AI Paper Atlas

Research map / Benchmarks / LIBERO Avg.

LIBERO Avg. leaderboard

12 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on LIBERO Avg.. Best success rate: 98.8 (StarVLA-α (MLP head, specialist), ECCV 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

LIBERO Avg. · success rate

12 papers, each with its best reported number for its own method; higher is better.

#success rate ↑MethodPaperTopic
198.8StarVLA-α (MLP head, specialist)
Qwen3-VL-4B
Less is More: Reducing Complexity in Vision-Language-Action Systems
ECCV 2026 · Table 1
Robot action and navigation
298.6OpenVLA-OFT+ActionUNet
OpenVLA-OFT
ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning
NeurIPS 2026 · Table 2
Robot action and navigation
398.1WAV (Ours)World–Value–Action Model: Implicit Planning for Vision–Language–Action Systems
NeurIPS 2026 · Table 1
Robot action and navigation
498.1X-VLA-0.9BX-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
ICLR 2026 · Table 2
Robot action and navigation
598BehaviorVLA
pi0.5
From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
ICML 2026 · Table 2
Robot action and navigation
697.9LaRA-VLA
Qwen3-VL (4B)
Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models
ICML 2026 · Table 2
Robot action and navigation
797.8pi0.5 (Few-shot) + VLA-Corrector
pi0.5 few-shot
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
NeurIPS 2026 · Table 2
Robot action and navigation
897.2T2VLA (self-reward)
OpenVLA-OFT
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
ECCV 2026 · Table 1
Robot action and navigation
997CronusVLA
7B
Towards Efficient and Robust Manipulation via Multi-Frame Vision-Language-Action Modeling
AAAI 2026 · Table 2
Robot action and navigation
1096.4GR00T N1.5 + RS-CLContrastive Representation Regularization for Vision-Language-Action Models
ICML 2026 · Table 2
Robot action and navigation
2 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.