Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

"Visual intensification: Focus," the latest Exosphere piece from XO/Art Contributor Felipe Pantone, explores perception at the scale of total visual immersion, where acceleration, excess, and continuous motion reshape how we see. Music by @selecta33 (IG) Motion design: @rozmerel (IG)

Sphere

232,326 subscribers

11,516 views • 7 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

$Mesmerized by the melt 🤩🌈 Jen Stark is a multidisciplinary visual artist whose work draws inspiration from sacred geometry, fractals, and organic growth patterns. Her XO/Art piece, 'Cosmic Cascade', is now live on the Exosphere! 🤝: David Lewandowski (Animation), eric epstein (Animation), jgvex (Sound Design), Joshua Liner (Creative Consultant)$

Mesmerized by the melt 🤩🌈 Jen Stark is a multidisciplinary visual artist whose work draws inspiration from sacred geometry, fractals, and organic growth patterns. Her XO/Art piece, 'Cosmic Cascade', is now live on the Exosphere! 🤝: David Lewandowski (Animation), eric epstein (Animation), jgvex (Sound Design), Joshua Liner (Creative Consultant)

Sphere

134,539 views • 1 year ago

Art in Motion. Here’s our recap of XPENG UK at the London Art Fair! As the official automotive partner, we brought technology and creativity together — from our design team’s deep-dive talk to live portraits by Mr Lee Lives. Tap the video to see how we’re driving culture forward. $XPEV

Art in Motion. Here’s our recap of XPENG UK at the London Art Fair! As the official automotive partner, we brought technology and creativity together — from our design team’s deep-dive talk to live portraits by Mr Lee Lives. Tap the video to see how we’re driving culture forward. $XPEV

XPENG

834,789 views • 8 months ago

$Example-based Motion Synthesis via Generative Motion Matching paper page: present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which typically require long offline training time, are prone to visual artifacts, and tend to fail on large and complex skeletons, GenMM inherits the training-free nature and the superior quality of the well-known Motion Matching method. GenMM can synthesize a high-quality motion within a fraction of a second, even with highly complex and large skeletal structures. At the heart of our generative framework lies the generative motion matching module, which utilizes the bidirectional visual similarity as a generative cost function to motion matching, and operates in a multi-stage framework to progressively refine a random guess using exemplar motion matches. In addition to diverse motion generation, we show the versatility of our generative framework by extending it to a number of scenarios that are not possible with motion matching alone, including motion completion, key frame-guided generation, infinite looping, and motion reassembly.$

Example-based Motion Synthesis via Generative Motion Matching paper page: present GenMM, a generative model that "mines" as many diverse motions as possible from a single or few example sequences. In stark contrast to existing data-driven methods, which typically require long offline training time, are prone to visual artifacts, and tend to fail on large and complex skeletons, GenMM inherits the training-free nature and the superior quality of the well-known Motion Matching method. GenMM can synthesize a high-quality motion within a fraction of a second, even with highly complex and large skeletal structures. At the heart of our generative framework lies the generative motion matching module, which utilizes the bidirectional visual similarity as a generative cost function to motion matching, and operates in a multi-stage framework to progressively refine a random guess using exemplar motion matches. In addition to diverse motion generation, we show the versatility of our generative framework by extending it to a number of scenarios that are not possible with motion matching alone, including motion completion, key frame-guided generation, infinite looping, and motion reassembly.

AK

93,765 views • 3 years ago

The next chapter of Indian cinema starts now. A&M MoCap Lab — India’s largest Motion and Performance Capture stage, built for scale & precision launched at Annapurna Studios in Hyderabad, in collaboration with Mihira Visual Labs and technical partner Animatrik Inaugurated by rajamouli ss, this advanced motion capture stage enables filmmakers and game developers from previsualization to final animation of content with speed, precision and within budgets! #IndianCinema #MotionCapture #AnnapurnaStudios #Hyderabad Nagarjuna Akkineni Shobu Yarlagadda #BrettIneson Mihira Visual Labs Animatrik #VenkatAkkineni sushila chaitanya akkineni #AdityaAkkineni #SupriyaYarlagadda C V Rao Prasad Nimmakayala #ChiranjeeviGeetadhar #SushmaKanneganti

