robotics
A closed-loop benchmark caught nine world models forgetting the room News
A new benchmark replaced scripted evaluation with an AI agent pursuing long-horizon goals inside generated worlds, and found that all nine leading world models lose spatial consistency and forget what happened out of frame.
Robot Policies That Predict the Touch Before They Make It News
Two matched robotics releases from NeoteAI and Fudan give manipulation policies a sense of touch that anticipates contact rather than reporting it, winning all nine real-robot tasks in the authors' benchmark against strong vision-only baselines.
Seven new papers cannot agree what a world model is made of News
PhiZero compresses video into a learned alphabet of state transitions, but six competing late-July papers argue the substrate should instead be executable simulator code, explicit game state, paired re-renderings, distribution coverage, architecture, or action intent.
Imitation Learning: Teaching Machines by Showing, Not Rewarding Lesson
Imitation learning trains a system by having it copy demonstrations from an expert rather than discover behaviour through trial and error, and behaviour cloning - simply predicting what the expert did in each situation - is the simplest and most widely used version of it.
Figure's viral ladder climb is a two-hour stair timelapse News
A widely shared clip of Figure's F.03 humanoid was reposted as an autonomous ladder climb; the company's own post describes a timelapse of repeated stair traversal that is helping move its robots closer to full autonomy.
Google's Gemini Robotics 2 controls a humanoid from feet to fingertips - for a waitlist News
Google DeepMind announced Gemini Robotics 2 with whole-body humanoid control, 22-degree-of-freedom hands and robots that delegate tasks to each other, but only the reasoning model is available to developers; the control models are in private preview.
Asked to sit in a chair it can see, the best AI model misses five times out of seven News
A new benchmark decouples motor control from decision-making and asks nine frontier vision-language models to find an object, walk to it and sit on it - the best completes 16.8% of episodes, and perception is not the problem.
A robot control model now runs 32 times a second on a gaming GPU, in under a gigabyte News
TurboVLA reaches real-time robot control at 32 Hz using 0.9GB of memory on a consumer RTX 4090, by removing the large language model from the control loop entirely rather than compressing it.
The FCC just added every foreign-made advanced robot to its national security Covered List News
On July 28 the FCC added all foreign-produced advanced robotic devices and foreign-produced power inverters to its Covered List, blocking them from new equipment authorizations, on national security determinations that cite remote commandeering and surveillance risk rather than naming any country or company.
A handheld gripper and a head camera can now train robots with no robot demonstrations News
Researchers report that raising the fidelity of handheld human demonstrations removes the need for any robot teleoperation on the target task, with policies trained on handheld data alone reaching parity with robot-taught baselines on four two-armed tasks.
Black Forest Labs launches FLUX 3 -- image, video, audio, and a robot that never renders the video News
Black Forest Labs announced FLUX 3 on July 23 as a unified image, video and audio model with 20-second video and native audio, available only in early access, with open weights deferred to a later Dev release.
Tencent's Open Robot Model Plans by Imagining the Scene It Wants to Create News
Tencent released RxBrain, an open ~6.2B robot model that interleaves text reasoning with generated goal images, betting that a robot needs an explicit picture of the world it is trying to build.
Sunday Robotics Says Its Robot Folds Laundry Reliably in Homes It Has Never Seen News
Sunday Robotics previewed ACT-2, a home-robotics model reporting 99.1% zero-shot success at folding laundry across diverse, unseen homes -- and proposed a new reliability metric to move robotics past cherry-picked demos.
LaMem-VLA gives robots a working memory so they stop forgetting what they just did News
A new robotics model, LaMem-VLA, fixes the 'short-horizon bias' that makes robots react only to what's in front of them by weaving compressed memories of past actions directly into the model's internal representation -- so it can handle multi-step tasks that require remembering an earlier state.
LaMem-VLA gives robots a memory so they stop forgetting the task News
A new framework called LaMem-VLA tackles the 'goldfish memory' problem in robot policies by compressing past experience into latent memory tokens and weaving them into the robot's current reasoning, targeting long-horizon manipulation tasks that single-frame models fail.
Sim-to-Real Transfer: Teaching Robots in a Dream Lesson
Sim-to-real transfer is the practice of training a robot's brain entirely in a fast, cheap computer simulation and then deploying it on real hardware, using tricks like domain randomization to survive the gap between the virtual world and the messy physical one.
New world models generate depth and motion, not just video, to train robots News
A cluster of world-model papers led by RynnWorld-4D shows AI generating synchronized color, depth, and motion instead of flat video, so robots can practice manipulation inside a generated world and turn predictions directly into actions.
Mistral's first robot model navigates unseen buildings with a single camera News
Mistral released Robostral Navigate, an 8-billion-parameter model that steers robots through buildings they have never seen using one ordinary RGB camera and a plain-language instruction, beating multi-sensor systems that rely on LiDAR and depth cameras.
