NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models

• URL: http://arxiv.org/abs/2605.07794v1
• Date: Fri, 08 May 2026 14:31:52 GMT
• Title: NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
• Abstract summary: World Action Models (WAMs) are policies that tie robot action generation to future-observation modeling.<n>NoiseGate is a lightweight Gating Policy Network that emits per-latent time increments during denoising.<n>NoiseGate delivers consistent gains on diverse RoboTwin random-scene manipulation tasks.
• Score: 19.272356473995245
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: World Action Models (WAMs) are an emerging family of policies that tie robot action generation to future-observation modeling. In this work, we focus on the joint video--action modeling paradigm, where actions and imagined future observations are co-generated along a shared denoising or flow trajectory, so that perception, prediction, and control are coupled within one generative process. Existing WAMs typically realize this paradigm with a Mixture-of-Transformers (MoT), where video and action tokens interact through shared self-attention. This architecture can in principle assign a separate timestep $t_f$ to each predicted latent frame, yet current systems collapse this degree of freedom onto a single shared scalar $t$. Under the noise-as-masking view of Diffusion Forcing, this shared schedule imposes the unjustified prior that every predicted latent is equally reliable for action generation. We instead view the per-latent schedule as a \emph{learnable information-gating policy}: by changing a latent frame's noise level, the policy modulates the reliability of its Key/Value contribution to the action tokens. We propose \textbf{NoiseGate}, which combines independent per-latent timestep sampling during backbone training, a lightweight Gating Policy Network that emits per-latent time increments during denoising, and task-reward optimization that trains the schedule policy without hand-crafted shape priors. Built on a joint video--action MoT backbone, NoiseGate delivers consistent gains on diverse RoboTwin random-scene manipulation tasks.

