EMM-QA 2026 Accepted & Shared Challenge Papers

β¬… Back to EMM-QA 2026 Workshop

Topic Paper Archival Authors
πŸ€– QANTA26 Challenge πŸ† Task-Specific Multimodal Question Answering Agents via Confidence βœ— Nirjhar Das; Md. Al-Mamun Provath
Multimodal Retrieval QA Scaling Down: Multi-Hop Information Retrieval in Resource-Constrained Environments βœ“ Nikolay Staroverov
Multimodal Retrieval QA Latent Abstraction for Retrieval-Augmented Generation βœ— Ha-Lan Nguyen; Nguyen A Minh; Dung D. Le
Multimodal Retrieval QA Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering βœ— Noor Islam S. Mohammad
Multimodal Retrieval QA Visual Evidence Collapse as the Missing Signal in Adaptive Multimodal Retrieval: A Position βœ— GΓΆktuğ Aslanoğlu
Multimodal Retrieval QA Look Before You Zoom: Adaptive Routing for the Resolution-Context Trade-off in Visual RAG βœ— Oanh N Tran; Thanh Quoc Hung Le; Oscar Chew; Kuan-Hao Huang; Khoa Doan
Multimodal Retrieval QA PixelRAG: Retrieval and Reading in Pixel Space over Millions of Web Screenshots βœ— Yichuan Wang; Zhifei Li; Zirui Wang; Paul Teiletche; Lesheng Jin; Matei Zaharia; Joseph E Gonzalez; Sewon Min
Multimodal Retrieval QA Read or Look? Textification Safety Boundaries for Efficient Multimodal Document QA βœ— Pan Xie
Multimodal Retrieval QA What Do Chart Question Answering Benchmarks Measure? Task-Specific Visual Dependence in Efficient Multimodal QA βœ“ Mary Le
Visual Token Efficiency One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QA βœ— Zhi Zheng; Ziqiao Meng; Hao Luan; Wei Liu; Wee Sun Lee
Visual Token Efficiency A Picture is Worth a Thousand Tokens: A Practitioner’s Guide to Visual Token Compression βœ— Vipul Joshi; Vikash Sharma; Amir Raza; Peyush Jain; Mayank Jauhari; Anurag Tripathi
Visual Token Efficiency Efficient Visual Token Compression for 3D Question Answering βœ— Changwoo Baek; Kyeongbo Kong
Visual Token Efficiency LARE: Low-Attention Region Encoding for Text–Image Retrieval βœ“ Muhammad K Khan; Abdulmalik Alquwayfili; Faisal AlMeshal; Jumanah Almajnouni; Leena Alotaibi; Huda A Alamri; Raied Aljadaany; Faisal alhajari; Alreem Almuhrij; Mohammed Alkhrashi; Abdullah Aldwyish
Data-Efficient QA ▢️ Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment βœ“ HARIKRISHNAN PUTHAN MADATHIL; Goutham Vignesh; Ganesh Parab; Saisubramaniam Gopalakrishnan; Vishal Vaddina; Varun V; Rohit Agrawal
Data-Efficient QA Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols βœ— Yosub Shin; Michael Buriek; Boris Sobolev; Pavel Bushuyeu; Vikas Kumar; Samuel Watson; Haoyang Xu; Igor Molybog
Confidence and Abstention Confidence-Aware Incremental Multimodal QA with Early Exit Reasoning βœ— Kaustubha V; Shravan K; Harini S
Confidence and Abstention Calibrated Confidence Is Hard to Beat: A Negative Result on Evidence-Accumulation Buzzing for Zero-Shot Incremental Question Answering βœ— Arihant Jain
Confidence and Abstention Cheap When Confident: The Per-Model Limits of Selective Answering in Multimodal Geometry QA βœ“ Vipra Bindal
Confidence and Abstention Context-Aware Conformal Prediction for VLM-Based Driving Scene QA βœ“ Yang-Jun Joo; Younggun Kim; Sung-Yeon Park; Mohamed Abdel-Aty
Medical QA Answer, Clarify, or Abstain: Fine-Grained Selective Prediction for Medical VLMs βœ— Duy A Nguyen; Tuan T Nguyen; Minh Do; Khoa Doan
Medical QA Efficient Multimodal Clinical Question Answering for Pulmonary Embolism Risk Assessment βœ“ Xiangyuan Xue; Yang Yu; Yan Gao; Junyan Wang; Bin Chen; Lingyan Ruan; Ting Dang; Hong Jia
Medical QA Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering βœ— Xupeng Chen; Binbin Shi; Chenqian Le; Jiaqi Zhang; Kewen Wang; Ran Gong; Jinhan Zhang; Chihang Wang
Medical QA Pocket-Dentist: Efficient Multimodal QA for On-Device Dental Image Understanding βœ“ Kai Bian; Xucheng Guo; Lingyan Ruan; Bin Chen; Yiran Shen; Ting Dang; Hong Jia
Missing Modality QA Recovering a Missing Modality in Multimodal QA via Low-Rank Completion βœ“ Jing Wang; Huan Xu; Jie Shen
