REVIEW 13 cited by
RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
Not yet reviewed by Pith; the record is open.
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
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
Forward citations
Cited by 13 Pith papers
-
Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills
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.
-
CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model
CoTinyVLA, a 0.9B vision-language-action model, outperforms 3-7B baselines on all four LIBERO-Plus robustness suites.
-
EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation
Action latents supervised by both control reconstruction and environment-conditioned visual consequences outperform trajectory-centric tokenizers for robotic manipulation, especially long-horizon tasks.
-
CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
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 ...
-
VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
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.
-
RwoR: Generating Robot Demonstrations from Human Hand Collection for Policy Learning without Robot
A generative model and wrist camera turn human hand videos into robot gripper demonstrations that train manipulation policies at success rates close to those trained on real gripper data.
-
AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making
AntiGrounding lifts candidate robot trajectories into the VLM's visual space via multi-view rendering and structured VQA, and reports 57.5% average success across eight manipulation tasks, beating three intermediate-r...
-
Source Component Shift Adaptation via Offline Decomposition and Online Mixing Approach
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%.
-
AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
AC-DiT adds mobility-to-body conditioning and perception-aware 2D/3D weighting to a diffusion transformer, improving success rates on simulated and real-world mobile manipulation tasks.
-
EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
EfficientVLA combines LLM layer pruning, task-aware visual token selection, and diffusion-head feature caching to cut CogACT's inference cost to 28.9% of baseline FLOPs with a 0.6% SIMPLER success drop.
-
SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
SR3D combines an off-the-shelf single-view 3D reconstruction model with view and keypoint matching to place the reconstructed mesh into the scene, enabling single-view grasping of transparent objects.
-
Leveraging OS-Level Primitives for Robotic Action Management
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.
-
Think Twice, Act Once: Token-Aware Compression and Action Reuse for Efficient Inference in Vision-Language-Action Models
FlashVLA, a training-free plug-in, reuses stable actions and prunes visual tokens to cut VLA model inference FLOPs by 55.7% and latency by 36% with only a 0.7% success-rate drop on LIBERO.
Discussion (0). Sign in to comment.