# Baseline-Relative Counterfactual Refinement for Bit-Aware Visual Token Communication

arXiv: https://arxiv.org/abs/2608.16192 · HTML: https://mlsanity.com/paper/2608.16192/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 17 Aug 2026.

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

- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation](https://mlsanity.com/paper/2406.06525/) (2024)
- [Joint Autoregressive and Hierarchical Priors for Learned Image Compression](https://mlsanity.com/paper/1809.02736/) (2018)
- [Deep Learning Enabled Semantic Communication Systems](https://mlsanity.com/paper/2006.10685/) (2020)
- [DivPrune: Diversity-based Visual Token Pruning for Large Multimodal Models](https://mlsanity.com/paper/2503.02175/) (2025)
- [Sionna: An Open-Source Library for Next-Generation Physical Layer Research](https://mlsanity.com/paper/2203.11854/) (2022)
- [Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models](https://mlsanity.com/paper/2409.10197/) (2024)
- [ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models](https://mlsanity.com/paper/2412.00447/) (2024)
- [VoCo-LLaMA: Towards Vision Compression with Large Language Models](https://mlsanity.com/paper/2406.12275/) (2024)
- [PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models](https://mlsanity.com/paper/2504.08966/) (2025)
- [Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration](https://mlsanity.com/paper/2412.13180/) (2024)
- [Language-Guided Image Tokenization for Generation](https://mlsanity.com/paper/2412.05796/) (2024)
- [Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM](https://mlsanity.com/paper/2412.09530/) (2024)
- [Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters](https://mlsanity.com/paper/2411.03312/) (2024)
- [PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models](https://mlsanity.com/paper/2412.09613/) (2024)
- [Token Cropr: Faster ViTs for Quite a Few Tasks](https://mlsanity.com/paper/2412.00965/) (2024)
- [Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing](https://mlsanity.com/paper/2503.10742/) (2025)
- [Adaptive Semantic Token Communication for Transformer-based Edge Inference](https://mlsanity.com/paper/2505.17604/) (2025)
- [CROP: Contextual Region-Oriented Visual Token Pruning](https://mlsanity.com/paper/2505.21233/) (2025)
- [Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping](https://mlsanity.com/paper/2503.21817/) (2025)
- [Generative Model Based Highly Efficient Semantic Communication Approach for Image Transmission](https://mlsanity.com/paper/2211.10287/) (2022)
- [Representation Shift: Unifying Token Compression with FlashAttention](https://mlsanity.com/paper/2508.00367/) (2025)
- [SQ-GAN: Semantic Image Communications Using Masked Vector Quantization](https://mlsanity.com/paper/2502.09520/) (2025)
- [Faster Parameter-Efficient Tuning with Token Redundancy Reduction](https://mlsanity.com/paper/2503.20282/) (2025)
- [Energy-Driven Adaptive Visual Token Pruning for Efficient Vision-Language Models](https://mlsanity.com/paper/2603.05950/) (2026)
- [RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference](https://mlsanity.com/paper/2605.00392/) (2026)
- [Biased Aggregation, Rollout, and Enhanced Policy Improvement for Reinforcement Learning](https://mlsanity.com/paper/1910.02426/) (2019)

## Built on by (most cited first, 1 of 1)

- [Selective Amortization of Full-Budget Counterfactual Reasoning for Visual Token Communication](https://mlsanity.com/paper/2609.30756/) (2026)

## Abstract (arXiv)

Generative visual-token communication reduces transmission load by sending only selected discrete tokens and reconstructing missing content at the receiver. However, existing token-selection criteria based on local uncertainty, importance, or diversity do not directly determine whether changing the current selection improves the final reconstruction under the same packet budget. To address this problem, we propose Gated Counterfactual Refinement for Communication (GCR-C), a rollout-style correction layer over Local-MDL. GCR-C constructs a compact diversified candidate set, evaluates each candidate through matched full-budget Local-MDL continuation, and replaces the baseline action only when a positive baseline-relative reconstruction gain is obtained. Experiments on CIFAR-10, STL-10, a coded 5G-LDPC link, and a limited high-resolution Kodak transfer show that GCR-C consistently improves reconstruction quality at active low- and medium-rate operating points without increasing the realized packet rate, while remaining effective across changes in dataset, channel condition, resolution, token grid, and tokenizer. The results also reveal a clear quality--computation tradeoff due to the additional encoder-side counterfactual evaluation.