ModelsSelected

T-Rex Dexterous Manipulation System

T-Rex: Tactile-Reactive Dexterous Manipulation Website: https://t.co/3irVptK79y Open dataset: https:...

Why we picked it

T-Rex offers researchers and developers in ASEAN access to advanced tactile manipulation tools for robotics applications at no cost.

T-Rex is a tactile-reactive dexterous manipulation system with a 100-hour dataset containing 7,700+ trajectories and 200+ everyday objects.

Body

The system uses a MoT architecture with spatial-temporal tactile encoding and achieves over 30% higher success rate than baselines across 12 real-world tasks.

The team combined 22,889 hours of human egocentric pretraining with tactile-grounded robot mid-training.All components including dataset, models, and code are fully open-sourced.

Original · Jim Fan

T-Rex: Tactile-Reactive Dexterous Manipulation Website: https://t.co/3irVptK79y Open dataset: https:...

T-Rex: Tactile-Reactive Dexterous Manipulation Website: tactile-reactive-dexterous.github.io Open dataset: huggingface.co/datasets/zekai… This work is led by @Dantong_Niu and co-advised by @trevordarrell . Congrats to the team! x.com/Dantong_Niu/st… Dantong Niu @Dantong_Niu Excited to share T-Rex: Tactile-Reactive Dexterous Manipulation 🦖🤖 Touch is fundamental to human dexterity, yet most Vision-Language-Action (VLA) models either ignore tactile feedback or lack the ability to react to high-frequency contact signals. In this work, we tackle both the data and architectural challenges of tactile-reactive dexterous manipulation. 🦖 A 100-hour tactile-synchronized dexterous manipulation dataset with 7,700+ trajectories, 22 motor primitives, and 200+ everyday objects. 🦖 A tactile-reactive MoT architecture with spatial-temporal tactile encoding and asynchronous high-frequency tactile refinement. 🦖 A scalable training recipe combining 22,889 hours of human egocentric pretraining with tactile-grounded robot mid-training. Across 12 real-world contact-rich manipulation tasks, T-Rex achieves over 30% higher average success rate than the strongest baseline. We are fully open-sourcing the dataset, models, teleoperation stack, training code, and inference pipeline. 🌐 Pro tactile-rex.github.io RR8YXU 📄 arxiv.org/abs/2606.17055 2UNLlqc � github.com/ZhuoyangLiu200… kCxUtwKC 🤗 huggingface.co/datasets/zekai… NwW8dcRZL 🧵 Thread ↓

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk. Key entities and technical topics under continuous tracking include T-Rex, datasets, open source.

Source attribution: curated from Jim Fan (@DrJimFan).