# Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning

arXiv: https://arxiv.org/abs/2511.13351 · HTML: https://mlsanity.com/paper/2511.13351/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 23 of 23)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Orthogonal Gradient Descent for Continual Learning](https://mlsanity.com/paper/1910.07104/) (2019)
- [Orthogonal Subspace Learning for Language Model Continual Learning](https://mlsanity.com/paper/2310.14152/) (2023)
- [Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning](https://mlsanity.com/paper/1904.03137/) (2019)
- [Continual Learning of Context-dependent Processing in Neural Networks](https://mlsanity.com/paper/1810.01256/) (2018)
- [Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models](https://mlsanity.com/paper/2303.06628/) (2023)
- [Generative Feature Replay For Class-Incremental Learning](https://mlsanity.com/paper/2004.09199/) (2020)
- [CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks](https://mlsanity.com/paper/2206.09059/) (2022)
- [Nutrition5k: Towards Automatic Nutritional Understanding of Generic Food](https://mlsanity.com/paper/2103.03375/) (2021)
- [Recent Advances of Multimodal Continual Learning: A Comprehensive Survey](https://mlsanity.com/paper/2410.05352/) (2024)
- [FoodLMM: A Versatile Food Assistant using Large Multi-modal Model](https://mlsanity.com/paper/2312.14991/) (2023)
- [FIRE: Food Image to REcipe generation](https://mlsanity.com/paper/2308.14391/) (2023)
- [RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models](https://mlsanity.com/paper/2407.12730/) (2024)
- [Enhancing Recipe Retrieval with Foundation Models: A Data Augmentation Perspective](https://mlsanity.com/paper/2312.04763/) (2023)
- [Advancing Food Nutrition Estimation via Visual-Ingredient Feature Fusion](https://mlsanity.com/paper/2505.08747/) (2025)
- [Retrieval Augmented Recipe Generation](https://mlsanity.com/paper/2411.08715/) (2024)

## Built on by (most cited first, 1 of 1)

- [ReGraph: Learning to Generate Recipe Graphs from Food Images](https://mlsanity.com/paper/2608.06917/) (2026)

## Abstract (arXiv)

Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastrophic forgetting when learning new tasks, requiring costly retraining from scratch. To address this, we propose a novel continual learning framework for multimodal food learning, integrating a Dual-LoRA architecture with Quality-Enhanced Pseudo Replay. We introduce two complementary low-rank adapters for each task: a specialized LoRA that learns task-specific knowledge with orthogonal constraints to previous tasks' subspaces, and a cooperative LoRA that consolidates shared knowledge across tasks via pseudo replay. To improve the reliability of replay data, our Quality-Enhanced Pseudo Replay strategy leverages self-consistency and semantic similarity to reduce hallucinations in generated samples. Experiments on the comprehensive Uni-Food dataset show superior performance in mitigating forgetting, representing the first effective continual learning approach for complex food tasks.