DRAP cuts plasticity in OpenVLA for replay-free continual learning
Risk-weighted gradient memory scales each tensor’s AdamW rate and retains prior LIBERO behaviors better than EWC.
Stories per day · 30 days
3 RSS
Relatedrobotics15vision-language-action5embodied-ai3policy-learning3reinforcement-learning3vla3benchmark2robotwin2simulation2world-model2coda1continual-learning1failure-recovery1flow-matching1latent-actions1mamba1meta-world1onewm1
42 stories, newest first · one card per story
Stories tagged #libero
REA runtime coordinates slow planners with fast robot policies
On 3,000 LIBERO-Pro episodes it reports 95.9% success, 25% fewer control steps, and 17% less control time than waiting on the brain.
Just Action Models match world-action policies without visual generation
Against FastWAM, reported LIBERO success moves from 97.0%, 55.3%, and 91.2% to 98.2%, 64.5%, and 91.4%.
Backtrack lets frozen vision-language-action policies retry failed motions
On LIBERO-Long, failure rates fall 19–48% and success rises by up to 7.4 points; the head adds 0.48–0.88% parameters.
Frontier models scored on LIBERO-10 robot tasks without fine-tuning
Across 1,800 episodes, GPT-6 Astra led at 44% success and Gemini-4 Argon followed at 43%.
ALPS unifies language, reconstruction and state in one visual encoder
Frozen ALPS tokens reach 85.5% mean policy success on LIBERO and match a 3.5x larger V-JEPA 2-L on state probes.
AgenticRoboRL post-trains robot planners across different harnesses
On LIBERO-PRO, a 9B planner rose from 18.1% to 71.0% success without external memory.
MambaAct swaps pi0.5 transformer action expert for compact Mamba
The public model keeps the pi0.5 vision-language encoder, shrinks the action expert 10 times, and raises mean LIBERO success by 1.08 points.
LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation
LIBERO-PeRM benchmarks whether robot policies satisfy user preferences separately from completing manipulation tasks.
CoDA: Co-Evolution of Data Engines and Action Policies
CoDA co-evolves robot simulation data and policies, lifting out-of-distribution success from 5.3% to 27.6%.
Can World and Action Modeling Benefit Each Other under Unified Causal Training?
OneWM shows unified causal training lets world modeling and action learning improve each other.
VLA-Δ: Learning Physical State Transition for Vision-Language-Action Models
VLA-Δ trains robot policies on physical state transitions and beats π0.5 in real-robot tests.
CoDA: Co-Evolution of Data Engines and Action Policies
CoDA co-evolves simulation data engines and robot policies, lifting out-of-distribution manipulation success.
MorphAct generates context-dependent updates for robot policies
The paper reports gains of up to 16.30% on LIBERO and Meta-World and up to 14% over π0.5 in real-world tests.
BridgeWAM links video and action experts with latent queries
The 5.06B model reports 98.25% LIBERO success and 28.72% fewer inference FLOPs than Fast-WAM.
RESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime Monitors
RESCUE finds robot-policy monitor accuracy does not imply lower intervention cost on LIBERO tasks.
RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments
RoboRSI lets a mobile manipulator reuse validated skills, beating baselines by up to 11 points.
Long-WAM: Scaling the Context of World-Action Models
Long-WAM raises robot task success by scaling causal world-action context with autoregressive video pretraining.
Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
One-word instruction edits swing VLA success sharply; rule-based rephrasing improves frozen policies without retraining.
EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
EmbodiedRSI reaches 77% success on RoboCasa365, nearly doubling the best baseline.
PAIR: Bridging Perception and Action in Vision-Language-Action Models
PAIR learns shared perception-action tokens that raise success for OpenVLA-OFT and VLA-Adapter robot policies.
CARE: Certifying Acceleration for Vision-Language-Action Inference
CARE certifies VLA inference accelerators so speedups stay inside a user-specified failure budget.
Recursive Video In-Context Learning for Agentic Robot
RV-ICL lets robot agents navigate one demo video, raising LIBERO success without extra training.
Conditional Trajectory Peaks: Single-Pass Multimodal Policies over Action Chunks
Conditional Trajectory Peaks models multimodal action chunks in one pass, matching pi0.5 at lower latency.