Enamul Hoque Prince

Our paper is accepted to EACL 2026 main conference (acceptance rate 20%). Aligning Text, Code, and Vision: A Multi-Objective RL Framework for Text-to-Visualization. We introduce RL-Text2Vis, the first RL framework for Text-to-Visualization using post-execution feedback.

Huge thanks to my amazing students and collaborators—this work is truly a team effort. Aaryaman Kartha, @Ahmed_Masry97, Mohammed Saidul Islam, Thinh Lang, Shadikur Rahman, Ridwan Mahbub, Mizanur Rahman, Mahir Rezoun Ahmed, Md Rizwan Parvez @JotyShafiq

4/4 📊Key finding State-of-the-art agents still struggle with: • grounding dashboard elements • planning interaction sequences • reasoning across coordinated views 👉 Interactive dashboard QA is far from solved. The code and data will be released here: github.com/vis-nlp/Dashbo…

Happy to share that our paper “DashboardQA: Benchmarking Multimodal Agents for Question Answering on Interactive Dashboards” is accepted at #EACL2026 🎉 📄 Preprint: arxiv.org/pdf/2508.17398 Even the best agents score <40% accuracy on real dashboards. Why? 👇

Nice work-Verification is critical for reliable LLMs!

Excited about multimodal LLMs for visualization? Join my #MLLM4Vis tutorial at @ieeevis — Mon, Nov 3 · 09:00–12:30 (Room 1.61 + 1.62)! We’ll explore vision-language models, chart reasoning & agentic systems and more. 🔗 nlp4vis.github.io #IEEEVIS

💥 Excited to share our survey paper “LLM-Based Data Science Agents: A Survey of Capabilities, Challenges, and Future Directions,” now available on arXiv! Read it here- arxiv.org/pdf/2510.04023

📢 Excited to share our COLM 2025 paper: BigCharts-R1 📊 We introduce a new dataset and training framework that push the boundaries of chart reasoning in VLMs. 🗓️ Join us at Poster Session 4 on Wednesday, 4:30 PM! 🧵 Thread below 👇 arxiv.org/abs/2508.09804

The submission deadline for the 2nd Workshop on Bangla Language Processing (BLP) workshop (co-located with AACL-IJCNLP 2025) has been extended to October 4, 2025 (blp-workshop.github.io) @firojalam04 @cryptexcode @Enamul_Hoque @shammur_absar @MdNishatRaihan @aaclmeeting

Excited to announce that AlignVLM got accepted to NeurIPS! 🎉🥳 We’ll be releasing the code and sharing an updated version of the paper with reviewer feedback soon. #NeurIPS2025

Excited to announce that our paper has been selected for a Best Paper Award at IEEE VIS 🏆 I would like to extend my gratitude to my co-authors, specifically to my supervisor Dr. @Enamul_Hoque . This achievement would not have been possible without their support. #IEEEVIS2025

Congrats to my PhD student @Mizanur10107462 on #Text2Vis at #EMNLP2025 🙌 A challenging benchmark for text-to-visualization. Check it out!

🚨 New Paper Alert! Excited to share that one of our latest works, "The Perils of Chart Deception: How Misleading Visualizations Affect Vision-Language Models", has been accepted at IEEE VIS 2025 📄 Preprint link: arxiv.org/pdf/2508.09716 1/6🧵

📢 New Paper Alert! Excited to share our one of our latest work: "From Charts to Fair Narratives: Uncovering & Mitigating Geo-Economic Biases in Chart-to-Text" 📄 arXiv: arxiv.org/pdf/2508.09450 1/5 🧵

The Call for Papers for the second edition of the Bangla Language Processing (BLP) Workshop is out (blp-workshop.github.io/cfp). This year's BLP workshop will be co-located with the IJCNLP-AACL conference from December 20-24, 2025, in Mumbai, India. We invite researchers to submit original work presenting novel approaches and resources that advance Bangla and other low-resource languages. This year's workshop will also consist of two shared tasks (blp-workshop.github.io/sharedtasks): *Task 1: Hate Speech Detection (github.com/AridHasan/blp2…) *Task 2: Code Generation (noshinulfat.github.io/blp25_code_gen…) Important Dates: *Paper submission due (both regular and shared tasks papers): Sep 29 (Mon), 2025 *Notification of acceptance: Nov 3 (Mon), 2025 *Camera-ready due: Nov 11 (Tue), 2025 @aaclmeeting @firojalam04 @shammur_absar @Enamul_Hoque @cryptexcode @MdNishatRaihan #aacl #ijcnlp #nlproc #blp

This is fake, right?

🚨 New Paper Alert! Excited to share our latest work accepted at ACL 2025 (Industry Track)!: "Judging the Judges: Can Large Vision-Language Models Fairly Evaluate Chart Comprehension and Reasoning?" 📄 arXiv: arxiv.org/abs/2505.08468 1/6 🧵

Excited to share that ChartQAPro has been accepted to ACL 2025 Findings 🚀🥳 See you in Vienna! #ACL2025