#Robotics
Curated coverage on «Robotics»: releases, research, benchmarks, open-source.
Alibaba DAMO Releases RynnUnify: A 16B Model That Plans in Video and Drives a Robot
The 16B-parameter RynnUnify combines scene understanding, video generation and robot control: 51.5% success on 20 RoboCasa365 tasks and 46.7% on three real-world…
HOLI-World Teaches a 4B Model to Understand the World from First-Person Recordings
HOLI-World's authors built an ecosystem of ~100 scenes and ~80K QA pairs so that HOLIWORLD-VL-4B can better understand space and time from egocentric video.
Tsinghua's LoopWAM Tops RoboChallenge Table30 and Goes Open Source
LoopWAM, a world action model from Tsinghua, 原力灵机 and 极寰时代, took first place on the RoboChallenge Table30 benchmark. The code, paper and project page are already…
Echo Teaches VLA Robots to Recognize Success and Failure Inside Their Own Actions
HiSTEVE 1.0 Plays Minecraft With a Mouse and Keyboard: 85.0% on MineStudio Bench
LeWorldModel Tested for Action Sensitivity: Axes Diverge by 36–42°
FocusVLA Teaches a Robot to Pick a Camera Based on Task Stage: +13.3 pp in Real-World Tests
NVIDIA open-sources Flora: robot data labeling 125 times cheaper than GPT-6 Astra
NVIDIA has open-sourced Flora, the labeling engine for GR00T. It labels 200 000 hours of data a day on 512 GB300 and costs about 125 times less than GPT-6 Astra.
HiP3R assembles 3D scenes from thousands of video frames without retraining models
Researchers at NTU Singapore proposed a hierarchical pose graph: video chunks are first aligned in Sim(3), then each frame gets a single shared SE(3) camera.
TARSphere Tests MLLM-Powered Robots Across 360 Episodes in 30 Scenes
SplatLab writes its own 3D Gaussian Splatting papers and beats baselines by up to +3.78 dB
Survey: Robots Are Learning to Improve Their Own Learning, but Evidence Is Still Missing
SERA teaches a VLM planner to self-evolve: robot scores 51.38% on RoboMME
LEGO-SCD learns to detect changes in 3D scenes at 17.2 FPS without manual labeling
LEGO-SCD trains on automatic edits to 3D Gaussian Splatting scenes and posts top results: 67.64% mIoU on PASLCD, 75.82% on CCS3D, and 17.2 FPS.
Huawei openJiuwen connects an LLM to lab equipment for electrocatalysis
Huawei's openJiuwen team and its computing platform team closed the loop: an LLM designs an electrocatalysis experiment, and physical instruments carry it out.