VLM Robustness Benchmarks DistortBench: Benchmarking Vision Language Models on Image Distortion Identification βœ“ Divyanshu Goyal; Akhil Eppa; Vanya Bannihatti Kumar
VLM Robustness Benchmarks AMVICC: A Novel Benchmark for Cross-Modal Failure Mode Profiling for VLMs and IGMs βœ— Pranay Goel; Aahana Basappa; Anusri Karra; Anish Karra; Kevin Zhu
VLM Robustness Benchmarks VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following βœ— Hyesoo Hong; Min Soo Kim; Wonje Jeung; Sangyeon Yoon; Dongjae Jeon; Albert No
VLM Failure Analysis Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models βœ— Oscar Chew; Serhii Honcharenko; Qian-Hui Chen; Patricia Lu; Dishant P Zaveri; Khoa Doan; Kuan-Hao Huang
VLM Failure Analysis Detection-Guided Attention Steering for Vision Language Models βœ“ Alan W Zhang; Rui Pan; Mike Wong; Ravi Netravali
VLM Failure Analysis Mirage Probes: Selective Construction of False Images in Vision Language Model Inference βœ— Daniel Ben-Levi; Judah A Goldfeder; Weiliang Zhao; Raz Lapid; Amit LeVi; Allen Roush; Ravid Shwartz-Ziv; Hod Lipson
Temporal Multimodal Understanding WorldMemArena: Evaluating Multimodal Agent Memory Through Action–World Interaction βœ— Chengzhi Liu; Yuzhe YANG; Sophia X Pu; Yepeng Liu; Lin Long; Yichen Guo; Nuo Chen; zhaotian Weng; yiheng zhong; Angxiao Zong; Elena Kochkina; Simerjot Kaur; Charese Smiley; Xiaomo Liu; James Zou; Sheng Liu; Yuheng Bu; Songyou Peng; Xin (Eric) Wang
Temporal Multimodal Understanding Multimodal Hidden Markov Models for Persistent Emotional State Tracking βœ— Anamika Ragu; Aneesh Jonelagadda
Temporal Multimodal Understanding Augmenting Video Models with Pose Tokens for Human-Centric Understanding βœ— Isabella Zhu; Stella Su; David Dai; Paul Pu Liang
Generative Media Detection Position: Efficient Dual-View AI-Generated Video Detection Needs a Visual-Language Dual View βœ— Dylan Xinming Hou; Juntian Zhang; Xu Gu; Yichen WU; Nils Lukas; Gus xia; Xiuying Chen; Yuhan Liu
Text-to-Image Evaluation FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models βœ— Youngsun Lim; Cusuh Ham; Pin-Yu Chen; Deepti Ghadiyaram
Text-to-Image Evaluation CCDiff: Inverse Canonical Correlation Analysis for Discovering Visual Differences in Natural Language βœ— Neelesh Bisht; Xingjian Li; Zihan Li; Bo Jiang; RUNMIN JIANG; Mostofa Rafid Uddin; Yang Liu; Min Xu
Multimodal Generation Tools MMDiff: Multimodal Model Diffing for Feature Discovery and Control βœ— Lachin Naghashyar; Hunar Batra; Ashkan Khakzar; Phil Torr; Ronald Clark; Christian Schroeder de Witt; Constantin Venhoff
Multimodal Generation Tools Any2Poster: Any-Source Poster Generation Across Modalities and Domains βœ— Amogh Vinaykumar; Suozhi Huang; Aiden Y Li; Shilong Liu
Multimodal Generation Tools From Synopsis to Storyboard: Enhancing Prompt Expressiveness for Multi-shot Video Generation βœ— Xu Gu; Yuhan Liu; Wei Ji; Ruihua Song; Roger Zimmermann
Reasoning Evaluation Auditable Step Verification for Vision-Language Reasoning βœ— Shervin Ghasemlou
Reasoning Evaluation Does Verbose Chain-of-Thought Really Help? A Dual-Validator Replication and Mechanistic Analysis βœ— Wenlong Wang; Fergal Reid
Reasoning Evaluation The Shape of Overthinking: Backtracking Bursts in Long Reasoning Traces βœ— Navid Rezazadeh; Arash Gholamidavoodi
Reasoning Evaluation Can LLMs Reconstruct Why an Answer Is Correct? A Step-Level Evaluation of Answer-Conditioned Reasoning βœ“ Lei Sun
Reasoning Evaluation Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning βœ— Noor Islam S. Mohammad; Mahmudul Hasan
Model Alignment Co-LoRA: Collaborative Model Personalization on Heterogeneous Multi-Modal Clients βœ— Minhyuk Seo; Taeheon Kim; Hankook Lee; Jonghyun Choi; Tinne Tuytelaars
Model Alignment SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport βœ— Simon Roschmann; Paul KRZAKALA; Sonia Mazelet; Quentin Bouniot; Zeynep Akata