# Reconstructive Visual Instruction Tuning

arXiv: https://arxiv.org/abs/2410.09575 · HTML: https://mlsanity.com/paper/2410.09575/

## Key facts

- Cited by 55 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 78 of its 105 references that are in the map.
- First posted on arXiv 12 Oct 2024.

## 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 78)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [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)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)

## Built on by (most cited first, 30 of 55)

- [Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model](https://mlsanity.com/paper/2510.12276/) (2025)
- [DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving](https://mlsanity.com/paper/2510.12796/) (2025)
- [VGR: Visual Grounded Reasoning](https://mlsanity.com/paper/2506.11991/) (2025)
- [Traceable Evidence Enhanced Visual Grounded Reasoning: Evaluation and Methodology](https://mlsanity.com/paper/2507.07999/) (2025)
- [Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness](https://mlsanity.com/paper/2504.01901/) (2025)
- [Reconstruction Alignment Improves Unified Multimodal Models](https://mlsanity.com/paper/2509.07295/) (2025)
- [Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence](https://mlsanity.com/paper/2510.20579/) (2025)
- [Visual Representation Alignment for Multimodal Large Language Models](https://mlsanity.com/paper/2509.07979/) (2025)
- [TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models](https://mlsanity.com/paper/2512.02014/) (2025)
- [The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer](https://mlsanity.com/paper/2504.10462/) (2025)
- [Sketch-in-Latents: Eliciting Unified Reasoning in MLLMs](https://mlsanity.com/paper/2512.16584/) (2025)
- [Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)](https://mlsanity.com/paper/2504.03151/) (2025)
- [SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models](https://mlsanity.com/paper/2510.12784/) (2025)
- [Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation](https://mlsanity.com/paper/2503.15905/) (2025)
- [Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation](https://mlsanity.com/paper/2601.21406/) (2026)
- [Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding](https://mlsanity.com/paper/2502.11168/) (2025)
- [Grasp Any Region: Towards Precise, Contextual Pixel Understanding for Multimodal LLMs](https://mlsanity.com/paper/2510.18876/) (2025)
- [Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better](https://mlsanity.com/paper/2506.09040/) (2025)
- [GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers](https://mlsanity.com/paper/2503.19480/) (2025)
- [Unified Multimodal Models as Auto-Encoders](https://mlsanity.com/paper/2509.09666/) (2025)
- [VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization](https://mlsanity.com/paper/2505.10917/) (2025)
- [Hita: Holistic Tokenizer for Autoregressive Image Generation](https://mlsanity.com/paper/2507.02358/) (2025)
- [ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models](https://mlsanity.com/paper/2602.17951/) (2026)
- [MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs](https://mlsanity.com/paper/2511.07250/) (2025)
- [MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues](https://mlsanity.com/paper/2510.17722/) (2025)
- [Toward Graph-Tokenizing Large Language Models with Reconstructive Graph Instruction Tuning](https://mlsanity.com/paper/2603.01385/) (2026)
- [VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification](https://mlsanity.com/paper/2604.01569/) (2026)
- [Visual Instruction Bottleneck Tuning](https://mlsanity.com/paper/2505.13946/) (2025)
- [Seeing Beyond Words: Self-Supervised Visual Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2512.15885/) (2025)
- [AffordVLA: Injecting Affordance Representations into Vision-Language-Action Models via Implicit Feature Alignment](https://mlsanity.com/paper/2605.17517/) (2026)

## Abstract (arXiv)

This paper introduces reconstructive visual instruction tuning (ROSS), a family of Large Multimodal Models (LMMs) that exploit vision-centric supervision signals. In contrast to conventional visual instruction tuning approaches that exclusively supervise text outputs, ROSS prompts LMMs to supervise visual outputs via reconstructing input images. By doing so, it capitalizes on the inherent richness and detail present within input images themselves, which are often lost in pure text supervision. However, producing meaningful feedback from natural images is challenging due to the heavy spatial redundancy of visual signals. To address this issue, ROSS employs a denoising objective to reconstruct latent representations of input images, avoiding directly regressing exact raw RGB values. This intrinsic activation design inherently encourages LMMs to maintain image detail, thereby enhancing their fine-grained comprehension capabilities and reducing hallucinations. Empirically, ROSS consistently brings significant improvements across different visual encoders and language models. In comparison with extrinsic assistance state-of-the-art alternatives that aggregate multiple visual experts, ROSS delivers competitive performance with a single SigLIP visual encoder, demonstrating the efficacy of our vision-centric supervision tailored for visual outputs.