# PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation

arXiv: https://arxiv.org/abs/2602.15882 · HTML: https://mlsanity.com/paper/2602.15882/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 40 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 27 of 27)

- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://mlsanity.com/paper/2501.09747/) (2025)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [Vision-Language Foundation Models as Effective Robot Imitators](https://mlsanity.com/paper/2311.01378/) (2023)
- [An Image is Worth 32 Tokens for Reconstruction and Generation](https://mlsanity.com/paper/2406.07550/) (2024)
- [Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models](https://mlsanity.com/paper/2310.10639/) (2023)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation](https://mlsanity.com/paper/2508.19236/) (2025)
- [Learning to Act from Actionless Videos through Dense Correspondences](https://mlsanity.com/paper/2310.08576/) (2023)
- [VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching](https://mlsanity.com/paper/2502.02175/) (2025)
- [RynnVLA-002: A Unified Vision-Language-Action and World Model](https://mlsanity.com/paper/2511.17502/) (2025)
- [VideoVLA: Video Generators Can Be Generalizable Robot Manipulators](https://mlsanity.com/paper/2512.06963/) (2025)
- [Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens](https://mlsanity.com/paper/2501.07730/) (2025)
- [World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/2509.19080/) (2025)
- [ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context](https://mlsanity.com/paper/2510.04246/) (2025)
- [Inference-Time Enhancement of Generative Robot Policies via Predictive World Modeling](https://mlsanity.com/paper/2502.00622/) (2025)
- [RoboHorizon: An LLM-Assisted Multi-View World Model for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2501.06605/) (2025)
- [Efficient Long-Horizon Vision-Language-Action Models via Static-Dynamic Disentanglement](https://mlsanity.com/paper/2602.03983/) (2026)
- [AVR: Active Vision-Driven Precise Robot Manipulation with Viewpoint and Focal Length Optimization](https://mlsanity.com/paper/2503.01439/) (2025)
- [Exo-ViHa: A Cross-Platform Exoskeleton System with Visual and Haptic Feedback for Efficient Dexterous Skill Learning](https://mlsanity.com/paper/2503.01543/) (2025)

## Built on by (most cited first, 5 of 5)

- [The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook](https://mlsanity.com/paper/2604.02029/) (2026)
- [FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models](https://mlsanity.com/paper/2607.14739/) (2026)
- [ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation](https://mlsanity.com/paper/2605.30484/) (2026)
- [Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models](https://mlsanity.com/paper/2605.11459/) (2026)
- [ReWAM: Reciprocal World Action Models for Interactive Autonomous Driving](https://mlsanity.com/paper/2609.39245/) (2026)

## Abstract (arXiv)

Robot manipulation uses temporal context to select actions and visual foresight to assess their consequences, yet dense representations of past and future observations incur substantial processing costs. We introduce PACT-WAM, a world-action model that jointly generates a 16-step action trajectory and its temporally corresponding visual forecast through conditional flow sampling. Hierarchical history encoding assigns coarse spatial representations to earlier observations and finer representations to recent ones, retaining 16 observations with 256 tokens per view, 75% fewer than dense encoding of the same frames. A shared flow module jointly updates continuous action and visual states through two modality-specific heads under transition-wise causal attention, and a TiTok-VAE decoder reconstructs multi-view future images from the visual latents. Decoded forecasts also support Proposal Review (PR), a vision-language model component for execution-prefix selection and proposal rejection. Without PR, PACT-WAM achieves average success rates of 98.6%, 92.3%, and 78.0% on LIBERO, RoboTwin 2.0, and real-world Piper tasks, respectively. PR provides a test-time enhancement, raising these rates to 99.5%, 93.4%, and 86.7%. Ablations show that hierarchical history allocation and joint action-visual generation improve control success, while analyses of visual capacity and forecast-guided execution characterize the trade-offs between success and proposal-generation cost.