List your company

Research

Papers for “question answering”

Find papers, implementations, and the benchmark evidence behind state-of-the-art AI systems.

Search results

TitleAuthorsYearSource
REKEY: Metadata-Grounded Visual-Key Regeneration for Contamination-Resilient VQA EvaluationTengjie Lin, Yutao Sun, Jingwei Ni2026arxiv 2606.20736
Scalable Training of Spatially Grounded 2D Vision-Language Models for RadiologyYusuf Salcan, Simon Ging, Robin Tibor Schirrmeister2026arxiv 2606.20477
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg DitheringYury Belousov, Brian Pulfer, Vitaliy Kinakh2026arxiv 2605.23065
FOL2NS: Generating Natural Sentences from First-Order LogicMei Jia2026arxiv 2605.18155
INAR-VL: Input-Aware Routing for Edge-Cloud Vision-Language InferenceAhmed Šabanović, Paul Joe Maliakel, Ivona Brandić2026arxiv 2605.18853
Towards Multi-Turn Dialog Systems for Industrial Asset Operations and MaintenanceChengrui Li, Rujing Li, Yitong Bai2026arxiv 2605.24953
Knowing but Not Showing: LLMs Recognize Ambiguity but Rarely Ask Clarifying QuestionsJinyan Su, Claire Cardie2026arxiv 2605.25284
Chain-based Adaptive Reconfiguration Over Lattices for Hallucination ReductionJoan Vendrell Gallart, Solmaz Kia, Russell Bent2026arxiv 2605.27706
PolitNuggets: Benchmarking Agentic Discovery of Long-Tail Political FactsYifei Zhu2026arxiv 2605.14002
Towards Paradigm-General Suicide Risk Detection via Speech LLMJialun Li, Weitao Jiang, Ziyun Cui2025arxiv 2509.22153
Who Judges the Judge? Evaluating LLM-as-a-Judge for French Medical open-ended QAIkram Belmadani, Oumaima El Khettari, Pacôme Constant dit Beaufils2026arxiv 2603.04033
Pragmatics Meets Culture: Culturally-adapted Artwork Description Generation and EvaluationLingjun Zhao, Dayeon Ki, Marine Carpuat2026arxiv 2604.02557
QFS-Composer: Query-focused summarization pipeline for less resourced languagesVuk \DJuranović, Marko Robnik Šikonja2026arxiv 2604.10687
Can MLLMs "Read" What is Missing?Jindi Guo, Chaozheng Huang, Xi Fang2026arxiv 2604.21277
When Your LLM Reaches End-of-Life: A Framework for Confident Model Migration in Production SystemsEmma Casey, David Roberts, David Sim2026arxiv 2604.27082
Calibrating Model-Based Evaluation Metrics for SummarizationHongye Liu, Dhanajit Brahma, Ricardo Henao2026arxiv 2604.17200
LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video UnderstandingBoyuan Sun, Jiaxing Zhao, Xiang Chen2025arxiv 2501.05067
Hierarchical Visual Agent: Managing Contexts in Joint Image-Text Space for Advanced Chart ReasoningQihua Dong, Ruozhen He, Junwen Chen2026arxiv 2605.04304
Task-Aware Answer Preservation under Audio Compression for Large Audio Language ModelsAmir Ivry2026arxiv 2605.06631
Improving VQA Reliability: A Dual-Assessment Approach with Self-Reflection and Cross-Model VerificationXixian Wu, Yang Ou, Pengchao Tian2025arxiv 2512.14770