mlsanityData to 14 Oct 2026

Uni-Retrieval: A Multi-Style Retrieval Framework for STEM's Education

arXiv 2502.05863 ↗First posted 9 Feb 2025cs.IR cs.AI cs.MMcited by 13

Not on the map. Why?

Abstract (arXiv)

In AI-facilitated teaching, leveraging various query styles to interpret abstract text descriptions is crucial for ensuring high-quality teaching. However, current retrieval models primarily focus on natural text-image retrieval, making them insufficiently tailored to educational scenarios due to the ambiguities in the retrieval process. In this paper, we propose a diverse expression retrieval task tailored to educational scenarios, supporting retrieval based on multiple query styles and expressions. We introduce the STEM Education Retrieval Dataset (SER), which contains over 24,000 query pairs of different styles, and the Uni-Retrieval, an efficient and style-diversified retrieval vision-language model based on prompt tuning. Uni-Retrieval extracts query style features as prototypes and builds a continuously updated Prompt Bank containing prompt tokens for diverse queries. This bank can updated during test time to represent domain-specific knowledge for different subject retrieval scenarios. Our framework demonstrates scalability and robustness by dynamically retrieving prompt tokens based on prototype similarity, effectively facilitating learning for unknown queries. Experimental results indicate that Uni-Retrieval outperforms existing retrieval models in most retrieval tasks. This advancement provides a scalable and precise solution for diverse educational needs.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 45 of its 78 references that are in the map. First posted on arXiv 9 Feb 2025.

Builds on

45 of 78 references.

References · 45

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  6. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  7. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  8. 2024GPT-4o System Cardcited by 4,588
  9. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  10. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  11. 2020The Pile: An 800GB Dataset of Diverse Text for Language Modelingcited by 2,411
  12. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
33 more
  1. 2021Learning to Prompt for Continual Learningcited by 944
  2. 2017An Overview of Multi-Task Learning in Deep Neural Networkscited by 803
  3. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  4. 2022A Survey on In-context Learningcited by 721
  5. 2023LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignmentcited by 370
  6. 2024Learning to (Learn at Test Time): RNNs with Expressive Hidden Statescited by 355
  7. 2023PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimizationcited by 316
  8. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 302
  9. 2020A Brief Review of Domain Adaptationcited by 288
  10. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  11. 2024Large Language Models for Education: A Survey and Outlookcited by 188
  12. 2019EdNet: A Large-Scale Hierarchical Dataset in Educationcited by 108
  13. 2023Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Modelscited by 94
  14. 2021Deep Learning for Instance Retrieval: A Surveycited by 70
  15. 2020SketchyCOCO: Image Generation from Freehand Scene Sketchescited by 67
  16. 2024VISTA: Visualized Text Embedding For Universal Multi-Modal Retrievalcited by 67
  17. 2019Cross-modal Scene Graph Matching for Relationship-aware Image-Text Retrievalcited by 66
  18. 2022Pro-tuning: Unified Prompt Tuning for Vision Taskscited by 53
  19. 2024Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learningcited by 53
  20. 2016Trace Norm Regularised Deep Multi-Task Learningcited by 50
  21. 2022FS-COCO: Towards Understanding of Freehand Sketches of Common Objects in Contextcited by 49
  22. 2023Prompt Optimization via Adversarial In-Context Learningcited by 33
  23. 2022SceneTrilogy: On Human Scene-Sketch and its Complementarity with Photo and Textcited by 30
  24. 2022Probabilistic Compositional Embeddings for Multimodal Image Retrievalcited by 29
  25. 2024Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyondcited by 28
  26. 2024Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillationcited by 27
  27. 2024Interactive Text-to-Image Retrieval with Large Language Models: A Plug-and-Play Approachcited by 25
  28. 2023FreestyleRet: Retrieving Images from Style-Diversified Queriescited by 20
  29. 2022UnifieR: A Unified Retriever for Large-Scale Retrievalcited by 19
  30. 2023FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memorycited by 11
  31. 2024BIPED: Pedagogically Informed Tutoring System for ESL Educationcited by 7
  32. 2020Structured Visual Search via Composition-aware Learningcited by 5
  33. 2016Generating Holistic 3D Scene Abstractions for Text-based Image Retrievalcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 3.

13 papers.

Sort:

By area:

  1. 2025VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documentscited by 116
  2. 2025UNIDOC-BENCH: A Unified Benchmark for Document-Centric Multimodal RAGcited by 21
  3. 2025Towards Robust Evaluation of STEM Education: Leveraging MLLMs in Project-Based Learningcited by 7
  4. 2025How to Detect and Defeat Molecular Mirage: A Metric-Driven Benchmark for Hallucination in LLM-based Molecular Comprehensioncited by 6
  5. 2025Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysiscited by 6
  6. 2025P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMscited by 6
  7. 2025Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systemscited by 4
  8. 2025Affective-ROPTester: Capability and Bias Analysis of LLMs in Predicting Retinopathy of Prematuritycited by 3
  9. 2025From Query to Explanation: Uni-RAG for Multi-Modal Retrieval-Augmented Learning in STEMcited by 2
  10. 2025Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Modelscited by 1
  11. 2026EduStory: A Unified Framework for Pedagogically-Consistent Multi-Shot STEM Instructional Video Generationcited by 1
  12. 2026Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shiftscited by 0
1 more
  1. 2026MMOE: Modernizing Diffusion Transformers with Efficient Expert Designcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education
  2. 2025From Slides to Chatbots: Enhancing Large Language Models with University Course Materials
  3. 2025Towards an Efficient, Customizable, and Accessible AI Tutor
  4. 2025An Open-Source Dual-Loss Embedding Model for Semantic Retrieval in Higher Education
  5. 2026CHSR-RRF: A curriculum-gated hybrid retrieval framework with reciprocal rank fusion and leakage-aware benchmarking for educational RAG
  6. 2025Aligning LLMs for the Classroom with Knowledge-Based Retrieval -- A Comparative RAG Study
  7. 2025Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook
  8. 2023How to Build an Adaptive AI Tutor for Any Course Using Knowledge Graph-Enhanced Retrieval-Augmented Generation (KG-RAG)