The next chapter of Indian cinema starts now. A&M MoCap Lab — India’s largest Motion and Performance Capture stage, built for scale & precision launched at Annapurna Studios in Hyderabad, in collaboration with Mihira Visual Labs and technical partner Animatrik Inaugurated by rajamouli ss, this advanced motion capture stage enables filmmakers and game developers from previsualization to final animation of content with speed, precision and within budgets! #IndianCinema #MotionCapture #AnnapurnaStudios #Hyderabad Nagarjuna Akkineni Shobu Yarlagadda #BrettIneson Mihira Visual Labs Animatrik #VenkatAkkineni sushila chaitanya akkineni #AdityaAkkineni #SupriyaYarlagadda C V Rao Prasad Nimmakayala #ChiranjeeviGeetadhar #SushmaKanneganti

Annapurna Studios

71,557 views • 7 months ago

She Means Business 2.25 | Saima Hussain Mir In the twenty-fifth episode of Season 2 of #SheMeansBusiness, presented by #KashmirLife in collaboration with Khyber Cements, host #UmaimaReshi speaks with Saima Hussain Mir, Creative and Art Director, Multidisciplinary Designer, and Founder of her independent design practice. In this inspiring conversation, Saima shares her remarkable journey from being a medical student who chose to follow her passion for design despite societal expectations and criticism. She reflects on building a career in communication design, motion graphics, branding, user experience, and creative direction, while drawing inspiration from Kashmir's rich culture to create meaningful visual stories.

She Means Business 2.25 | Saima Hussain Mir In the twenty-fifth episode of Season 2 of #SheMeansBusiness, presented by #KashmirLife in collaboration with Khyber Cements, host #UmaimaReshi speaks with Saima Hussain Mir, Creative and Art Director, Multidisciplinary Designer, and Founder of her independent design practice. In this inspiring conversation, Saima shares her remarkable journey from being a medical student who chose to follow her passion for design despite societal expectations and criticism. She reflects on building a career in communication design, motion graphics, branding, user experience, and creative direction, while drawing inspiration from Kashmir's rich culture to create meaningful visual stories.

Kashmir Life

60,686 views • 2 months ago

HKUST(GZ) and HKUST present "SURREALITY", the world's 1st large-scale cross-campus MR×Al art exhibition, for HKUST's 35th-anniversary celebrations. Featuring nearly 50 works by 70+ digital artists from 23 countries and regions, SURREALITY brings together renowned international artists. The signature piece, "The Gate", connects the 2 campuses through a virtual metaverse, embodying the "Unified HKUST, Complementary Campuses" framework. The exhibition explores the convergence of art, technology and human perception, demonstrating the strengths of HKUST and HKUST(GZ) in interdisciplinary studies and computational creativity. On view at HKUST(GZ) Activity Center C2-102 from July 1 to 31, with further exhibition plans to be announced.

HKUST(GZ) and HKUST present "SURREALITY", the world's 1st large-scale cross-campus MR×Al art exhibition, for HKUST's 35th-anniversary celebrations. Featuring nearly 50 works by 70+ digital artists from 23 countries and regions, SURREALITY brings together renowned international artists. The signature piece, "The Gate", connects the 2 campuses through a virtual metaverse, embodying the "Unified HKUST, Complementary Campuses" framework. The exhibition explores the convergence of art, technology and human perception, demonstrating the strengths of HKUST and HKUST(GZ) in interdisciplinary studies and computational creativity. On view at HKUST(GZ) Activity Center C2-102 from July 1 to 31, with further exhibition plans to be announced.

HKUST Guangzhou

42,701 views • 3 months ago

From the first brushstroke to the final masterpiece 🎨 At our #Freedom250 celebration in Abuja, visual artist Gabriel Gbenga (@captain_gahbrivah) brought the spirit of 250 years of American freedom, innovation, creativity, and cultural expression to life through a live painting experience. Inspired by the power of storytelling through art, a force that has long shaped culture, sparked new ideas, and expanded how we see the world, Gabriel transformed a blank canvas into a vibrant visual tribute to the values and U.S.-Nigeria connections celebrated throughout the evening. Watch the journey from beginning to end as creativity unfolds in real time, capturing the spirit of #Freedom250 and the longstanding friendship between the United States and Nigeria.

From the first brushstroke to the final masterpiece 🎨 At our #Freedom250 celebration in Abuja, visual artist Gabriel Gbenga (@captain_gahbrivah) brought the spirit of 250 years of American freedom, innovation, creativity, and cultural expression to life through a live painting experience. Inspired by the power of storytelling through art, a force that has long shaped culture, sparked new ideas, and expanded how we see the world, Gabriel transformed a blank canvas into a vibrant visual tribute to the values and U.S.-Nigeria connections celebrated throughout the evening. Watch the journey from beginning to end as creativity unfolds in real time, capturing the spirit of #Freedom250 and the longstanding friendship between the United States and Nigeria.