Related papers

• 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)
• ChronoSSM: Training for Temporally Aware Representations in Autoregressive State Space Models [0.5366467936613011]
  We introduce ChronoSSM, an autoregressive State Space Model (SSM) that jointly models events and timestamps with a shared backbone.<n>We show that temporal supervision can produce more temporally informative representations without materially degrading autoregressive event modeling.
  arXiv  Detail & Related papers  (2026-08-10T18:35:19Z)
• Understanding and Mitigating the Video-Action Generalization Gap via Temporal Ratio [42.378085641934796]
  Generative video foundation models exhibit strong compositional priors.<n>World-action models (WAMs) and video-action models (VAMs) often lose these priors after finetuning on robotic action data.<n>We propose an inference-time adaptive guidance method, which exploits this intrinsic feature attention pattern.
  arXiv  Detail & Related papers  (2026-07-09T05:56:08Z)
• World Action Models: A Survey [100.95337034529263]
  World Action Models (WAMs) are embodied predictive-action models that make a forecast of the future available to action.<n>Recent WAMs repurpose large video generation models, and a parallel line relies on language or vision-language backbones without a video-generation core.<n>This survey gives the field a common account. It first clarifies these boundaries, then organizes existing works through two complementary views.
  arXiv  Detail & Related papers  (2026-06-18T17:05:19Z)
• Action-Effect Memory Pretraining for Robot Manipulation [14.760244346330694]
  We present AEM, an Action-Effect Memory pretraining framework for robot manipulation.<n>AEM targets the temporal nature of manipulation, where the current observation alone is often insufficient under partial observability.<n>AEM consistently improves manipulation performance in both simulation and real-world settings.
  arXiv  Detail & Related papers  (2026-06-10T13:58:14Z)
• From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation [88.39072412680633]
  We propose MoLA, a control-oriented interface that transforms imagined future videos into executable representations.<n>We evaluate our approach on simulated benchmarks and real-world robot manipulation tasks.
  arXiv  Detail & Related papers  (2026-05-12T14:15:16Z)
• VAMPO: Policy Optimization for Improving Visual Dynamics in Video Action Models [46.94937828558026]
  We propose VAMPO, a post-training framework that directly improves visual dynamics in video action models through policy optimization.<n>Our key idea is to formulate multi-step denoising as a sequential decision process and optimize the denoising rewards defined over expert visual dynamics.<n>Across diverse simulated and real-world manipulation tasks, VAMPO improves task-relevant visual dynamics, leading to better downstream action generation and stronger generalization.
  arXiv  Detail & Related papers  (2026-03-19T18:04:03Z)
• FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model [73.03346643967309]
  We argue that effective joint visuomotor predictive modeling requires both temporal continuity and visually-conditioned supervision decoupling.<n>FutureVLA is designed to extract joint visuomotor embeddings by first decoupling visual and motor information.<n>In the post-training stage, we employ a latent embeddings alignment strategy, enabling diverse downstream VLA models to internalize these temporal priors.
  arXiv  Detail & Related papers  (2026-03-11T12:39:55Z)
• Sequence Diffusion Model for Temporal Link Prediction in Continuous-Time Dynamic Graph [5.83093727437226]
  Existing temporal graph neural networks mainly focus on learning representations of historical interactions.<n>We propose a novel sequence-level diffusion framework that unifies dynamic graph learning with generative denoising.<n>We show that our framework consistently achieves state-of-the-art performance in the temporal link prediction task.
  arXiv  Detail & Related papers  (2026-01-30T18:02:12Z)
• Temporal Graph Pattern Machine [17.352525018007473]
  Temporal Graph Pattern Machine (TGPM) conceptualizes each interaction as an interaction patch synthesized via temporally-biased random walks.<n>TGPM consistently achieves state-of-the-art performance in both transductive and inductive link prediction.
  arXiv  Detail & Related papers  (2026-01-30T01:46:13Z)
• ImplicitRDP: An End-to-End Visual-Force Diffusion Policy with Structural Slow-Fast Learning [52.86018040861575]
  We propose a unified end-to-end visual-force diffusion policy that integrates visual planning and reactive force control within a single network.<n>We introduce Structural Slow-Fast Learning, a mechanism utilizing causal attention to simultaneously process asynchronous visual and force tokens.<n>Experiments on contact-rich tasks demonstrate that ImplicitRDP significantly outperforms both vision-only and hierarchical baselines.
  arXiv  Detail & Related papers  (2025-12-11T18:59:46Z)
• Masked Temporal Interpolation Diffusion for Procedure Planning in Instructional Videos [32.71627274876863]
  We address the challenge of procedure planning in instructional videos, aiming to generate coherent and task-aligned action sequences from start and end visual observations.<n>Previous work has mainly relied on text-level supervision to bridge the gap between observed states and unobserved actions, but it struggles with capturing intricate temporal relationships among actions.<n>We propose the Masked Temporal Interpolation Diffusion Diffusion model that introduces a latent space temporal temporal module within the diffusion model.
  arXiv  Detail & Related papers  (2025-07-04T08:54:59Z)
• AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving [59.94343412438211]
  We introduce the GPT style next token motion prediction into motion prediction. Different from language data which is composed of homogeneous units -words, the elements in the driving scene could have complex spatial-temporal and semantic relations. We propose to adopt three factorized attention modules with different neighbors for information aggregation and different position encoding styles to capture their relations.
  arXiv  Detail & Related papers  (2024-03-20T06:22:37Z)
• Time-series Generation by Contrastive Imitation [87.51882102248395]
  We study a generative framework that seeks to combine the strengths of both: Motivated by a moment-matching objective to mitigate compounding error, we optimize a local (but forward-looking) transition policy. At inference, the learned policy serves as the generator for iterative sampling, and the learned energy serves as a trajectory-level measure for evaluating sample quality.
  arXiv  Detail & Related papers  (2023-11-02T16:45:25Z)
• Transform-Equivariant Consistency Learning for Temporal Sentence Grounding [66.10949751429781]
  We introduce a novel Equivariant Consistency Regulation Learning framework to learn more discriminative representations for each video. Our motivation comes from that the temporal boundary of the query-guided activity should be consistently predicted. In particular, we devise a self-supervised consistency loss module to enhance the completeness and smoothness of the augmented video.
  arXiv  Detail & Related papers  (2023-05-06T19:29:28Z)
• Learning to Align Sequential Actions in the Wild [123.62879270881807]
  We propose an approach to align sequential actions in the wild that involve diverse temporal variations. Our model accounts for both monotonic and non-monotonic sequences. We demonstrate that our approach consistently outperforms the state-of-the-art in self-supervised sequential action representation learning.
  arXiv  Detail & Related papers  (2021-11-17T18:55:36Z)

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.