ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models
read the original abstract
Learning real-world robotic manipulation is challenging, particularly when limited demonstrations are available. Existing methods for few-shot manipulation often rely on simulation-augmented data or pre-built modules like grasping and pose estimation, which struggle with sim-to-real gaps and lack extensibility. While large-scale imitation pre-training shows promise, adapting these general-purpose policies to specific tasks in data-scarce settings remains unexplored. To achieve this, we propose ControlVLA, a novel framework that bridges pre-trained VLA models with object-centric representations via a ControlNet-style architecture for efficient fine-tuning. Specifically, to introduce object-centric conditions without overwriting prior knowledge, ControlVLA zero-initializes a set of projection layers, allowing them to gradually adapt the pre-trained manipulation policies. In real-world experiments across 6 diverse tasks, including pouring cubes and folding clothes, our method achieves a 76.7% success rate while requiring only 10-20 demonstrations -- a significant improvement over traditional approaches that require more than 100 demonstrations to achieve comparable success. Additional experiments highlight ControlVLA's extensibility to long-horizon tasks and robustness to unseen objects and backgrounds.
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
X-Tokenizer creates semantic action tokens via asymmetric residual quantization and contrastive pretraining on large trajectory data, outperforming prior methods like FAST on robotic tasks.
-
MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
-
ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation
ELAN4D introduces plug-and-play 4D keypoint track supervision from forward kinematics to enhance VLA policy generalization in robotic manipulation tasks.
-
TMRL: Diffusion Timestep-Modulated Pretraining Enables Exploration for Efficient Policy Finetuning
TMRL bridges behavioral cloning pretraining and RL finetuning via diffusion noise and timestep modulation to enable controlled exploration, improving sample efficiency and enabling real-world robot training in under one hour.
-
Breaking Lock-In: Preserving Steerability under Low-Data VLA Post-Training
DeLock mitigates lock-in in low-data VLA post-training via visual grounding preservation and test-time contrastive prompt guidance, outperforming baselines across eight evaluations while matching data-heavy generalist...
-
OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulation
OFlow unifies temporal foresight and object-aware reasoning inside a shared latent space via flow matching to improve VLA robustness in robotic manipulation under distribution shifts.
-
FOCA: Future-Oriented Conditioning for Data-Efficient Vision-Language-Action Adaptation
FOCA improves few-shot VLA adaptation by explicitly predicting future interaction embeddings and implicitly aligning to goal observations, yielding up to 26% gains on real robots with only 20 demonstrations.
-
CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment
CoEnv introduces a compositional environment that integrates real and simulated spaces for multi-agent robotic collaboration, using real-to-sim reconstruction, VLM action synthesis, and validated sim-to-real transfer ...
-
SlotVLA: Towards Modeling of Object-Relation Representations in Robotic Manipulation
SlotVLA uses slot attention to model object-relation representations for multitask robotic manipulation, reducing visual tokens while achieving competitive generalization on the new LIBERO+ benchmark.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.