ReCoVLA improves VLA policy reliability by using a VLM as a semantic reward selector to train residual recovery policies in simulation, raising average success from 36.7% to 66.7% in sim and achieving 61.7% in zero-shot sim-to-real physical tests.
hub
Rlinf: Flexible and efficient large-scale reinforcement learning via macro-to-micro flow transformation
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 2
other 1
citation-polarity summary
representative citing papers
ActProbe is an action-space detector that uses temporal consistency error and action chunk magnitude from policy outputs, mapped via LSTM-MLP, to predict failures earlier than baselines across policies and real-robot tasks.
DVAC uses denoising variance as an intrinsic signal to adaptively chunk actions in flow-based robot policies, improving success rates and cutting replans on LIBERO, RoboTwin, CALVIN, and real-world tasks.
NoiseGate learns per-latent timestep schedules as an information-gating policy in diffusion-based world action models, yielding consistent gains on RoboTwin manipulation tasks.
SpecRLBench is a new benchmark evaluating generalization of LTL-guided RL methods across navigation and manipulation domains with static/dynamic environments and varied robot dynamics.
A memory-guided LLM harness that calls a frozen VLA only for contact-rich phases lifts success to 82.4% on LIBERO-Pro, 55.4% on RoboCasa365, and 58.4% on RoboTwin C2R with no policy finetuning.
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.
InDex adapts parallel-gripper VLA policies to dexterous hands by conditioning a diffusion hand policy on a normalized scalar grasp intent, raising average simulated task success from 50.3% to 85.8%.
FiberTune is a new fine-tuning objective that preserves action-fiber visual residuals in VLA policies, yielding performance gains on simulation and physical robot tasks.
PAIR-VLA adds invariance and sensitivity objectives over paired visual variants during PPO fine-tuning of VLA models, yielding 9-16% average gains on ManiSkill3 under distractors, textures, poses, viewpoints, and lighting shifts.
RAW-Dream disentangles world-model learning from task data by using a pre-trained task-agnostic world model and VLM rewards, with dual-noise filtering, to enable zero-shot VLA adaptation in simulation and real settings.
DORA's multi-version streaming rollout enables 2-3x higher throughput in asynchronous RL for LLMs while preserving convergence by maintaining policy consistency, data integrity, and bounded staleness.
JigsawRL achieves up to 1.85x higher throughput in LLM RL pipelines via pipeline multiplexing, sub-stage graphs, and look-ahead scheduling compared to prior systems.
AsyncVLA adds asynchronous flow matching and a confidence rater to VLA models so they can generate actions on flexible schedules and selectively refine low-confidence tokens before execution.
FORCE is a 3-stage RL fine-tuning method for VLA models that stabilizes Q-function via on-policy warm-up and filters high-value actions for updates, claiming 79% success rate gains and 32.5% faster training without human intervention.
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
TacCoRL integrates tactile feedback into VLA policies via real-aligned simulation co-training and RL, raising average success from 50% to 72.5% on four bimanual contact-rich tasks with direct real-robot transfer.
Sword improves world model simulators for VLA policies by disentangling visual style from dynamics and bootstrapping latents for better consistency, outperforming baselines on LIBERO in generalization and RL post-training success.
Pre-VLA is a multimodal runtime verifier that predicts safety confidence and advantage scores for action chunks, raising closed-loop success rates on the LIBERO benchmark from 30.79% to 37.62%.
citing papers explorer
-
ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies
ReCoVLA improves VLA policy reliability by using a VLM as a semantic reward selector to train residual recovery policies in simulation, raising average success from 36.7% to 66.7% in sim and achieving 61.7% in zero-shot sim-to-real physical tests.
-
ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies
ActProbe is an action-space detector that uses temporal consistency error and action chunk magnitude from policy outputs, mapped via LSTM-MLP, to predict failures earlier than baselines across policies and real-robot tasks.
-
Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies
DVAC uses denoising variance as an intrinsic signal to adaptively chunk actions in flow-based robot policies, improving success rates and cutting replans on LIBERO, RoboTwin, CALVIN, and real-world tasks.
-
NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Models
NoiseGate learns per-latent timestep schedules as an information-gating policy in diffusion-based world action models, yielding consistent gains on RoboTwin manipulation tasks.
-
SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
SpecRLBench is a new benchmark evaluating generalization of LTL-guided RL methods across navigation and manipulation domains with static/dynamic environments and varied robot dynamics.
-
Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
A memory-guided LLM harness that calls a frozen VLA only for contact-rich phases lifts success to 82.4% on LIBERO-Pro, 55.4% on RoboCasa365, and 58.4% on RoboTwin C2R with no policy finetuning.
-
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.
-
InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous Manipulation
InDex adapts parallel-gripper VLA policies to dexterous hands by conditioning a diffusion hand policy on a normalized scalar grasp intent, raising average simulated task success from 50.3% to 85.8%.
-
FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning
FiberTune is a new fine-tuning objective that preserves action-fiber visual residuals in VLA policies, yielding performance gains on simulation and physical robot tasks.
-
What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
PAIR-VLA adds invariance and sensitivity objectives over paired visual variants during PPO fine-tuning of VLA models, yielding 9-16% average gains on ManiSkill3 under distractors, textures, poses, viewpoints, and lighting shifts.
-
Reinforcing VLAs in Task-Agnostic World Models
RAW-Dream disentangles world-model learning from task data by using a pre-trained task-agnostic world model and VLM rewards, with dual-noise filtering, to enable zero-shot VLA adaptation in simulation and real settings.
-
DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training
DORA's multi-version streaming rollout enables 2-3x higher throughput in asynchronous RL for LLMs while preserving convergence by maintaining policy consistency, data integrity, and bounded staleness.
-
JigsawRL: Assembling RL Pipelines for Efficient LLM Post-Training
JigsawRL achieves up to 1.85x higher throughput in LLM RL pipelines via pipeline multiplexing, sub-stage graphs, and look-ahead scheduling compared to prior systems.
-
AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
AsyncVLA adds asynchronous flow matching and a confidence rater to VLA models so they can generate actions on flexible schedules and selectively refine low-confidence tokens before execution.
-
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
FORCE is a 3-stage RL fine-tuning method for VLA models that stabilizes Q-function via on-policy warm-up and filters high-value actions for updates, claiming 79% success rate gains and 32.5% faster training without human intervention.
-
MagicSim: A Unified Infrastructure for Executable Embodied Interaction
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
-
TacCoRL: Integrating Tactile Feedback into VLA via Simulation
TacCoRL integrates tactile feedback into VLA policies via real-aligned simulation co-training and RL, raising average success from 50% to 72.5% on four bimanual contact-rich tasks with direct real-robot transfer.
-
Sword: Style-Robust World Models as Simulators via Dynamic Latent Bootstrapping for VLA Policy Post-Training
Sword improves world model simulators for VLA policies by disentangling visual style from dynamics and bootstrapping latents for better consistency, outperforming baselines on LIBERO in generalization and RL post-training success.
-
Pre-VLA: Preemptive Runtime Verification for Reliable Vision-Language-Action and World-Model Rollouts
Pre-VLA is a multimodal runtime verifier that predicts safety confidence and advantage scores for action chunks, raising closed-loop success rates on the LIBERO benchmark from 30.79% to 37.62%.