Pith. sign in

REVIEW 19 cited by

RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.04339 v2 pith:RE72PZYA submitted 2024-06-06 cs.CV

Jiaming Liu , Mengzhen Liu , Zhenyu Wang , Pengju An , Xiaoqi Li , Kaichen Zhou , Senqiao Yang , Renrui Zhang
show 2 more authors
Yandong Guo Shanghang Zhang
This is my paper
classification cs.CV
keywords modelreasoningrobomambafine-tuninginferenceroboticcapabilitiesefficient
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A fundamental objective in robot manipulation is to enable models to comprehend visual scenes and execute actions. Although existing Vision-Language-Action (VLA) models for robots can handle a range of basic tasks, they still face challenges in two areas: (1) insufficient reasoning ability to tackle complex tasks, and (2) high computational costs for VLA model fine-tuning and inference. The recently proposed state space model (SSM) known as Mamba demonstrates promising capabilities in non-trivial sequence modeling with linear inference complexity. Inspired by this, we introduce RoboMamba, an end-to-end robotic VLA model that leverages Mamba to deliver both robotic reasoning and action capabilities, while maintaining efficient fine-tuning and inference. Specifically, we first integrate the vision encoder with Mamba, aligning visual tokens with language embedding through co-training, empowering our model with visual common sense and robotic-related reasoning. To further equip RoboMamba with SE(3) pose prediction abilities, we explore an efficient fine-tuning strategy with a simple policy head. We find that once RoboMamba possesses sufficient reasoning capability, it can acquire manipulation skills with minimal fine-tuning parameters (0.1\% of the model) and time. In experiments, RoboMamba demonstrates outstanding reasoning capabilities on general and robotic evaluation benchmarks. Meanwhile, our model showcases impressive pose prediction results in both simulation and real-world experiments, achieving inference speeds 3 times faster than existing VLA models. Our project web page: https://sites.google.com/view/robomamba-web

Discussion (0). Sign in to comment.

Forward citations

Cited by 19 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    CrossVLA develops a surrogate log-probability estimator for DPO on flow-matching VLAs, shows DoRA outperforming LoRA by +10.4 pp mean on LIBERO, and identifies inference bottlenecks with limited caching gains.

  2. CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models

    cs.CV 2026-05 conditional novelty 7.0 of 10

    CrossVLA introduces a surrogate log-probability estimator to enable DPO on flow-matching VLAs, reports DoRA yielding +10.4 pp mean gains over SFT on LIBERO with 600 trials, and shows inference caching limited to 21% s...

  3. AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models

    cs.RO 2026-05 unverdicted novelty 7.0 of 10

    AT-VLA proposes adaptive tactile injection and a dual-stream tactile reaction mechanism to enhance VLA models for contact-rich robotic manipulation with real-time responses.

  4. Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment

    cs.RO 2026-04 unverdicted novelty 7.0 of 10

    VLA models exhibit a compute-bound VLM phase followed by a memory-bound action phase on edge hardware; DP-Cache and V-AEFusion reduce redundancy and enable pipeline parallelism for up to 6x speedup on NPUs with margin...

  5. HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness

    cs.RO 2026-03 unverdicted novelty 7.0 of 10

    HeiSD delivers up to 2.45x faster inference for embodied VLA models by hybridizing speculative decoding with kinematic boundary detection and error-mitigation tricks while preserving task success rates.

  6. Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

    cs.RO 2026-08 conditional novelty 6.0 of 10

    A taxonomy of robot learning on a weights-versus-skills axis, with a five-rung self-improvement ladder whose top cell (feedback plus memory plus search) holds only a few recent systems.

  7. CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model

    cs.AI 2026-07 conditional novelty 6.0 of 10

    CoTinyVLA, a 0.9B vision-language-action model, outperforms 3-7B baselines on all four LIBERO-Plus robustness suites.

  8. EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Action latents supervised by both control reconstruction and environment-conditioned visual consequences outperform trajectory-centric tokenizers for robotic manipulation, especially long-horizon tasks.

  9. AT-VLA: Adaptive Tactile Injection for Enhanced Feedback Reaction in Vision-Language-Action Models

    cs.RO 2026-05 unverdicted novelty 6.0 of 10

    AT-VLA introduces adaptive tactile injection and a dual-stream tactile reaction mechanism to integrate real-time tactile feedback into pretrained VLA models for contact-rich robotic manipulation.

  10. CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CogVLA pairs instruction-conditioned visual-token aggregation (EFA-Routing) with transformer-layer pruning (LFP-Routing) and bidirectional action decoding (CAtten), reporting LIBERO 97.4%, real-world 70.0%, 2.5x less ...

  11. VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A vision-language model learns via reinforcement learning when to upscale a low-resolution image, cutting visual tokens roughly in half while preserving accuracy on most benchmarks.

  12. HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

    cs.CV 2025-03 unverdicted novelty 6.0 of 10

    HybridVLA unifies diffusion and autoregression in a single VLA model via collaborative training and ensemble to raise robot manipulation success rates by 14% in simulation and 19% in real-world tasks.

  13. CoDex: Learning Compositional Dexterous Functional Manipulation without Demonstrations

    cs.RO 2026-06 unverdicted novelty 5.0 of 10

    CoDex combines VLMs, constrained optimization, and RL to autonomously discover grasp-move-actuate policies for functional manipulation of unseen objects with internal mechanisms.

  14. The Hyperscale Lottery: How State-Space Models Have Sacrificed Edge Efficiency

    cs.AR 2026-04 unverdicted novelty 5.0 of 10

    Mamba-3 architectural changes made for hyperscale GPUs raise edge latency 28% at 880M parameters and 48% at 15M parameters relative to earlier Mamba designs.

  15. Source Component Shift Adaptation via Offline Decomposition and Online Mixing Approach

    cs.LG 2025-08 unverdicted novelty 5.0 of 10

    The claimed result is that source-component-shift adaptation splits cleanly into offline component learning via EM and online mixing-weight updates, cutting cumulative test loss by up to 67.4%.

  16. What Matters in Building Vision-Language-Action Models for Generalist Robots

    cs.RO 2024-12 unverdicted novelty 5.0 of 10

    Systematic tests of VLM backbones, policy architectures, and cross-embodiment data yield RoboVLMs that set new SOTA on robot manipulation benchmarks while requiring few manual designs.

  17. The Hyperscale Lottery: How State-Space Models Have Sacrificed Edge Efficiency

    cs.AR 2026-04 unverdicted novelty 4.0 of 10

    Mamba-3 architectural changes optimized for hyperscale GPUs cause 28% higher edge latency at 880M parameters and 48% at 15M parameters compared to earlier versions.

  18. Leveraging OS-Level Primitives for Robotic Action Management

    cs.OS 2025-08 conditional novelty 4.0 of 10

    Applying OS-style exception handling, context caching, and replay to robotic action slices raises success rates 7x to 24x and cuts execution steps up to 74% for repetitive manipulation tasks, without retraining the VLA model.

  19. A Survey of Mamba

    cs.LG 2024-08 unverdicted novelty 2.0 of 10

    The paper consolidates existing research on Mamba models, their architecture variants, adaptations to different data modalities, and applications across domains.

Pith tools