U.S. Mission Nigeria

10,779 views • 2 months ago

Seamless Human Motion Composition with Blended Positional Encodings Conditional human motion generation is an important topic with many applications in virtual reality, gaming, and robotics. While prior works have focused on generating motion guided by text, music, or scenes, these typically result in isolated motions confined to short durations. Instead, we address the generation of long, continuous sequences guided by a series of varying textual descriptions. In this context, we introduce FlowMDM, the first diffusion-based model that generates seamless Human Motion Compositions (HMC) without any postprocessing or redundant denoising steps. For this, we introduce the Blended Positional Encodings, a technique that leverages both absolute and relative positional encodings in the denoising chain. More specifically, global motion coherence is recovered at the absolute stage, whereas smooth and realistic transitions are built at the relative stage. As a result, we achieve state-of-the-art results in terms of accuracy, realism, and smoothness on the Babel and HumanML3D datasets. FlowMDM excels when trained with only a single description per motion sequence thanks to its Pose-Centric Cross-ATtention, which makes it robust against varying text descriptions at inference time. Finally, to address the limitations of existing HMC metrics, we propose two new metrics: the Peak Jerk and the Area Under the Jerk, to detect abrupt transitions.

Seamless Human Motion Composition with Blended Positional Encodings Conditional human motion generation is an important topic with many applications in virtual reality, gaming, and robotics. While prior works have focused on generating motion guided by text, music, or scenes, these typically result in isolated motions confined to short durations. Instead, we address the generation of long, continuous sequences guided by a series of varying textual descriptions. In this context, we introduce FlowMDM, the first diffusion-based model that generates seamless Human Motion Compositions (HMC) without any postprocessing or redundant denoising steps. For this, we introduce the Blended Positional Encodings, a technique that leverages both absolute and relative positional encodings in the denoising chain. More specifically, global motion coherence is recovered at the absolute stage, whereas smooth and realistic transitions are built at the relative stage. As a result, we achieve state-of-the-art results in terms of accuracy, realism, and smoothness on the Babel and HumanML3D datasets. FlowMDM excels when trained with only a single description per motion sequence thanks to its Pose-Centric Cross-ATtention, which makes it robust against varying text descriptions at inference time. Finally, to address the limitations of existing HMC metrics, we propose two new metrics: the Peak Jerk and the Area Under the Jerk, to detect abrupt transitions.

AK

30,887 views • 2 years ago

Your brain doesn't simply record reality - it interprets it. In this video, the Ferris wheel (the large rotating wheel seen at amusement parks) can appear to spin in two different directions even though the image never changes. This happens because the brain is a prediction machine. Your visual cortex receives the same visual information, but the prefrontal cortex helps decide how to interpret the motion. If you focus on one cabin and imagine it moving the opposite way, your brain can flip the direction of the wheel. Nothing in the video changes - only your brain's prediction does. This is how perception works: the world stays the same, but the brain's internal model can completely change what you experience. capiomind

Your brain doesn't simply record reality - it interprets it. In this video, the Ferris wheel (the large rotating wheel seen at amusement parks) can appear to spin in two different directions even though the image never changes. This happens because the brain is a prediction machine. Your visual cortex receives the same visual information, but the prefrontal cortex helps decide how to interpret the motion. If you focus on one cabin and imagine it moving the opposite way, your brain can flip the direction of the wheel. Nothing in the video changes - only your brain's prediction does. This is how perception works: the world stays the same, but the brain's internal model can completely change what you experience. capiomind

𝚃𝙷𝙴 𝚆𝙷𝙸𝚃𝙴 𝚁𝙰𝙱𝙱𝙸𝚃

21,334 views • 6 months ago

Kling AI Cannes Showcase — Technical Discussion on Born of the Tide AI-driven animation across the full industrial creative workflow. Set against the historical and cultural backdrop of the Tanka people, Born of the Tide explores a new way of bringing local stories to the screen through AI-powered animation. From art direction and environment design to character movement and cinematic shot planning, Kling AI helps streamline the animation process, making high-quality, epic-scale visual storytelling more accessible, efficient, and scalable. By lowering production barriers and reducing reliance on large teams and long production cycles, the project points to a more agile and creatively open future for original animation.

