Anshul Singh[]

M4-RAG: A Massive-Scale Multilingual Multi-Cultural Multimodal RAG
David Anugraha, Patrick Amadeus Irawan, Anshul Singh, En-Shiun Annie Lee, Genta Indra Winata
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
Paper / Poster

We introduce M4-RAG, a massive-scale benchmark covering 42 languages and 56 dialects with over 80,000 culturally diverse image-question pairs to evaluate retrieval-augmented VQA. Our systematic evaluation reveals that while RAG consistently benefits smaller Vision-Language Models (VLMs), it fails to scale to larger models and often degrades their performance, exposing a critical mismatch between model size and current retrieval effectiveness.

HybridNet: Efficient Multimodal Fake News Detection
Shreyas Kumar Tah, Anshul Singh, Prajeet Katari, et al.
PP-MisDet@CVPR, 2026

We propose HybridNet, a data-efficient framework that leverages hybrid active learning to select the most informative samples, drastically reducing labeling cost. We also propose a lightweight Reasoning-Aware Classifier (RAC) for challenging cases, which combines Vision–Language Model (VLM) features with reasoning from a Multimodal Large Language Model (MLLM) to further improve detection performance and provide human- interpretable explanations.

MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Space
Anshul Singh, Chris Biemann, Jan Strich
Empirical Methods of Natural Language Processing (EMNLP), 2025 Findings
Paper / Dataset / Poster

In this work, we address a critical gap in Vision-Language Model (VLM) evaluation by introducing MTabVQA, a novel benchmark for multi-tabular visual question answering. Our benchmark comprises 3,745 complex question-answer pairs that require multi-hop reasoning across several visually rendered table images, simulating real-world documents. We benchmark state-of-the-art VLMs, revealing significant limitations in their ability to reason over complex visual data. To address this, we release MTabVQA-Instruct, a large-scale instruction-tuning dataset. Our experiments demonstrate that fine-tuning with our dataset substantially improves VLM performance, bridging the gap between existing benchmarks that rely on single or non-visual tables.

Comparative Analysis of State-of-the-Art Attack Detection Models
Priyanka Kumari, Veenu Mangat, and Anshul Singh
14th International Conference on Computing Communication and Networking Technologies (ICCCNT), 2023
Paper

In this work, we address the growing security challenges in IoT networks by conducting a comprehensive comparative analysis of machine learning classifiers for intrusion detection. We evaluated five distinct models on two real-world IoT network traffic datasets to identify the most effective algorithms for detecting malicious activity. Our findings show that tree-based models, specifically Random Forest and Decision Trees, deliver outstanding performance, achieving accuracies exceeding 99%. This research provides a clear benchmark and practical guidance for developing robust and high-performance security systems to protect vulnerable IoT environments.