SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation

• URL: http://arxiv.org/abs/2603.05117v2
• Date: Sun, 08 Mar 2026 10:29:15 GMT
• Title: SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation
• Abstract summary: Imitation Learning (IL) enables robots to acquire manipulation skills from expert demonstrations.<n>We propose Self-Evolving Gated Attention (SEGA), a temporal module that maintains a time-evolving latent state via gated attention.<n> integrating SEGA into DP yields Self-Evolving Diffusion Policy (SeedPolicy), which resolves the temporal modeling bottleneck.
• Score: 50.002839579188624
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Imitation Learning (IL) enables robots to acquire manipulation skills from expert demonstrations. Diffusion Policy (DP) models multi-modal expert behaviors but suffers performance degradation as observation horizons increase, limiting long-horizon manipulation. We propose Self-Evolving Gated Attention (SEGA), a temporal module that maintains a time-evolving latent state via gated attention, enabling efficient recurrent updates that compress long-horizon observations into a fixed-size representation while filtering irrelevant temporal information. Integrating SEGA into DP yields Self-Evolving Diffusion Policy (SeedPolicy), which resolves the temporal modeling bottleneck and enables scalable horizon extension with moderate overhead. On the RoboTwin 2.0 benchmark with 50 manipulation tasks, SeedPolicy outperforms DP and other IL baselines. Averaged across both CNN and Transformer backbones, SeedPolicy achieves 36.8% relative improvement in clean settings and 169% relative improvement in randomized challenging settings over the DP. Compared to vision-language-action models such as RDT with 1.2B parameters, SeedPolicy achieves competitive performance with one to two orders of magnitude fewer parameters, demonstrating strong efficiency and scalability. These results establish SeedPolicy as a state-of-the-art imitation learning method for long-horizon robotic manipulation. Code is available at: https://github.com/Youqiang-Gui/SeedPolicy.

Related papers

• B-spline Policy: Accelerating Manipulation Policies via B-spline Action Representations [75.39816527838181]
  B-spline Policy ( BSP) is an action representation designed for accelerating robot manipulation policies.<n> BSP parameterizes actions as continuous B-spline curves defined by a set of knots and control points.
  arXiv  Detail & Related papers  (2026-07-10T17:46:32Z)
• Lagrangian Perturbation Diffusion Steering: Latent Reinforcement Learning for Generative Policies [5.170807667319543]
  We propose a lightweight adaptation method that improves a frozen generative policy by learning a compact noise-space perturbation before decoding.<n>Across RoboMimic manipulation, OpenAI Gym locomotion, and Adroit dexterous manipulation benchmarks, LP-DS improves sample efficiency, success, and return while maintaining higher action-space entropy than unconstrained noise-space steering.
  arXiv  Detail & Related papers  (2026-05-31T10:40:28Z)
• PolicyLong: Towards On-Policy Context Extension [23.33185151859789]
  We propose PolicyLong, shifting data construction towards a dynamic on-policy paradigm.<n>By iteratively re-executing data screening, PolicyLong ensures the training distribution tracks evolving capabilities.<n>Experiments show PolicyLong consistently outperforms EntropyLong and NExtLong.
  arXiv  Detail & Related papers  (2026-04-09T05:07:57Z)
• RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks [28.827331437876452]
  We present RoboClaw, an agentic robotics framework that unifies data collection, policy learning, and task execution under a single VLM-driven controller.<n>At the policy level, RoboClaw introduces Entangled Action Pairs (EAP), which couple forward manipulation behaviors with inverse recovery actions to form self-resetting loops for autonomous data collection.<n>During deployment, the same agent performs high-level reasoning and dynamically orchestrates learned policy primitives to accomplish long-horizon tasks.
  arXiv  Detail & Related papers  (2026-03-12T05:22:59Z)
• Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation [95.89924101984566]
  We introduce OptimusVLA, a dual-memory VLA framework with Global Prior Memory (GPM) and Local Consistency Memory (LCM)<n>GPM replaces Gaussian noise with task-level priors retrieved from semantically similar trajectories.<n>LCM injects a learned consistency constraint that enforces temporal coherence and smoothness of trajectory.
  arXiv  Detail & Related papers  (2026-02-22T15:39:34Z)
• AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering [52.67783579040657]
  AceGRPO is a machine learning system that prioritizes tasks at the agent's learning frontier to maximize learning efficiency.<n>Our trained Ace-30B model achieves a 100% valid submission rate on MLE-Bench-Lite, approaches the performance of proprietary frontier models, and outperforms larger open-source baselines.
  arXiv  Detail & Related papers  (2026-02-08T10:55:03Z)
• D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss [13.132582315951193]
  Diffusion policies excel at robotic manipulation by modeling multimodal action distributions in high-dimensional spaces.<n>Diffusion policies suffer from representation collapse when semantically similar observations are mapped to indistinguishable features.<n>D2PPO introduces dispersive loss regularization that combats representation collapse by treating all hidden representations within each batch as negative pairs.
  arXiv  Detail & Related papers  (2025-08-04T17:33:41Z)
• Diffusion Transformer Policy [48.50988753948537]
  We propose a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, to model continuous end-effector actions.<n>By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets.
  arXiv  Detail & Related papers  (2024-10-21T12:43:54Z)
• Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding [121.08841110022607]
  Existing agent-centric methods have demonstrated outstanding performance on public benchmarks. We introduce the K-nearest neighbor attention with relative pose encoding (KNARPE), a novel attention mechanism allowing the pairwise-relative representation to be used by Transformers. By sharing contexts among agents and reusing the unchanged contexts, our approach is as efficient as scene-centric methods, while performing on par with state-of-the-art agent-centric methods.
  arXiv  Detail & Related papers  (2023-10-19T17:59:01Z)
• GPU-Accelerated Policy Optimization via Batch Automatic Differentiation of Gaussian Processes for Real-World Control [8.720903734757627]
  We develop a policy optimization method by leveraging fast predictive sampling methods to process batches of trajectories in every forward pass. We demonstrate the effectiveness of our approach in training policies on a set of reference-tracking control experiments with a heavy-duty machine.
  arXiv  Detail & Related papers  (2022-02-28T09:31:15Z)
• Modular Deep Reinforcement Learning for Continuous Motion Planning with Temporal Logic [59.94347858883343]
  This paper investigates the motion planning of autonomous dynamical systems modeled by Markov decision processes (MDP) The novelty is to design an embedded product MDP (EP-MDP) between the LDGBA and the MDP. The proposed LDGBA-based reward shaping and discounting schemes for the model-free reinforcement learning (RL) only depend on the EP-MDP states.
  arXiv  Detail & Related papers  (2021-02-24T01:11:25Z)

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.