EmbodiedMidtrain mid-trains VLMs on curated VLA-aligned data subsets to improve downstream performance on robot manipulation benchmarks.
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
8 Pith papers cite this work, alongside 20 external citations. Polarity classification is still indexing.
8
Pith papers citing it
20
external citations · OpenAlex
years
2026 8verdicts
UNVERDICTED 8representative citing papers
CoStream composes semantic, predictive, and reactive behaviors on an SE(3) interface to enable precise, generalizable performance on eight real-world contact-rich manipulation tasks.
Reflective VLA improves VLA generalization on LIBERO-Plus and LIBERO-Plus-Hard by 5.4 and 4.2 percentage points by conditioning on action consequences instead of reactive single-frame inputs.
dVLA-RL models denoising as an MDP to enable RL on dVLAs via trajectory probabilities, reporting 99.7% success on LIBERO and 30.6% gains over SFT on RoboTwin 2.0.
PolicyTrim is an RL post-training framework that boosts VLA policy efficiency by 3x chunk utilization and 51.4% fewer steps, yielding up to 5.83x speedup.
SafeDojo is a new world model-based safe RL framework for VLA that outperforms baselines on SafeLIBERO and real robot tasks.
Adding recurrent memory tokens to VLA models raises success rates on partially observable manipulation tasks from 0.42 to 0.84 on training and 0.07 to 0.23 on held-out tasks while preserving performance under full observability.
Dexterity-BEV creates 3D vertex-based inputs and BEV-aligned outputs to reduce spatial-temporal misalignments in end-to-end robot policies trained on diverse datasets and embodiments.
citing papers explorer
-
EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
EmbodiedMidtrain mid-trains VLMs on curated VLA-aligned data subsets to improve downstream performance on robot manipulation benchmarks.
-
CoStream: Composing Simple Behaviors for Generalizable Complex Manipulation
CoStream composes semantic, predictive, and reactive behaviors on an SE(3) interface to enable precise, generalizable performance on eight real-world contact-rich manipulation tasks.
-
Reflective VLA: In-Context Action Consequences Make VLAs Generalize
Reflective VLA improves VLA generalization on LIBERO-Plus and LIBERO-Plus-Hard by 5.4 and 4.2 percentage points by conditioning on action consequences instead of reactive single-frame inputs.
-
dVLA-RL: Reinforcement Learning over Denoising Trajectories for Discrete Diffusion Vision-Language-Action Models
dVLA-RL models denoising as an MDP to enable RL on dVLAs via trajectory probabilities, reporting 99.7% success on LIBERO and 30.6% gains over SFT on RoboTwin 2.0.
-
PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models
PolicyTrim is an RL post-training framework that boosts VLA policy efficiency by 3x chunk utilization and 51.4% fewer steps, yielding up to 5.83x speedup.
-
SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model
SafeDojo is a new world model-based safe RL framework for VLA that outperforms baselines on SafeLIBERO and real robot tasks.
-
$\mu$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models
Adding recurrent memory tokens to VLA models raises success rates on partially observable manipulation tasks from 0.42 to 0.84 on training and 0.07 to 0.23 on held-out tasks while preserving performance under full observability.
-
Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning
Dexterity-BEV creates 3D vertex-based inputs and BEV-aligned outputs to reduce spatial-temporal misalignments in end-to-end robot policies trained on diverse datasets and embodiments.