# Accelerating Multi-modal LLM Gaming Performance via Input Prediction and Mishit Correction

arXiv: https://arxiv.org/abs/2512.17250 · HTML: https://mlsanity.com/paper/2512.17250/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 15 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Residual Policy Learning](https://mlsanity.com/paper/1812.06298/) (2018)
- [Elastic Decision Transformer](https://mlsanity.com/paper/2307.02484/) (2023)
- [You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model](https://mlsanity.com/paper/2211.11152/) (2022)
- [FREE: Fast and Robust Vision Language Models with Early Exits](https://mlsanity.com/paper/2506.06884/) (2025)
- [Decision Transformer under Random Frame Dropping](https://mlsanity.com/paper/2303.03391/) (2023)
- [Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs](https://mlsanity.com/paper/2505.19481/) (2025)
- [Predictive Coding for Decision Transformer](https://mlsanity.com/paper/2410.03408/) (2024)

## Built on by (most cited first, 3 of 3)

- [SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning](https://mlsanity.com/paper/2603.23483/) (2026)
- [Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC](https://mlsanity.com/paper/2609.32591/) (2026)
- [Separating Decision Time from Decision Quality in the Real-Time Gap of Distilled Deciders: Evidence from a Game and a Conveyor Simulator](https://mlsanity.com/paper/2610.04810/) (2026)

## Abstract (arXiv)

Real-time sequential control agents are often bottlenecked by inference latency. Even modest per-step planning delays can destabilize control and degrade overall performance. We propose a speculation-and-correction framework that adapts the predict-then-verify philosophy of speculative execution to model-based control with TD-MPC2. At each step, a pretrained world model and latent-space MPC planner generate a short-horizon action queue together with predicted latent rollouts, allowing the agent to execute multiple planned actions without immediate replanning. When a new observation arrives, the system measures the mismatch between the encoded real latent state and the queued predicted latent. For small to moderate mismatch, a lightweight learned corrector applies a residual update to the speculative action, distilled offline from a replanning teacher. For large mismatch, the agent safely falls back to full replanning and clears stale action queues. We study both a gated two-tower MLP corrector and a temporal Transformer corrector to address local errors and systematic drift. Experiments on the DMC Humanoid-Walk task show that our method reduces the number of planning inferences from 500 to 282, improves end-to-end step latency by 25 percent, and maintains strong control performance with only a 7.1 percent return reduction. Ablation results demonstrate that speculative execution without correction is unreliable over longer horizons, highlighting the necessity of mismatch-aware correction for robust latency reduction.