# Beyond Token Accuracy: Prioritizing What Matters for Visual Reconstruction

arXiv: https://arxiv.org/abs/2610.03822 · HTML: https://mlsanity.com/paper/2610.03822/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 36 of its 41 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Chameleon: Mixed-Modal Early-Fusion Foundation Models](https://mlsanity.com/paper/2405.09818/) (2024)
- [Emu3: Next-Token Prediction is All You Need](https://mlsanity.com/paper/2409.18869/) (2024)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis](https://mlsanity.com/paper/2211.09117/) (2022)
- [DeepJSCC-f: Deep Joint Source-Channel Coding of Images with Feedback](https://mlsanity.com/paper/1911.11174/) (2019)
- [Nonlinear Transform Source-Channel Coding for Semantic Communications](https://mlsanity.com/paper/2112.10961/) (2021)
- [Improved Masked Image Generation with Token-Critic](https://mlsanity.com/paper/2209.04439/) (2022)
- [CDDM: Channel Denoising Diffusion Models for Wireless Semantic Communications](https://mlsanity.com/paper/2309.08895/) (2023)
- [Generative Joint Source-Channel Coding for Semantic Image Transmission](https://mlsanity.com/paper/2211.13772/) (2022)
- [Robust Semantic Communications with Masked VQ-VAE Enabled Codebook](https://mlsanity.com/paper/2206.04011/) (2022)
- [SwinJSCC: Taming Swin Transformer for Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2308.09361/) (2023)
- [Bandwidth-Agile Image Transmission with Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2009.12480/) (2020)
- [DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding](https://mlsanity.com/paper/2206.08100/) (2022)
- [WITT: A Wireless Image Transmission Transformer for Semantic Communications](https://mlsanity.com/paper/2211.00937/) (2022)
- [Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications](https://mlsanity.com/paper/2502.12096/) (2025)
- [Deep Joint Source-Channel Coding for Adaptive Image Transmission over MIMO Channels](https://mlsanity.com/paper/2309.00470/) (2023)
- [OFDM-guided Deep Joint Source Channel Coding for Wireless Multipath Fading Channels](https://mlsanity.com/paper/2109.05194/) (2021)
- [Channel-Adaptive Wireless Image Transmission with OFDM](https://mlsanity.com/paper/2205.02417/) (2022)
- [Joint Coding-Modulation for Digital Semantic Communications via Variational Autoencoder](https://mlsanity.com/paper/2310.06690/) (2023)

## Abstract (arXiv)

Tokens have become a unified interface for multimodal foundation models, making visual-token communication a natural paradigm for efficient image delivery. However, existing methods typically rely on static policies that cannot jointly adapt to image content and channel conditions. Moreover, their token-level utility objectives do not necessarily translate into improved image reconstruction quality. In this paper, we propose AdapToC, an adaptive, reconstruction-oriented visual-token communication framework. At the transmitter, an adaptive selector jointly models image content, channel state, and communication budget to perform instance-wise resource allocation. Rather than using a fixed token rate and protection policy, it dynamically determines how many tokens should be transmitted and assigns different protection levels according to token importance and current channel conditions. At the receiver, an adaptive MaskGIT receiver incorporates channel reliability into contextual token modeling. It distinguishes tokens with different reliability levels, preserves high-confidence observations, corrects potentially corrupted tokens, and iteratively reconstructs missing content from the received evidence and global visual context. By co-designing token quantity, unequal protection, and reliability-aware recovery for image-level reconstruction quality, AdapToC achieves a peak mean PSNR gain of 4.20 dB over the strongest static baseline under matched communication costs and state-of-the-art performance among the evaluated visual-token communication methods.