Sensitive content

This media may contain sensitive content.

Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

The slow walk, the serious face, and those two huge, barely-contained breasts bouncing with every step. Yeah. She’s doing this on purpose. #diva #Pushpa #Srivalli #kasthurishankar #indian #PranithaSubash #kayadulohar #PriyankaMohan #keerthisuresh #Nikithavimal #RukminiVasanth

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Trained on zero real-world data. Learned to walk, pick up boxes, and follow multi-step instructions... in the REAL world. ( 📌 Paper below) Researchers from Amazon FAR, Berkeley, Stanford, and CMU scanned real rooms with an iPhone, rebuilt them as 3D Gaussian Splatting scenes, then generated 48,000 synthetic trajectories of a Unitree G1 walking, grasping, and placing objects inside those virtual replicas. They rendered the robot's first-person camera view from each run and paired it with the matching language instruction and motion data. That's the dataset every humanoid team needs and nobody has: synced egocentric video + language + kinematics, at scale. Instead of collecting it in the real world, they manufactured it. They trained a vision-language-kinematics policy on that synthetic data alone, then deployed it on the physical G1 across five task types: navigation to a named object, lifting boxes of three different sizes with no per-size tuning, chained multi-step tasks, robustness to mid-task layout changes and flickering lights, and multi-minute long-horizon runs. No real-world fine-tuning at any point. Real-world interaction data has been the hard limit on humanoid learning... slow, expensive, and small. If scanning a room once and synthesizing thousands of labeled interactions holds up as a general recipe, that limit moves. Data stops being the bottleneck robotics teams have to solve for. 📌 Paper: Project: ——- Weekly robotics and AI insights. Subscribe free:

Ilir Aliu

12,950 Aufrufe • vor 2 Monaten

Walking in the rain is one of the purest freedoms that we forget among the concrete walls of modern life. When you get bored of the noise of the city, the blue light of the screens and the tiredness of the hustle and bustle, this cool invitation that the sky presents to you will revitalize your soul. The first moment you step outside, drops fall on your face. You first feel a slight surprise, then a deep sense of relief. Rain is the cleanest sink in the world; Every drop eases the burden on your shoulders and wipes the dust from your heart. Getting wet is no longer scary. On the contrary, integrating with water and being a part of nature gives you incredible power. The wet sound of your shoes rings in your ears like a rhythmic melody. The puddles sparkling in the light of the street lamps are like stars on the ground. With each step, you surrender to the flow of life. Walking in the rain is also a meditation. You put your phone in your pocket and take off your headphones. Only the sound of the drops and your own footsteps remain. Your thoughts slow down and your mind becomes clear. Many great ideas, poems and decisions were born precisely on such wet walks. The next time you're watching the rain from the window and a voice inside you says, "Get out," don't stop. Open the door, take a deep breath and smile at the first drop. Don't be afraid of getting wet. The rain is waiting for you; To make you stronger, lighter, more alive. Because walking in the rain is the wettest and most beautiful way to say "yes" to life. #nature #rain

NatureUnleashed

15,132 Aufrufe • vor 4 Monaten

A wrist force sensor fires at 100Hz. The policy only ever sees it at 30Hz, downsampled to land on the same control step as the camera and the joint state. That's not a bug, it's the whole point, and it sits inside a bigger pattern in VLA research this year. Every major release has been Markovian at its core, mapping the current frame straight to the next action. The fix everyone reaches for is more vision: more history frames, longer image context. FM-VLA makes a clean case that the fix is the wrong channel for a whole class of tasks. Press a button three times and stop. A camera watching that has almost nothing to work with, the scene barely changes between press one and press three. Force doesn't have that ambiguity problem. Each press is a sharp, distinct spike in the wrench signal, whether or not the camera noticed anything at all. So FM-VLA doesn't add more frames. It compresses the wrench history into eight tokens with a VAE, pretrained purely on reconstructing force signals, frozen before it ever touches the policy, then hands those tokens to the action expert alongside a short window of joint state. That's the entire memory system. Averaged across three contact-rich tasks, FM-VLA hits 83.3 percent success against 33.3 percent for the strongest vision-memory baseline on the button-counting task specifically, where the ambiguity problem is worst, 72.2 percent for FM-VLA there. Strip out the short-state window and force-only performance drops well below the combined system, so force alone isn't the answer either. The two channels are doing different jobs. The field has defaulted to one memory channel for every kind of temporal problem. This is a clean data point that the channel should match the ambiguity you're actually trying to resolve, not just get bigger. Source: Paper: Credit to the teams at Tsinghua University, Microsoft Research, and Fudan University. #Robotics #PhysicalAI #RobotLearning

Stephen James

11,658 Aufrufe • vor 1 Monat