RynnWorld-Latent conditions a world model on universal latent actions
Pretraining spans 23 datasets and about 553.5 million frames, then adapts to target robots without a shared action space.
46
Product
LIBERO
- Mentions · 7d0
- Mentions · 30d12
- All mentions17
- First seenAug 31, 2026
- Last mentioned7d ago
Timeline
17 articles · newest firstJust 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%.
46
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.
42
LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation
LIBERO-PeRM benchmarks whether robot policies satisfy user preferences separately from completing manipulation tasks.
33
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.
38
LIBERO-Industry benchmarks robot policies under factory process constraints
Five generalist policies, including vision-language-action models, degrade as industrial constraints are combined.
36
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.
38
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.
46
CARE: Certifying Acceleration for Vision-Language-Action Inference
CARE certifies VLA inference accelerators so speedups stay inside a user-specified failure budget.
48
Recursive Video In-Context Learning for Agentic Robot
RV-ICL lets robot agents navigate one demo video, raising LIBERO success without extra training.
46
TAPDreamer: Transferable Adversarial Patches for World Action Models
TAPDreamer crafts transferable adversarial patches that drop world-action robot success to near zero without querying policies.
62
SimForcing: Distilling Simulation Motion Priors into Real-Domain Robot World Models
SimForcing distills simulation motion into robot world models and improves LIBERO policy success.
44
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
DiVeR reweights VLA verifier training toward decision-critical states, improving robot task success with little inference overhead.
48
FastOPD: On-Policy Distillation for Lightweight VLA Deployment
FastOPD distills large vision-language-action models into few-step students that keep most performance at much lower latency.
52
Rolling-WAM: World Action Models with Rolling Imagination
Rolling-WAM speeds robot replanning 4.5x by staggering joint video-action denoising across cycles.
44
Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies
A 0.8B robot policy distilled from cached world-model features hits 97.9% on LIBERO without extra test-time compute.
54
EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents
Researchers introduce EmbodiedSkills, a framework treating VLA skill decisions as verified execution proposals, reaching 86.2% success on RoboTwin 2.0.
46
Appears with
- pi0.5ai model · 5
- RoboTwinproduct · 5
- LIBERO-Plusproduct · 3
- FastWAMai model · 2
- RoboTwin 2.0product · 2
- ImageWAMai model · 1
- Unitreevendor · 1
- SimForcingai model · 1
- VLA-Deltaai model · 1
- RPentai model · 1
- Llama-3.1-8Bai model · 1
- π0-FASTai model · 1
- pi0ai model · 1
- RoboCasaproduct · 1
- NVIDIAvendor · 1
- Qwen3.5-9Bai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.