Kling AI Cannes Showcase — Technical Discussion on Born of the Tide AI-driven animation across the full industrial creative workflow. Set against the historical and cultural backdrop of the Tanka people, Born of the Tide explores a new way of bringing local stories to the screen through AI-powered animation. From art direction and environment design to character movement and cinematic shot planning, Kling AI helps streamline the animation process, making high-quality, epic-scale visual storytelling more accessible, efficient, and scalable. By lowering production barriers and reducing reliance on large teams and long production cycles, the project points to a more agile and creatively open future for original animation.

Kling AI

364,604 views • 4 months ago

Today, we're sharing new research on GWM Worlds 2. Our latest General World Model that generates interactive real-time simulations in continuous 720p video at 24 fps with 48000 Hz audio. Built on top of our foundational audio-visual generation model, GWM Worlds 2 allows you to define the environment, subjects, visual style, physical rules and ambience of any world. Once inside, you steer it with text actions addressed to any subject or to the scene itself, alongside continuous camera motion. The world continues from each new input instead of following a fixed clip or script so sessions have no preset length. GWM Worlds 2 creates a new foundation for interactive entertainment, virtual characters, robotics and embodied-agent simulation. Learn more about GWM Worlds 2 at the link below.

Today, we're sharing new research on GWM Worlds 2. Our latest General World Model that generates interactive real-time simulations in continuous 720p video at 24 fps with 48000 Hz audio. Built on top of our foundational audio-visual generation model, GWM Worlds 2 allows you to define the environment, subjects, visual style, physical rules and ambience of any world. Once inside, you steer it with text actions addressed to any subject or to the scene itself, alongside continuous camera motion. The world continues from each new input instead of following a fixed clip or script so sessions have no preset length. GWM Worlds 2 creates a new foundation for interactive entertainment, virtual characters, robotics and embodied-agent simulation. Learn more about GWM Worlds 2 at the link below.

Runway

306,144 views • 1 month ago

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Zhiyang (Frank) Dou

14,704 views • 1 year ago

Happy New Year from The Met! 🪩 Start 2025 with a closer look at Awol Erizku's dazzling "Nefertiti–Miles Davis," a mirrored tile bust of the Egyptian queen inspired by Miles Davis’s 1968 album Nefertiti. Suspended from the ceiling and rotating like a disco ball, this work explores the intersection of music and visual art, highlighting diasporic connections to ancient Egypt. Erizku frequently features Nefertiti in his work, blending references from culture coded as "urban" and the art-historical canon to examine themes of race, identity, and history. 🎨 Awol Erizku (Ethiopian American, 1988). Nefertiti–Miles Davis, 2017. Hand-coated foam and mirrored tile.

Happy New Year from The Met! 🪩 Start 2025 with a closer look at Awol Erizku's dazzling "Nefertiti–Miles Davis," a mirrored tile bust of the Egyptian queen inspired by Miles Davis’s 1968 album Nefertiti. Suspended from the ceiling and rotating like a disco ball, this work explores the intersection of music and visual art, highlighting diasporic connections to ancient Egypt. Erizku frequently features Nefertiti in his work, blending references from culture coded as "urban" and the art-historical canon to examine themes of race, identity, and history. 🎨 Awol Erizku (Ethiopian American, 1988). Nefertiti–Miles Davis, 2017. Hand-coated foam and mirrored tile.

The Metropolitan Museum of Art

38,544 views • 1 year ago

How Experiencing awe affects the brain and body: "When your visual aperture is small, your perception of time is different. You're fine slicing." "If I'm in line at the store and I have some place to be, my visual aperture shrinks and it feels like the person in front of me is taking forever." "When we see a horizon and our aperture opens up, we relax, but we also are taking fewer time bit snapshots." "It's not about having a small aperture or a big aperture per se, it's the process of going from one aperture to the next." "With awe we have a sense of self, and then we connect to vast things out there. It changes the neurophysiology of the mind." Dr. Dacher Keltner on Andrew D. Huberman, Ph.D.

How Experiencing awe affects the brain and body: "When your visual aperture is small, your perception of time is different. You're fine slicing." "If I'm in line at the store and I have some place to be, my visual aperture shrinks and it feels like the person in front of me is taking forever." "When we see a horizon and our aperture opens up, we relax, but we also are taking fewer time bit snapshots." "It's not about having a small aperture or a big aperture per se, it's the process of going from one aperture to the next." "With awe we have a sense of self, and then we connect to vast things out there. It changes the neurophysiology of the mind." Dr. Dacher Keltner on Andrew D. Huberman, Ph.D.

