianda Du, Max Ku, Weiming Ren, Zhi Rui Tam, Chunlin Ren, Ping Nie, Min-Hung Chen, Wenhu Chen

llms diffusion fine-tuning multimodal benchmarks