RECURRENT-DEPTH VLA: IMPLICIT TEST-TIME COMPUTE SCALING OF VISION–LANGUAGE–ACTION MODELS VIA LATENT ITERATIVE REASONING

Yalcin Tur, Jalal Naghiyev, Haoquan Fang, Wei-Chuan Tsai, Jiafei Duan, Dieter Fox, Ranjay Krishna

Track: long paper (up to 10 pages)

Keywords: Robot Learning: Imitation Learning, Robot Learning: Found Models, Robot Learning: Model Learning, Latent Reasoning.

TL;DR: Latent Recurrent Action Head for Robotics capable of uncertainty based behaviours.

Abstract: Current Vision-Language-Action (VLA) models utilize fixed computational depth, processing simple adjustments and complex multi-step manipulations with same amount of compute. While Chain-of-Thought (CoT) prompting enables variable compute, it scales memory linearly and struggles with continuous action spaces. We introduce Recurrent-Depth VLA (RD-VLA), an architecture that achieves computational adaptivity through latent iterative refinement instead of explicit token generation. RD-VLA employs a recurrent action head with weight-tied layers, enabling arbitrary depth with a constant memory footprint. We train the model using truncated backpropagation through time (TBPTT), allowing for efficient supervision of the refinement process. At inference, an adaptive stopping criterion based on latent convergence enables the model to dynamically allocate compute per sample. Our experiments on complex manipulation tasks demonstrate that recurrent depth is critical for success: tasks failing (0%) with single-iteration inference achieve +90% success with four iterations, while simpler tasks saturate quickly. RD-VLA provides a scalable path for test-time compute in robotics, bypassing the data and memory overhead of CoT while replacing discrete, token-based reasoning with latent reasoning, which maintains a constant memory footprint regardless of depth, and does not require any special data collection.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Presenter: ~Jalal_Naghiyev2

Format: Maybe: the presenting author will attend in person, contingent on other factors that still need to be determined (e.g., visa, funding).

Funding: Yes, the presenting author of this submission falls under ICLR’s funding aims, and funding would significantly impact their ability to attend the workshop in person.

Submission Number: 78