Skip to content
Conference Open access

VLMinators at Sci-ImageMiner 2026 Tasks 1–4: QLoRA Fine-Tuning of Qwen2.5-VL With Selective Label Disambiguation and Cross-Task Context Injection

Sep 2026 · Open Conference Proceedings · 0 citations · 22 references

TL;DR

A cross-task context-injection pipeline that prepends the structured outputs of earlier tasks to downstream prompts at inference time, grounding summarizations and VQA answers in explicitly extracted values rather than visual estimation, without additional training is proposed.

Abstract

We describe our system for the ICDAR 2026 Sci-ImageMiner competition, covering figure panel classification (Task 1), data extraction (Task 2), summarization (Task 3), and visual question answering (Task 4) on scientific figures from atomic layerdeposition and etching literature. For Task 1, we progress from CNN and zero-shot VLM baselines through QLoRA fine-tuning of Qwen2.5-VL-7B-Instruct, finding that short disambiguation descriptions injected only for the most confusable class pairs improved fine-grained classification without degrading well-separated classes; a six model weighted ensemble achieved F1=0.8059 on the CodaBench evaluation phase. For Tasks 2–4, we fine-tune Qwen2.5-VL independently for each task and additionally propose a cross-task context-injection pipeline that prepends the structured outputs of earlier tasks to downstream prompts at inference time, grounding summarizations and VQA answers in explicitly extracted values rather than visual estimation, without additional training.

Read PDF

Similar papers

Conference Open access Sep 2026

IIT PATNA CV 1 at Sci-ImageMiner 2026 Task 1: LoRA-Enhanced Generative Vision–Language Models for Scientific Figure Panel Classification

This paper presents a solution to the Sci-ImageMiner Competition: Task 1 (classification) at ICDAR 2026. The objective is to accurately classify individual scientific figure panels from Atomic Layer Deposition and Etching (ALD/E) literature into a domain-specific taxonomy. We formulate this challenge as a conditional t...

Soumyajyoti Mohanta, Shresth Kasyap, Sasmit Shashwat et al. · 0 citations
Conference Open access Sep 2026

[DocMiner] at Sci-ImageMiner 2026 (Tasks 1, 2, and 4): Skill-Based Agentic DocMiner

This work presents Skill-Based Agentic DocMiner, a unified agentic workflow with three recurring components: multimodal context enrichment from captions and paper text, iterative skill refinement using development-set feedback, and collaborative verification by specialist reviewers.

Shu-Tao Gong, Jing Huang · 0 citations
Conference Open access Sep 2026

DeepVitminC at Sci-ImageMiner 2026 Tasks 3&4: Structured Context Augmentation for Scientific Figure Reasoning

Scientific figures encode critical experimental findings that are often not fully captured in textual descriptions. Despite recent advances in MLLMs, their performance on domain-specific scientific figures remains limited due to insufficient grounding in relevant context. In this work, we focus on in Task 3 (summarizat...

Xiaole Lv, Wei Wu, Yang Tan et al. · 0 citations
Conference Open access Sep 2026

Vassilis Sioros at Sci-ImageMiner 2026 Tasks 2, 3, and 4

In this work, we address two core challenges in the ALD-E domain: auxiliary evidence construction via summarization and data table extraction, and visual question answering (VQA). Our approach first generates auxiliary summaries and structured tables to support test-time VQA prompting, using Qwen3.5-9B vision-language...

Vassilis Sioros · 0 citations

MNN at HAHA@IberLEF 2026 Task-Adaptive Reasoning and Fine-Tuning for Spanish Humor Detection

Results show that the two subtasks behave differently in practice: satirical headline detection is better handled by prompting a large instruction-following model, while LLM-generated joke detection benefits more from supervised learning over dataset-specific stylistic and length-related cues.

Q. Dang, Nhan Phuoc Thanh Tran, M.-J. Truong et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.