REVIEW 19 cited by
Towards Synergistic, Generalized, and Efficient Dual-System for Robotic 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
Signed reviews
read the original abstract
The increasing demand for versatile robotic systems to operate in diverse and dynamic environments has emphasized the importance of a generalist policy, which leverages a large cross-embodiment data corpus to facilitate broad adaptability and high-level reasoning. However, the generalist would struggle with inefficient inference and cost-expensive training. The specialist policy, instead, is curated for specific domain data and excels at task-level precision with efficiency. Yet, it lacks the generalization capacity for a wide range of applications. Inspired by these observations, we introduce RoboDual, a synergistic dual-system that supplements the merits of both generalist and specialist policy. A diffusion transformer-based specialist is devised for multi-step action rollouts, exquisitely conditioned on the high-level task understanding and discretized action output of a vision-language-action (VLA) based generalist. Compared to OpenVLA, RoboDual achieves 26.7% improvement in real-world setting and 12% gain on CALVIN by introducing a specialist policy with merely 20M trainable parameters. It maintains strong performance with 5% of demonstration data only, and enables a 3.8 times higher control frequency in real-world deployment. Code would be made publicly available. Our project page is hosted at: https://opendrivelab.com/RoboDual/
Forward citations
Cited by 19 Pith papers
-
SLIM-0.5B: Learning Action-Grounded Predictive Latents for Robot Manipulation
A compact latent interaction policy trained with bidirectional masked trajectory prediction matches or exceeds large VLA and world-action-model baselines on robot manipulation benchmarks while using far less compute.
-
TEMPO: Semantic-Action Decoupled RL Post-Training for Vision-Language-Action Models
A two-timescale RL post-training method that updates the semantic projection layer rarely and the action expert often improves VLA policy success on long-horizon manipulation tasks.
-
Fast and Accurate: An Adaptive VLA Inference Framework through Environment-aware Model Selection
EMS, a dual-system VLA framework with RL-trained switching, achieves near-large-model success on LIBERO at high effective command rate.
-
Mind-VLA: Instruction-Aware Spatial Representation Alignment for Vision-Language-Action Models
Aligning a VLA's latent features with instruction-selected target-object tri-views (VAE and VGGT) improves manipulation success, especially under target occlusion, with a compact 345M backbone.
-
RoboInter1.5: A Holistic Intermediate Representation Suite for Embodied World Modeling and Robotic Manipulation
Dense per-frame intermediate representations (traces, masks, grasp poses, subtasks) improve embodied VQA, VLA action generation, and world-model video prediction in the new 230k-episode RoboInter-Data suite.
-
Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment
Preserving pretrained VLM features with layer-wise distillation plus supervising the language head on discretized action directions improves OOD generalization of VLA policies on LIBERO, CALVIN, and a real xArm7.
-
UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models
Uncertainty-aware observation reinjection into FFN layers improves VLA manipulation success rates across LIBERO, SIMPLER, CALVIN, and real-robot tasks with no training.
-
FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies
A compact 950-million-parameter robot policy trained in about 200 GPU-hours matches or beats multi-billion-parameter baselines on most manipulation benchmarks, including a new best score on CALVIN ABC.
-
ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models
An asynchronous dual-system architecture forecasts large-model features into the current frame and adds a small-model update to drive in near real time, scoring 69.53 on Bench2Drive at 50 ms.
-
ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge
ChatVLA-2 uses dynamic mixture-of-experts and a two-stage training recipe to let a vision-language-action model retain pretrained reasoning while following robot instructions.
-
Hume: Introducing System-2 Thinking in Visual-Language-Action Model
A dual-system vision-language-action model that improves robot control by ranking multiple sampled action chunks with a learned value function before fast execution.
-
WorldEval: World Model as Real-World Robot Policies Evaluator
WorldEval conditions a video generation model on a policy's internal action embeddings (Policy2Vec) and shows generated-video success rates correlate with real-world robot success rates.
-
Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoning
A robot policy generates its own language reasoning before acting and injects it into a diffusion action decoder, outperforming several VLA baselines on real-robot manipulation.
-
TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging
A 0.5B VLA with bridge-conditioned discrete diffusion and 2D temporal–spatial action masking reaches 95.7% LIBERO success and 4.19 CALVIN average length.
-
Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation
A dual-system framework with a structured subtask interface, event-balanced training, and inference harness enables VLM-guided long-horizon robotic manipulation, achieving 95.5% on LIBERO-Long and 65% on real-world ch...
-
EnerVerse-AC: Envisioning Embodied Environments with Action Condition
EnerVerse-AC generates realistic multi-view robot videos conditioned on action sequences and shows early evidence it can augment training data and rank policy performance like a real robot.
-
OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
OpenHelix shows that a frozen vision-language model with a prompt-tuned token and an auxiliary action-prediction head beats full fine-tuning on CALVIN language generalization while training far fewer parameters.
-
StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
StemVLA supervises a GPT-2-based VLA with predicted future 3D-geometry features (VGGT) and temporally aggregated history, reporting 86.0% on LIBERO-Long - but its CALVIN results and equations are placeholders.
-
Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
A survey that groups VLA efficiency techniques into four categories: model architecture, perception features, action generation, and training/inference strategies.
Discussion (0). Continue with ORCID to comment.