UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models

• URL: http://arxiv.org/abs/2606.22794v1
• Date: Mon, 22 Jun 2026 03:10:19 GMT
• Title: UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models
• Abstract summary: We introduce UniFS, a unified fast-to-slow architecture for vision-language models.<n>We show that UniFS achieves state-of-the-art performance (98.3% average success rate, a 2.5% gain over VLA-Adapter baseline)<n> Experiments on LIBERO show that UniFS achieves state-of-the-art performance (98.3% average success rate, a 2.5% gain over VLA-Adapter baseline)
• Score: 15.95393143175101
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mainstream Fast-Slow dual system vision-language-action models decouple a high-frequency action expert from a low-frequency vision-language model for efficiency, yet they face a fundamental frequency dilemma: large update gaps cause semantic drift from stale context, while small gaps erode the intended computational savings. Moreover, because the action expert receives only the VLM's final-layer representation at a single fixed frequency, rich intermediate features are discarded, limiting both information coupling and manipulation precision. Inspired by multi-timescale neural processing in the human brain, we introduce UniFS, a unified fast-to-slow architecture that resolves these challenges through three key designs. First, we stratify the VLM layers into groups with progressively decreasing update frequencies, enabling shallow layers to capture fast-changing dynamics while deeper layers cache stable semantic context. Second, a latent vector inversion mechanism re-routes the interaction order between multi-scale VLM features and the action expert, aligning fast-varying representations with fine-grained action decoding and slow-varying ones with coarse planning. Third, a multi-level supervision strategy enforces a coarse-to-fine learning hierarchy across temporal scales. Together, these designs enable richer cross-frequency information transfer within a single backbone, while the low-frequency pathways additionally preserve temporal context across steps. Experiments on LIBERO show that UniFS achieves state-of-the-art performance (98.3\% average success rate, a 2.5\% gain over VLA-Adapter baseline) while reducing average inference latency from 36.5~ms to 17.8~ms (2.1$\times$ speedup). Real-robot experiments on a Franka platform further validate its practical applicability. Code is opensourced at https://github.com/linsun449/UniFS.

Related papers

• WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA [27.102605117827398]
  Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving.<n>They are constrained by high computational latency and exposure bias arising from sequential autoregressive decoding.<n>We introduce WAM-Diff2, a multi-task discrete diffusion VLA framework powered by a three-stage hierarchical strategy.
  arXiv  Detail & Related papers  (2026-08-02T06:45:16Z)
• FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detection [0.0]
  Event cameras offer inherent advantages in high-speed and high-dynamic-range scenarios.<n>Current approaches partition the accumulation window into fixed temporal sub-bins.<n>We propose FATE, a unified framework built upon a novel spatial framework.
  arXiv  Detail & Related papers  (2026-06-15T22:32:09Z)
• Kwai Keye-VL-2.0 Technical Report [53.82434681649277]
  Keye-VL-2.0 is a multimodal foundation model designed to advance long-video understanding and agentic intelligence.<n>It is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures.<n>Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL overcomes the algorithmic dilemma of catastrophic forgetting.
  arXiv  Detail & Related papers  (2026-06-09T09:58:08Z)
• Asynchronous Fast-Slow Vision-Language-Action Policies for Whole-Body Robotic Manipulation [10.09057399213028]
  Vision-Language-Action (VLA) systems integrate a Vision-Language Model (VLM) for semantic reasoning with an action expert generating continuous action signals.<n>We introduce a truly asynchronous Fast-Slow VLA framework (DuoCore-FS) to organize the system into a fast pathway for action generation and a slow pathway for rich VLM reasoning.
  arXiv  Detail & Related papers  (2025-12-23T09:28:20Z)
• 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)
• USV: Unified Sparsification for Accelerating Video Diffusion Models [11.011602744993942]
  Unified Sparsification for Video diffusion models is an end-to-end trainable framework.<n>It orchestrates sparsification across both the model's internal computation and its sampling process.<n>It achieves up to 83.3% speedup in the denoising process and 22.7% end-to-end acceleration, while maintaining high visual fidelity.
  arXiv  Detail & Related papers  (2025-12-05T14:40:06Z)
• LUMA: Low-Dimension Unified Motion Alignment with Dual-Path Anchoring for Text-to-Motion Diffusion Model [18.564067196226436]
  We propose a text-to-motion diffusion model that incorporates dual-path anchoring to enhance semantic alignment.<n>LUMA achieves state-of-the-art performance, with FID scores of 0.035 and 0.123, respectively.
  arXiv  Detail & Related papers  (2025-09-29T17:58:28Z)
• NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows [75.70583906344815]
  Diffusion models have been widely adopted as action decoders due to their ability to model complex, multimodal action distributions.<n>We present NinA, a fast and expressive alternative to diffusion-based decoders for Vision-Language-Action (VLA) models.
  arXiv  Detail & Related papers  (2025-08-23T00:02:15Z)
• EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models [21.42353501209045]
  Vision-Language-Action (VLA) models demonstrate transformative potential for embodied intelligence but are severely hampered by high computational and memory demands.<n>We introduce EfficientVLA, a structured and training-free inference acceleration framework.<n>We apply our method to a standard VLA model CogACT, yielding a 1.93X inference speedup and reduces FLOPs to 28.9%, with only a 0.6% success rate drop in the SIMPLER benchmark.
  arXiv  Detail & Related papers  (2025-06-11T18:34:57Z)
• SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining [62.433137130087445]
  SuperFlow++ is a novel framework that integrates pretraining and downstream tasks using consecutive camera pairs.<n>We show that SuperFlow++ outperforms state-of-the-art methods across diverse tasks and driving conditions.<n>With strong generalizability and computational efficiency, SuperFlow++ establishes a new benchmark for data-efficient LiDAR-based perception in autonomous driving.
  arXiv  Detail & Related papers  (2025-03-25T17:59:57Z)
• Mutual Information-driven Triple Interaction Network for Efficient Image Dehazing [54.168567276280505]
  We propose a novel Mutual Information-driven Triple interaction Network (MITNet) for image dehazing. The first stage, named amplitude-guided haze removal, aims to recover the amplitude spectrum of the hazy images for haze removal. The second stage, named phase-guided structure refined, devotes to learning the transformation and refinement of the phase spectrum.
  arXiv  Detail & Related papers  (2023-08-14T08:23:58Z)
• Searching Multi-Rate and Multi-Modal Temporal Enhanced Networks for Gesture Recognition [89.0152015268929]
  We propose the first neural architecture search (NAS)-based method for RGB-D gesture recognition. The proposed method includes two key components: 1) enhanced temporal representation via the 3D Central Difference Convolution (3D-CDC) family, and optimized backbones for multi-modal-rate branches and lateral connections. The resultant multi-rate network provides a new perspective to understand the relationship between RGB and depth modalities and their temporal dynamics.
  arXiv  Detail & Related papers  (2020-08-21T10:45:09Z)

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.