Content types
Research papers
Papers, technical reports, research datasets, and new benchmark designs centered on a new method, experiment, or finding. Releasing code or a physical robot demonstration alongside a paper does not change its main research contribution.
105 selected · 72 in the last 30 days
arXiv cs.RO ·
FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors
The research team proposes FTP-1, a generalist foundation tactile policy pretrained across multiple tactile sensors and embodiments. It uses heterogeneous encoders to map image-, array-, and state-based tactile signals into unified morphology-aware latent tokens, which are jointly modeled by a shared tactile Transformer expert.
arXiv cs.RO ·
Rendering-Free Event Frame Simulation Accelerates Reinforcement Learning for Autonomous Robot Navigation
The authors propose an analytic event simulator that synthesizes event streams directly from scene geometry and ego-motion without image rendering, generating 64x64 event observations in just 17 microseconds on a single GPU, over 400 times faster than state-of-the-art rendering pipelines. Reinforcement learning training for an event-camera obstacle-avoidance policy based on this simulator converges in under 30 minutes, three orders of magnitude faster than training on rendered events, and transfers zero-shot to ray-traced event simulation in Isaac Sim.
Shanghai AI Laboratory - Embodied Intelligence ·
Shanghai AI Laboratory and partners jointly launch materials multimodal large model "Caihua·MatVerse"
Suzhou National Laboratory, Shanghai AI Laboratory, Shanghai Jiao Tong University and others jointly launched the "Caihua·MatVerse" materials multimodal large model and agent application system, which uses an "independent encoders plus unified decoder" architecture to align XRD spectra, electron microscope images and molecular structures into the same semantic space.
机器之心 · 微信公众号 ·
Ropedia Releases Six Research Results, Exploring How First-Person Human Data Can Be Turned into Robot Capabilities
Ropedia released six studies at the first Ropedia Super Week, held October 19 to 23, centered on how first-person human video can be turned into training and execution information usable by robots.
CVer · 微信公众号 ·
Tsinghua AIR proposes OxyGen: unified KV Cache management lets robots talk while acting
The Institute for AI Industry Research (AIR) at Tsinghua University, together with Tsinghua's Department of Electronic Engineering and the University of Science and Technology of China, has proposed OxyGen, which uses unified KV Cache management to let an embodied model's action and language reasoning share prefix computation. The paper has been accepted to NeurIPS 2026.
arXiv cs.RO ·
X-WBC: A Cross-Embodiment Foundation Model for Humanoid Whole-Body Control
X-WBC is a cross-embodiment humanoid whole-body control foundation framework that separates relatively shared human motion semantics from embodiment-specific physical execution. It uses human-centered command tokens to align full human motion, robot reference motion, and sparse VR observations; a causal Transformer learns reusable temporal structure from mixed multi-robot rollouts, and lightweight robot-specific modules map the shared representation to each robot's proprioception and action space.
arXiv cs.RO ·
RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions
The research team proposes the RynnVLA-Latent framework, which uses RynnLAM to learn continuous, 3D-grounded latent actions from visual changes without native robot control signals, converting 30.1K hours of human, robot, and simulation video into 745.52M latent action descriptors for policy pretraining.
机器之心 · 微信公众号 ·
RoboCoach: Using World Models to Locate Weak Subtasks and Improve Long-Horizon Task Success Through Targeted Teaching
Zhang Changshui and Cui Sen's team at Tsinghua University propose RoboCoach, an embodied intelligence system that uses the world model CoachWorld to run closed-loop trials of long-horizon tasks in imagination, identify the first weak subtask that times out, and request targeted human teaching for it, updating only the corresponding skill expert. Under a fixed demonstration budget, the success rate rises from 13.3% to 75.0% on Franka and from 40.0% to 83.8% on AgileX, while the uniform collection baseline reaches only 30.0% and 47.5%, respectively. On four unseen new task routes, the average success rate is 35.0%, compared with 0% for the shared-policy baseline.
arXiv cs.RO ·
Study: Full-weight VLA fine-tuning without an fp32 master copy silently erases most updates
The paper points out that when VLA models are fully fine-tuned in bf16 without keeping an fp32 master copy, AdamW rounds away any update smaller than 1/512 of a weight; 9 of 12 open-source VLA codebases train this way by default or in documented recipes, including LeRobot's SmolVLA default configuration and the π0/π0.5 guides.
arXiv cs.RO ·
RepresentNav: A Navigation Foundation Model Built on a Self-Constructed Representation Space
The authors propose RepresentNav, a navigation foundation model that uses Representation Residuals, a three-layer transformer, to aggregate full-depth features from multiple vision foundation models and construct a representation space driven by the policy's own objectives.
HuggingFace Daily Papers ·
Rollback: Using World-Model Backtracking of Counterfactual Experience to Improve Robot Policies
Rollback proposes a policy improvement paradigm that turns an action-conditioned world model from a one-way simulator into a backtrackable counterfactual engine: it returns to key decision points, branches to try different actions, and compares the outcomes, thereby distilling counterfactual results into action-level supervision without learning a separate value model.
机器之心 · 微信公众号 ·
Tsinghua team builds HandsOn dexterous manipulation benchmark with 66 tasks to evaluate robot bimanual capabilities
Ding Ning's team at Tsinghua University, together with researchers from Beijing University of Posts and Telecommunications, Peking University, and Nature Will, built HandsOn, a simulation platform and evaluation benchmark for cross-embodiment dexterous manipulation, containing 66 manually verified tasks and 18,000 human simulation teleoperation demonstrations.
深蓝AI · 微信公众号 ·
TU Delft's MonoRace achieves 100 km/h autonomous drone racing using only a single front-facing camera
The MonoRace system from TU Delft's MAVLab in the Netherlands, relying only on a single front-facing camera and an IMU, defeated three world-champion-level pilots in a row at the 2025 Abu Dhabi Autonomous Drone Racing competition; the paper was published in Science Robotics on October 14, 2026.
机器之心 · 微信公众号 ·
Harvard, Berkeley, NVIDIA and others propose RAX, using online exploration scaling to let robots learn skills with zero demonstrations
A research team from Harvard, NVIDIA, Berkeley, MIT and Stanford proposes RAX (Robot Agent eXploration), which connects a general coding agent to robot perception and control interfaces, uses online exploration to write successful decisions into executable programs and accumulate them as reusable skills, while keeping model parameters frozen.
HuggingFace Daily Papers ·
RynnVLA-Latent: Scaling robotic manipulation foundation models with 3D latent actions
The research team proposes the RynnVLA-Latent framework, which uses RynnLAM to learn continuous, 3D-grounded latent actions from visual changes without requiring native robot control signals. The method processes 30.1K hours of human, robot, and simulation video, generating 745.52M latent action descriptors, then uses flow matching to predict latent action chunks and adapt them to specific embodiments.
云深处科技 · 微信公众号 ·
DEEP Robotics unveils five embodied brain results: world model DR-WM-1.0, VLA model DR-VLA-2.0, and more
DEEP Robotics has released five research results centered on its self-developed embodied brain, DEEPRobotics-Brain, including the world model DR-WM-1.0, the embodied foundation model DR-VLA-2.0, the embodied agent DR-Agent, the policy optimization framework DR-APO, and the data closed-loop platform DR-Benchmark. The company is also collaborating with seven universities, including MIT, Tsinghua, and Zhejiang University.
Kinetix AI · YouTube ·
KAI Halo case study EgoWild2Dex: training bimanual dexterous manipulation with first-person data
The KAI Halo case study EgoWild2Dex shows how high-quality bimanual dexterous manipulation capabilities can be derived from highly challenging egocentric data. The project page is https://mmlab.hk/egowild2dex.
简智机器人 · X ·
Genrobot open-sources Gen-HumanWholeBody first-person whole-body manipulation dataset
Genrobot has released and open-sourced Gen-HumanWholeBody, a first-person whole-body manipulation dataset it says has the industry's highest precision, hosted on Hugging Face. The dataset contains 600 hours of whole-body manipulation data, approximately 3 cm whole-body MPJPE, 16,976 real-world scenes, and 1,281 human skills, and is open for research on whole-body motion learning, human-to-robot transfer, and embodied foundation models.
北京理工大学 · 微信公众号 ·
BIT team publishes meter-scale titanium alloy single-crystal additive manufacturing results in Nature
A team led by Professor Liu Changmeng at Beijing Institute of Technology has pioneered a single-crystal additive manufacturing method based on unsteady pulsed growth in a micro-melt pool, achieving meter-scale titanium alloy single-crystal additive manufacturing for the first time. The results were published in Nature on October 21 in a paper titled "Additive manufacturing ultralong and architected single crystals," with corresponding authors Liu Changmeng, Cui Yinan of Tsinghua University, and Yinmin Morris Wang of the University of California, Los Angeles.
arXiv cs.RO ·
Learning from Fleet Experience: Collective Experience Learning Across 96 Robots
The paper proposes the Collective Experience Learning (CEL) paradigm, in which deployed robots pool their own execution experience to update a shared policy that is then returned to the fleet for use. It is implemented through failure-guided experience retrieval fine-tuning (FERT), which uses failure contexts to retrieve relevant segments from successful trajectories and prioritizes their recorded actions for supervised updates, without additional expert demonstrations or corrective actions; a supporting fault-tolerant asynchronous training system (FATS) coordinates robot execution, cloud inference, and policy optimization.