Skip to content
Only Research#Embodied AI

#Embodied AI

Oct 8

TodayOct 8Thu5 items
  1. PandailyAI score41

    Simplexity Robotics Trains One Robot to Tend Two CNC Lathes With 600 Trajectories

    Simplexity Robotics says it trained a single robot to load and unload two CNC lathes on its own, using 600 real-robot trajectories and reporting a 100% success rate on the precision CNC insertion task. The work, presented at IROS 2026 on September 29, combines the SimpleWAM world action model, a DRAM memory module and DPE action scoring, with force and torque feedback for insertion recovery. The company did not say how many trials the 100% figure covers, and it does not describe the yield of the whole cell.

  2. QbitAI (量子位)AI score58

    AgentGarten lets agents evolve through code-built worlds and neural rendering

    MirroS released AgentGarten, which pairs executable code environments with a real-time neural renderer running above 30 fps so agents can act, observe, and learn. In a one-on-one hide-and-seek setup, the hider learned to block passages by round 4 and the seeker learned to climb ramps by round 10, guided by notes the agents wrote after each round. The authors report applying the same loop to four other tasks, including a dog-companion game, a narrow-bridge car passing task, herding, and quarry loading.

  3. PandailyAI score44

    Donghua University Spins Transistors Into Fibers That Act as Soft Robot Circuits

    Donghua University researchers spun transistors, resistors and capacitors into a continuous fiber that functions as a circuit, using microfluidic encoded spinning, according to a Nature Electronics paper. The fibers integrated multicolor electroluminescence, analog and digital logic, and non-contact spatial sensing, and in demonstrations guided a robotic gripper and let a finger control a robotic arm and drone without touch.

  4. Leiphone (雷峰网)AI score46

    IROS 2026 papers show AI reintegrating with classical robotics rather than replacing it

    Of 1,933 IROS 2026 papers, Robot Learning/Embodied AI appears in about 809, while Navigation/Planning covers 564 and Perception/Vision 556. The article argues large models are being embedded into traditional planning, geometry, and control rather than replacing them. Vision-language-action models are shifting toward efficiency, 3D understanding, memory, and system integration.

  5. PandailyAI score46

    Galbot and Tsinghua's LATENT Wins IROS Award for Humanoid Tennis Forehand

    A Galbot, Tsinghua University and collaborators paper won IROS 2026's Best Entertainment and Amusement Paper Award for LATENT, a humanoid tennis-return method trained on imperfect amateur motion-capture clips. In simulation, the full forehand policy succeeded on 96.52 percent of returns, versus 71.85 percent for PULSE. On a real Unitree G1, the paper reports 90.90 percent forehand success across 20 consecutive rallies, with motion capture still used rather than the robot's own cameras.

Oct 7

Oct 7Wed
  1. IEEE Spectrum · AIAI score32

    HiPHI: A Large-Scale Benchmark for High-Precision Human Motion and Object Interaction

    HiPHI is a 617.5-hour whole-body human motion dataset captured with optical motion capture at sub-millimeter accuracy, including 245.7 hours of human-object interaction with synchronized object trajectories and meshes. The dataset organizes coverage using FrameNet, a linguistic framework for human action. The white paper also reports results from policies trained on HiPHI and deployed on a physical Unitree G1 humanoid robot.

Oct 1

Oct 1Thu
  1. OdysseyAI score30

    Today we’re introducing PROWL-2, where agents and their world model improve through recursive learning. Agents expose errors in imagination, and repairing those errors enables further learning. We believe this open-ended learning is a critical step towards superintelligence.

    Today we’re introducing PROWL-2, where agents and their world model improve through recursive learning. Agents expose errors in imagination, and repairing those errors enables further learning. We believe this open-ended learning is a critical step towards superintelligence.

  2. OdysseyAI score26

    We're very excited about PROWL-2. This recursive loop delivers up to 91% relative gains over the StarCraft world-model baseline, alongside stronger robot coordination in simulation. Learn more, read the PROWL-2 paper, and let us know any questions! https://odyssey.systems/introducing-prowl-2

    We're very excited about PROWL-2. This recursive loop delivers up to 91% relative gains over the StarCraft world-model baseline, alongside stronger robot coordination in simulation. Learn more, read the PROWL-2 paper, and let us know any questions! https://odyssey.systems/introducing-prowl-2

Sep 27

Sep 27Sun
  1. Sakana AIAI score46

    Sakana AI's SAIL boosts VLM robot trajectory success via test-time scaling

    Sakana AI and the University of Tokyo introduced SAIL, a method that generates robot trajectories with a VLM and refines them through simulator testing, VLM feedback, and Monte Carlo tree search. Across six simulated manipulation tasks, raising the search budget from one candidate to 45 increased the success rate of finding a working trajectory from 25% to 73%. The authors also tested the approach on a physical robot, though the post frames further transfer to real hardware as an open question.

Sep 23

Sep 23Wed
  1. Microsoft ResearchAI score34

    Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. https://msft.it/6014agepg

    Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. https://msft.it/6014agepg

Sep 8

Sep 8Tue
  1. BAAIAI score34

    Knowing one move is not the same as doing the whole job. The models were trained to grasp, place, pull, open. Then they were asked to string those moves together. No extra practice on the full task. Best score: 16.7%. Some models: ZERO. A robot can open a drawer and then get stuck on the handle.

    Knowing one move is not the same as doing the whole job. The models were trained to grasp, place, pull, open. Then they were asked to string those moves together. No extra practice on the full task. Best score: 16.7%. Some models: ZERO. A robot can open a drawer and then get stuck on the handle.

  2. BAAIAI score46

    In simulation, the best models finish easy tabletop tasks about 98% of the time. On physical Franka hardware, the success rate falls to 24%–72% of what the model achieves in simulation. With a dual-arm configuration, the range is 13%–60%. Two models that look tied in sim can be 30 points apart on hardware. Sim is the practice room. The robot is the test.

    In simulation, the best models finish easy tabletop tasks about 98% of the time. On physical Franka hardware, the success rate falls to 24%–72% of what the model achieves in simulation. With a dual-arm configuration, the range is 13%–60%. Two models that look tied in sim can be 30 points apart on hardware. Sim is the practice room. The robot is the test.

  3. BAAIAI score43

    Embodied AI demos are advancing rapidly, but how much do high benchmark scores actually reflect physical reality? Introducing FlagEval-Robo — an open, dual-track evaluation suite connecting simulation with real-world execution. We systematically post-trained and stress-tested 12 leading open-weight models under strictly aligned conditions. Here is what we discovered👇

    Embodied AI demos are advancing rapidly, but how much do high benchmark scores actually reflect physical reality? Introducing FlagEval-Robo — an open, dual-track evaluation suite connecting simulation with real-world execution. We systematically post-trained and stress-tested 12 leading open-weight models under strictly aligned conditions. Here is what we discovered👇

Aug 21

Aug 21Fri
  1. Jim FanAI score59

    NVIDIA and Berkeley open-source T-Rex, a tactile robot learning method

    NVIDIA and Berkeley are open-sourcing T-Rex, a methodology for adding touch sensing to robot manipulation models. It uses a mixture-of-transformer with a slow visuomotor expert and a fast tactile expert running four touch ticks per vision tick. A 50-hour dataset of about 5,500 episodes from 22-degree-of-freedom tactile hands is available on Hugging Face.

Aug 19

Aug 19Wed
  3. GeneralistAI score31

    Fine-tuned (or prompted) behaviors generalize beyond their demonstrations, and can improvise fundamentally different manipulation strategies to achieve the same goal. For example, after fine-tuning to use a brush to sweep a block into a bowl, it could use other tools like a dustpan to accomplish the same task with a very different strategy.

    Fine-tuned (or prompted) behaviors generalize beyond their demonstrations, and can improvise fundamentally different manipulation strategies to achieve the same goal. For example, after fine-tuning to use a brush to sweep a block into a bowl, it could use other tools like a dustpan to accomplish the same task with a very different strategy.

  5. GeneralistAI score34

    For few-shot learning, it can adapt to new physical tasks in as few as 1 - 10 gradient steps on 1 - 5 minutes of data (~10 - 50 demonstrations). In practice, this can be described as test-time training in a low-data regime. We did not tune this procedure or sweep hyperparameters; these results come largely out of the box.

    For few-shot learning, it can adapt to new physical tasks in as few as 1 - 10 gradient steps on 1 - 5 minutes of data (~10 - 50 demonstrations). In practice, this can be described as test-time training in a low-data regime. We did not tune this procedure or sweep hyperparameters; these results come largely out of the box.

  6. GeneralistAI score46

    Generalist model learns physical tasks from one or few demonstrations

    Generalist's model reached 59% average success on 10 diverse physical tasks with one-shot prompting straight from pretraining. With few-shot learning, using 10 gradient steps on 5 minutes of data per task, performance rose to 83%. The post calls it the first model it knows of that learns a wide range of dexterous closed-loop physical tasks from one or few demonstrations.

  7. GeneralistAI score34

    In some cases, in-context learning with GEN-1.5 transfers across the embodiment gap entirely: a human demonstrates a task with their own hands, observable through the robot’s cameras, and the robot can reproduce it immediately afterward.

    In some cases, in-context learning with GEN-1.5 transfers across the embodiment gap entirely: a human demonstrates a task with their own hands, observable through the robot’s cameras, and the robot can reproduce it immediately afterward.

  8. GeneralistAI score38

    In-context learning also crosses the sim-to-real gap, zero-shot. Prompts can be formed entirely from simulated experience (e.g., from a scripted policy, an RL agent, or a human teleoperating a simulated robot) and be used to produce behaviors on a real robot. The model was not trained on the task in either the simulator or the real world.

    In-context learning also crosses the sim-to-real gap, zero-shot. Prompts can be formed entirely from simulated experience (e.g., from a scripted policy, an RL agent, or a human teleoperating a simulated robot) and be used to produce behaviors on a real robot. The model was not trained on the task in either the simulator or the real world.

Aug 17

Aug 17Mon
  1. Rowan CheungAI score34

    Keio and MIT Media Lab unveil a floating helium-filled companion robot

    Researchers from Keio University and the MIT Media Lab built a soft, helium-filled robot with gentle flapping fins and no face, rotors, or pinch points. In demos it served as an alarm clock, study buddy, movement reminder, and dance partner, communicating through movement. The team designed it to avoid the uncanny valley and be safe to touch, betting people will welcome it into their personal space.

Jul 15

Jul 15Wed
  1. Fei-Fei LiAI score60

    RoboTTT scales robot policy context to 8,000 timesteps using test-time training

    Stanford SVL and NVIDIA Robotics introduced RoboTTT, which uses test-time training to give robot policies up to 8,000 timesteps of context at constant inference cost. The source reports that 8K-context pretraining beats 1K by 62%, and that performance keeps improving from 128 to 8K timesteps with no sign of saturation. The authors also describe one-shot imitation from human video and in-episode error recovery.

  2. Jim FanAI score62

    RoboTTT scales robot policy context to 8,000 timesteps with constant inference cost

    Jim Fan introduced RoboTTT, a robot model that uses test-time training to compress history into a tiny inner model updated at each sensor reading. The post reports closed-loop performance rising steadily from 128 to 8K timesteps, and 8K-context pretraining beating 1K by 62%. It also claims one-shot in-context learning from human video and mid-episode error recovery, with learning continuing after deployment.

Jul 9

Jul 9Thu

Jul 1

Jul 1Wed
  1. Jim FanAI score51

    Jim Fan introduces ASPIRE, a self-evolving robot skills library for continual learning

    Jim Fan announces ASPIRE, a system where coding agents use multimodal sensory traces from simulation and real robots to run evolutionary search over control programs and add the results to a growing skills library. The post claims up to a roughly 10x reduction in transfer learning tokens for sim-to-real and single-arm to bimanual transfer, and says the full stack will be open-sourced.

Jun 30

Jun 30Tue
  1. Jim FanAI score60

    ASPIRE lets robots build an evolving skills library that transfers across tasks

    Jim Fan introduces ASPIRE, a system in which coding agents observe multimodal sensory traces and run evolutionary search over control programs to distill skills into a growing library. The post says ASPIRE shares know-how rather than pixels or weights across the sim-to-real gap, reducing transfer learning tokens by up to about 10x. The author also says the full stack will be open-sourced and provides a gallery of 150+ tasks and 90+ skills.

Mar 17

Mar 17Tue
  1. BAAIAI score46

    BAAI unveils RoboBrain-Dex, dexterous manipulation trained on human egocentric data

    BAAI has released RoboBrain-Dex, a dexterous manipulation model for embodied intelligence trained on large-scale, diverse human egocentric data rather than massive robot teleoperation datasets. The company says this approach yields strong generalization, marking a shift from small-data, weakly generalizing methods toward big-data robotic manipulation. The code has been open-sourced on GitHub.

Feb 25

Feb 25Wed
  1. Jim FanAI score75

    EgoScale trains a 22-DoF humanoid mostly on 20,000 hours of human video

    Researchers trained a humanoid with 22-DoF dexterous hands mainly on over 20,000 hours of egocentric human video, with no robot in the loop, to perform tasks such as assembling model cars and folding shirts. They report a log-linear scaling law (R² = 0.998) between human video volume and action prediction loss, and state that this loss predicts real-robot success rate. The recipe, called EgoScale, pre-trains GR00T N1.5 on the video, adds only 4 hours of robot play data, and reports a 54% gain over training from scratch across five dexterous tasks.