'World model' was too vague, so researchers wrote a 58-page definition News
With 'world model' stretched to mean everything from video generators to robot simulators, a 58-page technical report set out to pin down a single scientific definition - as a wave of new papers pushed the field from world-models-as-pretty-video toward world-models-as-working-tools.
What Are Vision-Language-Action Models? Lesson
A vision-language-action (VLA) model is a single neural network that takes in camera images and a plain-language instruction and outputs the actual motor commands to carry it out, letting one model both understand a scene and physically act on it.
Robot AI Models Ace Colors but Flunk 'Is This Alive?' News
A new study shows vision-language-action models lose most of their commonsense world knowledge when fine-tuned to control robots, scoring near coin-flip on questions their source models answered almost perfectly.
South Korea bets over a trillion dollars on chips, data centers, and robots News
The government and its biggest companies committed more than $1 trillion to memory fabs, AI data centers, and a goal of building tens of thousands of humanoid robots a year by 2028.
NVIDIA's new method stops AI dream-worlds from breaking the laws of physics News
PhysisForcing trains video-generating world models to keep objects solid and interactions believable, raising how often a robot's imagined plan actually works.
A robot AI that adapts to a moved camera by wiggling, not retraining News
A new method lets robot policies figure out a changed setup from a few seconds of self-directed fiddling, so they keep working when the camera or robot body changes - with no retraining.
This AI predicts how objects move by tracking shapes, not pixels News
PhysiFormer forecasts physical motion as real 3D meshes in space - and recovers rigidity and momentum without anyone hand-coding the laws of physics.
An AI's hallucinations turned out to be a map with blank spots News
Researchers showed that when a world-model AI imagines impossible futures, it's usually in places it barely saw in training - and that you can predict and fix those blind spots cheaply.
A robot hand learns to open things by reasoning about touch, not video News
New research teaches multi-finger robot hands to manipulate things with moving parts — handles, drawers, hinges — by focusing on contact points, and stays steady even without touch sensors.
Robots may not need to picture the future as video to act on it News
Generating a full imagined video of what comes next is expensive. A new method skips it — pulling a robot's next move straight from the inner workings of an image-editing model.
What are world models? Lesson
A world model is an AI system's internal understanding of how an environment works — not just what it sees right now, but what will happen after an action, and what would have happened differently. Central to planning, robotics, and the next generation of physical AI.
Turn the camera away, and the AI's world freezes News
A new benchmark tests whether video AI systems can track what happens to parts of a scene the camera isn't currently showing. Across 23 models, the answer is mostly no — and making the models larger made the problem worse, not better.
Turn around, and the world disappears News
AI video models that are supposed to "understand" a 3D scene only remember what's on screen — pan away and back, and things have reset. Bigger models are worse at it.
Do robots even need to imagine the movie? News
The common belief is that a robot needs to imagine a video of what happens next to plan. A new method says no — imagine a single still frame, and don't even fully draw it.
A robot that runs its own experiments — and sometimes fails when it matters News
NVIDIA researchers gave AI coding agents full control of a physical robot lab — including automated reset and vision-based success checking. One agent inserted a graphics card into a motherboard. The headline success rate is real but requires a close read.
A coding assistant ran a real robot News
An AI coding agent read the research, wrote the control code, watched it fail, and fixed it — seating a graphics card into a motherboard by itself. The honest catch: most of the success is retrying.
WorldDiT Tool
Four released checkpoints plus self-contained inference and evaluation code for a sub-billion-parameter diffusion transformer that emits continuous robot action chunks while predicting future camera-frame pixels as auxiliary training signal. The visual prediction head is dropped at deployment. Tested across four LIBERO simulation suites; the model card notes its cross-paper comparison mixes published protocols.
RxBrain (Hy-Embodied-RxBrain-1.0) Tool
Tencent's ~6.2B embodied model that interleaves text reasoning with generated goal images to plan robot tasks. Weights and inference code released under Apache-2.0.
Robostral Navigate Tool
Mistral's 8B embodied model that steers wheeled, legged, or flying robots through unseen environments from a single RGB camera and a plain-language instruction.
HiFi-UMI-2K Tool
Released dataset behind this week's handheld-only robot training result: high-fidelity two-handed human demonstrations captured with a head-mounted stereo rig and tracked grippers, with every trajectory reconstructed and rejected unless a target robot could physically replay it. Covers wiping, shirt folding, remote insertion and produce sorting. Directly usable for imitation-learning experiments without owning a teleoperation setup.
Gemini Robotics ER 2 Tool
The embodied-reasoning half of Google DeepMind's new robotics family, and the only part available now - it reasons about physical scenes and plans robot tasks via the Gemini API and AI Studio, while the models that actually drive motors stay in private preview.
Cosmos3-Edge Tool
NVIDIA's compact 4-billion-parameter physical-AI model generates text autoregressively while producing image, video, audio and action-trajectory outputs through a diffusion tower, sized for local robotics, autonomous-vehicle and smart-infrastructure workloads. NVIDIA warns it is not physically accurate simulation or safety-certified reasoning.