paper-with-me

홈 › Papers

Beyond Pixels: Introspective and Interactive Grounding for Visualization Agents

2026-04-22 · Yiyang Lu, Woong Shin, Ahmad Maroof Karimi, Feiyi Wang, Jie Ren, Evgenia Smirni arxiv

Vision-Language Models (VLMs) frequently misread values, hallucinate details, and confuse overlapping elements in charts. Current approaches rely solely on pixel interpretation, creating a Pixel-Only Bottleneck: agents treat interactive charts as static images, losing access to the structured specification that encodes exact values. We introduce Introspective and Interactive Visual Grounding (IVG), a framework that combines (1) spec-grounded introspection, which queries the underlying specification for deterministic evidence, with (2) view-grounded interaction, which manipulates the view to resolve visual ambiguity. To enable evaluation without VLM bias, we present iPlotBench, a benchmark of 500 interactive Plotly figures with 6,706 binary questions and ground-truth specifications. Experiments show that introspection improves data reconstruction fidelity, while the combination with interaction achieves the highest QA accuracy (0.81), with +6.7 % gains on overlapping geometries. We further demonstrate IVG in deployed agents that explore data autonomously and collaborate with human users in real time.

📄 PDF Abstract BibTeX arXiv:2604.21134

Code (0)

등록된 구현이 없습니다.

Tasks

Visual Grounding

Similar Papers 제목 키워드 기반

Interactive Segmentation and Visualization for Tiny Objects in Multi-megapixel Images

2022-04-21 · CVPR 2022 1 · Chengyuan Xu, Boning Dong, Noah Stier, Curtis McCully 외

We introduce an interactive image segmentation and visualization framework for identifying, inspecting, and editing tiny objects (just a few pixels wide) in large multi-megapixel high-dynamic-range (HDR) images. Detectin…

GPUImage SegmentationInteractive SegmentationSegmentation+1

Polaris: Open-ended Interactive Robotic Manipulation via Syn2Real Visual Grounding and Large Language Models

2024-08-15 · Tianyu Wang, Haitao Lin, Junqiu Yu, Yanwei Fu

This paper investigates the task of the open-ended interactive robotic manipulation on table-top scenarios. While recent Large Language Models (LLMs) enhance robots' comprehension of user instructions, their lack of visu…

Pose EstimationVisual Grounding

Introspective Learning : A Two-Stage Approach for Inference in Neural Networks

2022-09-17 · Mohit Prabhushankar, Ghassan AlRegib

In this paper, we advocate for two stages in a neural network's decision making process. The first is the existing feed-forward inference framework where patterns in given data are sensed and associated with previously l…

Active LearningDecision MakingImage Quality AssessmentOut-of-Distribution Detection+2

Introspective Diffusion Language Models

2026-04-13 · Yifan Yu, Yuqing Jian, Junxiong Wang, Zhongzhu Zhou 외 arxiv

Diffusion language models promise parallel generation, yet still lag behind autoregressive (AR) models in quality. We stem this gap to a failure of introspective consistency: AR models agree with their own generations, w…

When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't

2026-04-07 · Jonathan Nemitz, Carsten Eickhoff, Junyi Jessy Li, Kyle Mahowald 외 arxiv

Understanding when Vision-Language Models (VLMs) will behave unexpectedly, whether models can reliably predict their own behavior, and if models adhere to their introspective reasoning are central challenges for trustwor…