CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning

arXiv:2606.02502 · cs.CL · Submitted 2026-06-01 · Read on arXiv

cs.CL

Submitted: 2026-06-01

Updated: 2026-08-28

Comments: Accepted to EMNLP 2026 (Main Conference). Code is available at https://github.com/LAMDA-CL/EMNLP2026-CRAM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Instruction Tuning — 36× in this paper · explained in 2 episodes
• Benchmark — 26× in this paper · explained in 2 episodes
• Adaptation — 19× in this paper · explained in 1 episode
• Accuracy — 17× in this paper · explained in 1 episode
• Catastrophic Forgetting — 12× in this paper · explained in 5 episodes
• Multimodal Continual Instruction Tuning — 11× in this paper
• Parameter Efficiency — 10× in this paper · explained in 3 episodes
• Continual Learning — 7× in this paper · explained in 2 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Aggregation — 5× in this paper · explained in 1 episode
• Embeddings — 5× in this paper · explained in 2 episodes
• Decoupling — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Clustering — 3× in this paper · explained in 2 episodes
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Distribution Shift — 2× in this paper · explained in 5 episodes
• LoRA Adapters — 2× in this paper · explained in 3 episodes
• Adam — 1× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Centroid Routing Adaptive MoE — 1× in this paper
• Decode — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Mixture of Experts — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning — 1× in this paper · explained in 2 episodes
• Parameter-Efficient Fine-Tuning (PEFT) — 1× in this paper · explained in 4 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark
• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Continual LLaVA: Continual Instruction Tuning in Large Vision-Language Models
• When Continue Learning Meets Multimodal Large Language Model: A Survey
• Dynamic Mixture of Curriculum LoRA Experts for Continual Multimodal Instruction Tuning
• OASIS: Online Sample Selection for Continual Visual Instruction Tuning
• Large Continual Instruction Assistant
• Multimodal Continual Instruction Tuning with Dynamic Gradient Guidance
• CLEVR-Math: A Dataset for Compositional Language, Visual and Mathematical Reasoning
• LLaVA-c: Continual Improved Visual Instruction Tuning
• Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
• A Practitioner's Guide to Continual Multimodal Pretraining
• IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning
• Prism: A Plug-in Reproducible Infrastructure for Scalable Multimodal Continual Instruction Tuning
• PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
• LoKI: Low-damage Knowledge Implanting of Large Language Models
• LLaVA-CMoE: Towards Continual Mixture of Experts for Large Vision-Language Models
• Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs
• MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
• SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering