Technology areas
Robot models and learning
Robot VLA models, general action and world models, imitation and reinforcement learning, skill and motion policy learning, online adaptation, and transfer across tasks and robot bodies. The contribution is a model, policy, or learning method. Dataset releases belong under Data and simulation; inference deployment belongs under Software and compute systems.
206 selected · 116 in the last 30 days
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.
Union Square Ventures · X ·
USV and Creandum co-lead $40 million seed round for Machenta
USV announced that it co-led Machenta's $40 million seed round with Creandum, as the company also emerged from stealth. Machenta says its robotics foundation model is trained entirely in simulation, with no real-world data, and can learn a task from a single demonstration without additional training, adapting when the environment changes.
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.
云启资本 ·
Synrise completes Pre-A round exclusively invested by Yunqi, first smart knee S5 in mass production
Synrise announced the completion of a Pre-A funding round exclusively invested by Yunqi Capital, with proceeds going toward the SynchroMind algorithm foundation, R&D for next-generation products, and global market expansion. Within one year of founding, the company's first product, the Synrise S5 bionic intelligent hydraulic knee, has entered mass production, completed validation deployments in Europe, and received orders exceeding ten million yuan from domestic and overseas markets. A next-generation AI active-power knee is now in R&D, aiming to move from compliant motion to active power output.
Kinetix AI · YouTube ·
Kinetix AI releases KAI World Model, supporting locomotion and manipulation tasks
Kinetix AI has released the KAI World Model, which is based on parallel video generation and 4D spatial modeling and can simultaneously generate virtual worlds and reconstruct spatial scenes. The model was pre-trained on millions of videos and supports pure locomotion, pure manipulation, and coordinated locomotion-manipulation tasks; it claims generalization across tasks and across robot embodiments. Live demonstrations include a robotic arm autonomously opening a beverage can and a humanoid robot playing real-time table tennis rallies.
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 ·
AgiBot Team Releases GE-Act 2.0 World-Action Model Technical Report
The AgiBot Research Team released a technical report on GE-Act 2.0, a world-action model whose generative and action components are all trained from scratch on manipulation data. It consists of a control-oriented autoencoder (CoAE), a single-step visual planner (SVP), and an inverse dynamics model (IDM), and is jointly trained with KASO.
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.
AgiBot ·
AgiBot releases Genie Studio 2.0 embodied intelligence development and deployment platform
AgiBot has released Genie Studio 2.0, an embodied intelligence application platform covering development, deployment, and operations. It consists of three modules—Flywheel, Agent, and Monitor—that connect data collection, model training, evaluation, inference, task orchestration, and robot fleet management.
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.
中科慧灵 · 微信公众号 ·
CASBOT completes several-hundred-million-yuan A++ round to advance embodied intelligence mass production and delivery
CASBOT completed an A++ funding round of several hundred million yuan, jointly invested by Zhilai Investment, Yonghua Investment, Maotian Investment, Yuanhe Chenkun, Guoke Kezhi, Luning Investment and others. The funds will be used for product mass production and delivery, R&D iteration of embodied brain technology, and market expansion. The company's self-developed CASBOT PA perception-to-action model has been validated at actual workstations in a shoe factory in Putian, achieving a cycle time of 7 seconds per piece for the outsole stamping process and 18 seconds per pair for sole pressing. In 2026, its total orders for embodied shoe-making robots exceeded 400 million yuan, with equipment production scheduling reaching the scale of several thousand units.
Robotics & Automation News ·
Dream Labs raises $90 million seed round and launches Dream API and Dream-1 model
Dream Labs announced it has completed a $90 million seed round led by B Capital, with participation from Kindred Ventures and others. The company also launched Dream API, which can convert robot camera footage and natural-language instructions directly into motor commands, and said its flagship model Dream-1 is trained on videos of everyday human tasks and can zero-shot control any robot with a gripper.
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.