# Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models

arXiv: https://arxiv.org/abs/2411.02564 · HTML: https://mlsanity.com/paper/2411.02564/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 91 of its 111 references that are in the map.
- First posted on arXiv 4 Nov 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 91)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)

## Built on by (most cited first, 22 of 22)

- [SEFE: Superficial and Essential Forgetting Eliminator for Multimodal Continual Instruction Tuning](https://mlsanity.com/paper/2505.02486/) (2025)
- [Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning](https://mlsanity.com/paper/2506.11672/) (2025)
- [MLLM-CL: Continual Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2506.05453/) (2025)
- [PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos](https://mlsanity.com/paper/2412.01800/) (2024)
- [Bisecle: Binding and Separation in Continual Learning for Video Language Understanding](https://mlsanity.com/paper/2507.00469/) (2025)
- [Federated Continual Instruction Tuning](https://mlsanity.com/paper/2503.12897/) (2025)
- [When Continue Learning Meets Multimodal Large Language Model: A Survey](https://mlsanity.com/paper/2503.01887/) (2025)
- [EACO: Enhancing Alignment in Multimodal LLMs via Critical Observation](https://mlsanity.com/paper/2412.04903/) (2024)
- [SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning](https://mlsanity.com/paper/2602.01990/) (2026)
- [IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting](https://mlsanity.com/paper/2503.20612/) (2025)
- [Video Spatial Reasoning with Object-Centric 3D Rollout](https://mlsanity.com/paper/2511.13190/) (2025)
- [Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models](https://mlsanity.com/paper/2512.03125/) (2025)
- [φ-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models](https://mlsanity.com/paper/2602.22601/) (2026)
- [On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models](https://mlsanity.com/paper/2603.27481/) (2026)
- [Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning](https://mlsanity.com/paper/2605.10765/) (2026)
- [The Blind Spot of Adaptation: Quantifying and Mitigating Forgetting in Fine-tuned Driving Models](https://mlsanity.com/paper/2604.04857/) (2026)
- [Octopus: History-Free Gradient Orthogonalization for Continual Learning in Multimodal Large Language Models](https://mlsanity.com/paper/2605.14938/) (2026)
- [Hidden Forgetting in Continual Multimodal Learning: When Accuracy Survives but Grounding Fails](https://mlsanity.com/paper/2607.02020/) (2026)
- [Listen, Look, and Learn: Learning Without Forgetting through SAM-Audio](https://mlsanity.com/paper/2606.10887/) (2026)
- [ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation](https://mlsanity.com/paper/2606.12633/) (2026)
- [Curvature-Guided Mixing for MLLM Adaptation](https://mlsanity.com/paper/2606.24963/) (2026)
- [Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction Tuning](https://mlsanity.com/paper/2609.13742/) (2026)

## Abstract (arXiv)

Instruction tuning constitutes a prevalent technique for tailoring Large Vision Language Models (LVLMs) to meet individual task requirements. To date, most of the existing approaches are confined to single-task adaptation, whereas the requirements in real-world scenarios are inherently varied and continually evolving. Thus an ideal LVLM should sustain continual instruction tuning in the face of stream-task distributions (i.e., different domains, emerging capabilities, and new datasets) while minimizing the forgetting of previously acquired knowledge. To achieve this, we propose a new benchmark for COntinuAl inStruction Tuning on LVLMs (COAST), which encompasses the aforementioned domain-incremental, capability-incremental, and dataset-incremental configurations. In terms of methodology, we propose Continual LLaVA, a rehearsal-free method tailored for continual instruction tuning in LVLMs. To circumvent the additional overhead associated with experience replay, we freeze LVLMs and construct the dual increment embeddings for each input instruction to facilitate parameter-efficient tuning. Specifically, the increment embeddings can be decomposed into two principal components: 1) intrinsic increment embeddings to encode task-specific characteristics. To achieve this, we set up a low-rank pool containing candidate embeddings, from which we select the relevant ones based on their similarity with the user instructions; 2) contextual increment embeddings to investigate the inter-dependencies across tasks. In this regard, the low-rank embeddings chosen in the previous tasks are aggregated via learnable weighted sum to provide complementary hints. Extensive experiments indicate that the proposed Continual LLaVA outperforms previous methods by significantly reducing the forgetting during the continual instruction tuning process.