Beyond Token Accuracy: Prioritizing What Matters for Visual Reconstruction
cs.CV
Submitted: 2026-10-02
Updated: 2026-10-02
Terminology
Sources
- DeepJSCC-l++: Robust and Bandwidth-Adaptive Wireless Image Transmission
- Joint Coding-Modulation for Digital Semantic Communications via Variational Autoencoder
- Chameleon: Mixed-Modal Early-Fusion Foundation Models
- Muse: Text-To-Image Generation via Masked Generative Transformers
- Nonlinear Transform Source-Channel Coding for Semantic Communications
- Generative Joint Source-Channel Coding for Semantic Image Transmission
- Taming Transformers for High-Resolution Image Synthesis
- Improved Masked Image Generation with Token-Critic
- MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis
- TONIC: Token-Centric Semantic Communication for Task-Oriented Wireless Systems
- Token Communications: A Large Model-Driven Framework for Cross-modal Context-aware Semantic Communications
- Zero-Shot Text-to-Image Generation
- Generating Diverse High-Fidelity Images with VQ-VAE-2
- Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
- DeepJSCC-Q: Constellation Constrained Deep Joint Source-Channel Coding
- Neural Discrete Representation Learning
- DiffCom: Channel Received Signal is a Natural Condition to Guide Diffusion Posterior Sampling
- Emu3: Next-Token Prediction is All You Need
- Deep Joint Source-Channel Coding for Adaptive Image Transmission over MIMO Channels
- Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models