Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models

• URL: http://arxiv.org/abs/2608.04404v1
• Date: Wed, 05 Aug 2026 03:18:58 GMT
• Title: Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Models
• Abstract summary: World Action Models (WAMs) improve robot manipulation by learning how the environment evolves beyond the current observation.<n>Joint-WAMs preserve future-aware representations during inference but incur prohibitive computation costs.<n>We show that inference-time future conditioning is critical for generalization under distribution shifts.
• Score: 40.0682886050991
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World Action Models (WAMs) improve robot manipulation by learning how the environment evolves beyond the current observation. However, existing approaches face a fundamental dilemma: Joint-WAMs preserve future-aware representations during inference but incur prohibitive computation costs, while efficient alternatives remove future modeling at inference time and may lose the robustness benefits of temporal reasoning. In this work, we revisit the role of future representations in WAMs and show that inference-time future conditioning is critical for generalization under distribution shifts. This observation motivates Faster-WAM, an efficient future-conditioning WAM that preserves future representations while avoiding expensive video-action interaction. Faster-WAM introduces a sparse future-conditioning framework that computes future representations once and selectively reuses them throughout action denoising. Specifically, we propose SparseMoT to replace ubiquitous layer-wise fusion with selective video-action interaction at a compact subset of network stages, and Interval KV-Fusion to aggregate multi-depth future representations without increasing attention complexity. Experiments demonstrate that Faster-WAM achieves a substantially better performance-efficiency trade-off than existing WAMs. On the out-of-distribution LIBERO-Plus benchmark, Faster-WAM improves success rate from 49.14% to 73.57% compared with Fast-WAM, while running 2.21$\times$ faster than Joint-WAM. It further achieves state-of-the-art performance on LIBERO and RoboTwin 2.0, while demonstrating strong robustness in real-world manipulation.

Related papers

• Learning to Use Imagination: Progress-Conditioned Future Utilization for World Action Models [72.02240114225107]
  World Action Models (WAMs) extend Vision-Language-Action (VLA) models by incorporating future visual dynamics into action generation.<n>Existing WAMs often utilize imagined futures with limited adaptation to evolving execution progress, potentially introducing distracting or unreliable predictive cues.<n>We propose ProWAM, a Progress-Conditioned World Action Model that introduces execution progress as an explicit intermediate representation for imagination utilization.
  arXiv  Detail & Related papers  (2026-09-06T12:46:20Z)
• StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action Models [84.17128030384099]
  StreamPI is a streaming multimodal temporal modeling framework.<n>It equips single-frame VLA with temporal reasoning capability without introducing any additional parameters.<n> Experiments on real-robot tasks spanning memory-dependent and precise perception scenarios, as well as the simulation benchmark LIBERO, demonstrate that StreamPI outperforms pi0.5 across diverse tasks.
  arXiv  Detail & Related papers  (2026-08-26T17:33:19Z)
• Latent Action as Intention Enables Efficient Future Imagination for World Action Models [20.031922437200524]
  We introduce **LAWA**, a WAM architecture that uses compact latent actions as an operational representation of future intentions.<n>On RoboCasa, LAWA achieves state-of-the-art average success rates of 65.6% and 80.8% in the few-shot and full data settings.<n>It also preserves the performance level of the matched Joint-WAM variant while requiring 42.9% lower inference latency.
  arXiv  Detail & Related papers  (2026-08-25T17:59:03Z)
• JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling [23.76460420882974]
  We introduce JEPA-WAM, a latent WAM built in a pretrained V-JEPA space.<n>It couples latent transition prediction with continuous action generation through a shared predictor.<n>On LIBERO-Plus, JEPA-WAM achieves 79.2%, the best result without large-scale robot-policy pretraining.
  arXiv  Detail & Related papers  (2026-08-10T09:57:54Z)
• ST-WAM: Semantic-Temporal World Action Model for Robust Manipulation under Visual Distribution Shifts [24.959404195743744]
  Training-Distribution Hallucination is a recurring phenomenon in which futures conditioned on visually shifted observations hallucinate training-domain content rather than remain faithful to the current scene.<n>We propose Semantic-Temporal WAM (ST-WAM) to improve action robustness by using DINOv3 as a shared semantic representation for future prediction and history retrieval while retaining fine-grained VAE dynamics.
  arXiv  Detail & Related papers  (2026-07-31T03:44:56Z)
• Next Forcing: Causal World Modeling with Multi-Chunk Prediction [65.05727210375643]
  Next Forcing is a multi-chunk prediction framework for causal world modeling.<n>It enables faster training, higher accuracy, and accelerated inference.<n>It achieves 93.1% relative improvement over LingBot-VA at 5k training steps and 2.3x faster convergence.
  arXiv  Detail & Related papers  (2026-06-09T17:59:22Z)
• Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination [45.6948544726412]
  World-Action Models (WAMs)couple future visual prediction with action generation.<n>Most existing WAMs rely on future prediction, which incurs high inference latency and makes real-time robot deployment difficult.<n>We introduce Efficient-WAM, a World-Action Model that reduces the cost of future imagination while preserving its control benefit.
  arXiv  Detail & Related papers  (2026-06-08T18:14:08Z)
• FUTURE-VLA: Forecasting Unified Trajectories Under Real-time Execution [27.399648455932397]
  FUTURE-VLA is a unified architecture that reformulates long-horizon control and future forecasting as a monolithic sequence-generation task.<n> FUTURE-VLA achieves success rates of 99.2% on LIBERO, 75.4% on RoboTwin, and 78.0% on a real-world Piper platform.
  arXiv  Detail & Related papers  (2026-02-05T14:27:43Z)
• FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization [61.10456021136654]
  We introduce FASTer, a unified framework for efficient and general robot learning.<n>FASTerVQ encodes action chunks as single-channel images, capturing global-temporal dependencies while maintaining a high compression ratio.<n>FASTerVLA builds on this tokenizer with block-wise autoregressive decoding and a lightweight action expert, achieving both faster inference and higher task performance.
  arXiv  Detail & Related papers  (2025-12-04T16:21:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.