# TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configuration

arXiv: https://arxiv.org/abs/2505.17098 · HTML: https://mlsanity.com/paper/2505.17098/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 61 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 34)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [A Survey on In-context Learning](https://mlsanity.com/paper/2301.00234/) (2022)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://mlsanity.com/paper/2005.04790/) (2020)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering](https://mlsanity.com/paper/2212.10375/) (2022)
- [What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning](https://mlsanity.com/paper/2305.09731/) (2023)
- [Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs](https://mlsanity.com/paper/2504.17432/) (2025)
- [Z-ICL: Zero-Shot In-Context Learning with Pseudo-Demonstrations](https://mlsanity.com/paper/2212.09865/) (2022)
- [In-context Learning with Retrieved Demonstrations for Language Models: A Survey](https://mlsanity.com/paper/2401.11624/) (2024)
- [Multimodal Neurons in Pretrained Text-Only Transformers](https://mlsanity.com/paper/2308.01544/) (2023)
- [An Information-Theoretic Analysis of In-Context Learning](https://mlsanity.com/paper/2401.15530/) (2024)
- [VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning](https://mlsanity.com/paper/2403.13164/) (2024)
- [M2IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering](https://mlsanity.com/paper/2504.04633/) (2025)
- [An Early Evaluation of GPT-4V(ision)](https://mlsanity.com/paper/2310.16534/) (2023)
- [Multimodal Language Models See Better When They Look Shallower](https://mlsanity.com/paper/2504.21447/) (2025)
- [In-Context Demonstration Selection with Cross Entropy Difference](https://mlsanity.com/paper/2305.14726/) (2023)
- [Learning to Retrieve Iteratively for In-Context Learning](https://mlsanity.com/paper/2406.14739/) (2024)
- [In-Context Learning Demonstration Selection via Influence Analysis](https://mlsanity.com/paper/2402.11750/) (2024)

## Built on by (most cited first, 23 of 23)

- [Causal Tracing of Object Representations in Large Vision Language Models: Mechanistic Interpretability and Hallucination Mitigation](https://mlsanity.com/paper/2511.05923/) (2025)
- [CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning](https://mlsanity.com/paper/2508.07871/) (2025)
- [True Multimodal In-Context Learning Needs Attention to the Visual Context](https://mlsanity.com/paper/2507.15807/) (2025)
- [TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval](https://mlsanity.com/paper/2604.21806/) (2026)
- [SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis](https://mlsanity.com/paper/2506.07603/) (2025)
- [MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs](https://mlsanity.com/paper/2508.10264/) (2025)
- [From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning](https://mlsanity.com/paper/2511.23031/) (2025)
- [FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapter](https://mlsanity.com/paper/2508.19639/) (2025)
- [Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs](https://mlsanity.com/paper/2511.08409/) (2025)
- [ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2605.05126/) (2026)
- [Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction](https://mlsanity.com/paper/2604.20311/) (2026)
- [Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrieval](https://mlsanity.com/paper/2509.09118/) (2025)
- [Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks](https://mlsanity.com/paper/2604.13403/) (2026)
- [ReLoop: "Seeing Twice and Thinking Backwards" via Closed-loop Training to Mitigate Hallucinations in Multimodal understanding](https://mlsanity.com/paper/2507.04943/) (2025)
- [STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignment](https://mlsanity.com/paper/2508.20944/) (2025)
- [Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification](https://mlsanity.com/paper/2510.24749/) (2025)
- [HIFICL: High-Fidelity In-Context Learning for Multimodal Tasks](https://mlsanity.com/paper/2603.12760/) (2026)
- [Balancing Multimodal Domain Generalization via Gradient Modulation and Projection](https://mlsanity.com/paper/2603.14175/) (2026)
- [Zero-shot Cross-lingual NER via Mitigating Language Difference: An Entity-aligned Translation Perspective](https://mlsanity.com/paper/2509.01147/) (2025)
- [UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning](https://mlsanity.com/paper/2604.05517/) (2026)
- [Gradient-free Task-Conditioned Retrieval for On-Device In-Context Learning](https://mlsanity.com/paper/2607.27766/) (2026)
- [MAG: MAnifold Guided Semi-Supervised Multi-modal In-Context Learning](https://mlsanity.com/paper/2608.12724/) (2026)
- [MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models](https://mlsanity.com/paper/2609.39920/) (2026)

## Abstract (arXiv)

Multimodal in-context learning (ICL) has emerged as a key mechanism for harnessing the capabilities of large vision-language models (LVLMs). However, its effectiveness remains highly sensitive to the quality of input ICL sequences, particularly for tasks involving complex reasoning or open-ended generation. A major limitation is our limited understanding of how LVLMs actually exploit these sequences during inference. To bridge this gap, we systematically interpret multimodal ICL through the lens of task mapping, which reveals how local and global relationships within and among demonstrations guide model reasoning. Building on this insight, we present TACO, a lightweight transformer-based model equipped with task-aware attention that dynamically configures ICL sequences. By injecting task-mapping signals into the autoregressive decoding process, TACO creates a bidirectional synergy between sequence construction and task reasoning. Experiments on five LVLMs and nine datasets demonstrate that TACO consistently surpasses baselines across diverse ICL tasks. These results position task mapping as a novel and valuable perspective for interpreting and improving multimodal ICL.