Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning

• URL: http://arxiv.org/abs/2605.10765v1
• Date: Mon, 11 May 2026 15:59:06 GMT
• Title: Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
• Abstract summary: DRAPE is a prompt-learning framework that synthesizes continuous instance-specific soft prompts for MCIT.<n>DRAPE achieves state-of-the-art performance among representative prompt-based and LoRA-based continual-learning baselines.
• Score: 13.499744113926505
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, yet real-world deployment often requires continual capability expansion across sequential tasks. In such scenarios, Multimodal Continual Instruction Tuning (MCIT) aims to acquire new capabilities while limiting catastrophic forgetting. Existing methods mainly follow a module-composition paradigm: they maintain task-level prompts or LoRA experts and dynamically route or aggregate a subset of them at inference. However, samples within the same task can still differ substantially in visual scenes, question intents, and reasoning demands. This motivates instance-level adaptation to individual query-image pairs rather than only selecting or combining task-level modules. To this end, we propose DRAPE (Dynamic Cross-Modal Prompt Generation), a prompt-learning framework that synthesizes continuous instance-specific soft prompts for MCIT. Instead of selecting prompts from a fixed pool, DRAPE derives prompt queries from the textual instruction and cross-attends to visual patch features, producing query-image conditioned prompts that are prepended to the frozen LLM. To mitigate forgetting during sequential updates, DRAPE applies null-space gradient projection to the shared projector and uses CLIP-based prototype routing for task-label-free generator selection at inference. Extensive experiments on MCIT benchmarks show that DRAPE achieves state-of-the-art performance among representative prompt-based and LoRA-based continual-learning baselines.

Related papers

• FRAMEWORKERS: A Dynamic Multi-Agent Framework for AI-Generated Video Production [55.71860113185132]
  We introduce FRAMEWORKERS, a task-centric and workspace-grounded multi-agent framework for open-ended video production.<n>A central Director formulates video creation as dynamic task management, continuously editing a Task Stack to determine which subtask to execute next and which sub-agent to invoke.<n>An Assistant serves as the execution layer, grounding each selected task in a shared Workspace, retrieving the required assets and context, invoking the assigned sub-agent, and persisting the resulting artifacts.<n>Experiments show that FRAMEWORKERS outperforms strong planners in routing accuracy, recovers reliably from runtime failures, generalizes to unseen sub
  arXiv  Detail & Related papers  (2026-08-30T14:28:50Z)
• InA-Probe: Instruction-Aware Active Probing for Time Series Forecasting with LLMs [45.91332553359387]
  Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting.<n>We propose Instruction-aware Active Probing (InA-Probe), which shifts the paradigm from passive alignment toward an active, instruction-driven probing mechanism.<n>In experiments, InA-Probe consistently outperforms state-of-the-art deep learning and LLM-based baselines.
  arXiv  Detail & Related papers  (2026-06-07T12:27:13Z)
• ProtoAda: Prototype-Guided Adaptive Adapter Expansion and Geometric Consolidation for Multimodal Continual Instruction Tuning [16.21619173438734]
  Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually acquire new vision-language capabilities.<n>Recent methods often employ sparse architectures like Mixture of LoRA Experts with image-text similarity routing.<n>We propose ProtoAda, a prototype-guided adaptive tuning framework.
  arXiv  Detail & Related papers  (2026-06-01T17:59:13Z)
• AR-MOT: Autoregressive Multi-object Tracking [56.09738000988466]
  We propose a novel autoregressive paradigm that formulates MOT as a sequence generation task within a large language model (LLM) framework.<n>This design enables the model to output structured results through flexible sequence construction, without requiring any task-specific heads.<n>To enhance region-level visual perception, we introduce an Object Tokenizer based on a pretrained detector.
  arXiv  Detail & Related papers  (2026-01-05T09:17:28Z)
• Teaching Prompts to Coordinate: Hierarchical Layer-Grouped Prompt Tuning for Continual Learning [69.17264556340244]
  We propose a novel hierarchical layer-grouped prompt tuning method for continual learning.<n>It improves model stability in two ways: (i) Layers in the same group share roughly the same prompts, which are adjusted by position encoding.<n>It utilizes a single task-specific root prompt to learn to generate sub-prompts for each layer group.
  arXiv  Detail & Related papers  (2025-11-15T08:15:51Z)
• TemPrompt: Multi-Task Prompt Learning for Temporal Relation Extraction in RAG-based Crowdsourcing Systems [21.312052922118585]
  Temporal relation extraction (TRE) aims to grasp the evolution of events or actions, and thus shape the workflow of associated tasks. We propose a multi-task prompt learning framework for TRE (TemPrompt), incorporating prompt tuning and contrastive learning to tackle these issues.
  arXiv  Detail & Related papers  (2024-06-21T01:52:37Z)
• Fine-tuning Large Language Models with Sequential Instructions [2.546845645875049]
  We find that existing instruction-tuned models struggle to respond to queries with multiple instructions. We contend that part of the fine-tuning data mixture should be sequential--containing a chain of interrelated tasks. We automate this process by turning instructions in existing datasets into diverse and complex sequential instructions. Models that underwent our sequential instruction tuning show improved results in coding, maths, and open-ended generation.
  arXiv  Detail & Related papers  (2024-03-12T16:33:30Z)
• SMAUG: A Sliding Multidimensional Task Window-Based MARL Framework for Adaptive Real-Time Subtask Recognition [11.236363226878975]
  Subtask-based multi-agent reinforcement learning (MARL) methods enable agents to learn how to tackle different subtasks. textbfSliding textbfMultidimensional ttextbfAsk window based mtextbfUti-agent reinforcement learnintextbfG framework (SMAUG) is proposed for adaptive real-time subtask recognition. Experiments on StarCraft II show that SMAUG not only demonstrates performance superiority in comparison with all baselines but also presents a more prominent and swift rise in rewards
  arXiv  Detail & Related papers  (2024-03-04T08:04:41Z)
• Self-regulating Prompts: Foundational Model Adaptation without Forgetting [112.66832145320434]
  We introduce a self-regularization framework for prompting called PromptSRC. PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations.
  arXiv  Detail & Related papers  (2023-07-13T17:59:35Z)
• Dynamic Prompting: A Unified Framework for Prompt Tuning [33.175097465669374]
  We present a unified dynamic prompt (DP) tuning strategy that dynamically determines different factors of prompts based on specific tasks and instances. Experimental results underscore the significant performance improvement achieved by dynamic prompt tuning across a wide range of tasks. We establish the universal applicability of our approach under full-data, few-shot, and multitask scenarios.
  arXiv  Detail & Related papers  (2023-03-06T06:04:46Z)
• Prompting Decision Transformer for Few-Shot Policy Generalization [98.0914217850999]
  We propose a Prompt-based Decision Transformer (Prompt-DT) to achieve few-shot adaptation in offline RL. Prompt-DT is a strong few-shot learner without any extra finetuning on unseen target tasks.
  arXiv  Detail & Related papers  (2022-06-27T17:59:17Z)
• Support-set based Multi-modal Representation Enhancement for Video Captioning [121.70886789958799]
  We propose a Support-set based Multi-modal Representation Enhancement (SMRE) model to mine rich information in a semantic subspace shared between samples. Specifically, we propose a Support-set Construction (SC) module to construct a support-set to learn underlying connections between samples and obtain semantic-related visual elements. During this process, we design a Semantic Space Transformation (SST) module to constrain relative distance and administrate multi-modal interactions in a self-supervised way.
  arXiv  Detail & Related papers  (2022-05-19T03:40:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.