Search

Any time Past 24 hours Past week Past monthSort:Relevance Newest

Benchmark

LIBERO

Reported in 31 papers on Zotpaper. The latest, each as the paper states it:

AI robot controllers raise average task success from 33% to 95%85% success rate
Simple prompt trick stops AI agents from faking progress in robot tasks51.4% Success@25
Scoring imagined futures and actions before execution triples robot success rates78.3% mean success

LIBERO-Plus (16)LIBERO-PRO (6)LIBERO-Long (3)All benchmarks →

3 results for “LIBERO”

Research · Efficiency & systems
Robot fleets can finish more work with fewer active robots
Serving Agentic Robot Fleets: Workload Characterization, KV-Cache Thrashing, and Admission Control
In sustained replay of robot workloads, limiting active episodes restored shared computing throughput and roughly quadrupled completed programs.
LIBERO-PRO: 7.78 s Astra request latency (median) (as reported)
3 Nov 2026Huawei Inc.
Research · Robotics & embodied AI
Robot AI speed depends more on action generation than model size
VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware
Benchmarking 18 models with a seven-stage inference breakdown reveals that kernel fusion and few-step generation are key to real-time robot control.
LIBERO-10: 114 ms latency (as reported)
27 Oct 2026National University of Singapore, 0G Labs
Research · Robotics & embodied AI
Caching frozen model states makes forward-only robot adaptation much faster
VLA-ZO: Fast Zeroth-Order Adaptation for Vision-Language-Action Models
VLA-ZO accelerates memory-efficient adaptation by updating only action components and reusing vision-language conditioning across parameter perturbations.
LIBERO camera-viewpoint shifts: 58.17% average task success (as reported)
8 Oct 2026UNIST