Huberman Lab Clips

33,467 views • 2 months ago

In Second Fiddle (1939), Sonja Henie—three-time Olympic gold medalist—turns figure skating into pure cinematic art. What makes this scene special isn’t just the romance with Tyrone Power, but the way the ice performance is filmed: real Olympic-level skating, no doubles, no tricks of modern CGI—just precision, speed, and control captured in long, elegant camera movements. The rink becomes a stage, and every spin and glide is choreographed like ballet for the lens. 1930s Hollywood transforms sport into visual poetry—where skating isn’t shown as competition, but as fluid motion, music, and emotion merged into one continuous flow. ❄️🎬

In Second Fiddle (1939), Sonja Henie—three-time Olympic gold medalist—turns figure skating into pure cinematic art. What makes this scene special isn’t just the romance with Tyrone Power, but the way the ice performance is filmed: real Olympic-level skating, no doubles, no tricks of modern CGI—just precision, speed, and control captured in long, elegant camera movements. The rink becomes a stage, and every spin and glide is choreographed like ballet for the lens. 1930s Hollywood transforms sport into visual poetry—where skating isn’t shown as competition, but as fluid motion, music, and emotion merged into one continuous flow. ❄️🎬

𝗖𝗹𝗮𝘀𝘀𝗶𝗰𝗮𝗹 𝗠𝗲𝗹𝗼𝗱𝗶𝗲𝘀

37,315 views • 6 months ago

Agile Continuous Jumping in Discontinuous Terrains discuss: We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping requires accurately executing highly dynamic motions over long horizons, which is challenging for existing approaches. To accomplish this task, we design a hierarchical learning and control framework, which consists of a learned heightmap predictor for robust terrain perception, a reinforcement-learning-based centroidal-level motion policy for versatile and terrain-adaptive planning, and a low-level model-based leg controller for accurate motion tracking. In addition, we minimize the sim-to-real gap by accurately modeling the hardware characteristics. Our framework enables a Unitree Go1 robot to perform agile and continuous jumps on human-sized stairs and sparse stepping stones, for the first time to the best of our knowledge. In particular, the robot can cross two stair steps in each jump and completes a 3.5m long, 2.8m high, 14-step staircase in 4.5 seconds. Moreover, the same policy outperforms baselines in various other parkour tasks, such as jumping over single horizontal or vertical discontinuities.

Agile Continuous Jumping in Discontinuous Terrains discuss: We focus on agile, continuous, and terrain-adaptive jumping of quadrupedal robots in discontinuous terrains such as stairs and stepping stones. Unlike single-step jumping, continuous jumping requires accurately executing highly dynamic motions over long horizons, which is challenging for existing approaches. To accomplish this task, we design a hierarchical learning and control framework, which consists of a learned heightmap predictor for robust terrain perception, a reinforcement-learning-based centroidal-level motion policy for versatile and terrain-adaptive planning, and a low-level model-based leg controller for accurate motion tracking. In addition, we minimize the sim-to-real gap by accurately modeling the hardware characteristics. Our framework enables a Unitree Go1 robot to perform agile and continuous jumps on human-sized stairs and sparse stepping stones, for the first time to the best of our knowledge. In particular, the robot can cross two stair steps in each jump and completes a 3.5m long, 2.8m high, 14-step staircase in 4.5 seconds. Moreover, the same policy outperforms baselines in various other parkour tasks, such as jumping over single horizontal or vertical discontinuities.

AK

35,820 views • 2 years ago

At the 4th edition of #UMAGINETN2026, we turn the spotlight on a domain where Tamil Nadu has long led—the creative industries. This year’s programme brings together industry veterans and the next generation of creative leaders across Cinema & Storytelling, Music & Digital Creativity, Visual Effects & Animation, Gaming & Interactive Media, and Language Technology, examining how innovation is reshaping art, culture, and creative expression. Together, these conversations highlight Tamil Nadu’s expanding role in the global creative-tech ecosystem. Join us on January 8–9 at the Chennai Trade Centre as we come together to imagine, create, and build the future at Umagine TN.

At the 4th edition of #UMAGINETN2026, we turn the spotlight on a domain where Tamil Nadu has long led—the creative industries. This year’s programme brings together industry veterans and the next generation of creative leaders across Cinema & Storytelling, Music & Digital Creativity, Visual Effects & Animation, Gaming & Interactive Media, and Language Technology, examining how innovation is reshaping art, culture, and creative expression. Together, these conversations highlight Tamil Nadu’s expanding role in the global creative-tech ecosystem. Join us on January 8–9 at the Chennai Trade Centre as we come together to imagine, create, and build the future at Umagine TN.

Dr P Thiaga Rajan (PTR)

23,932 views • 9 months ago

I believe that the interfaces of the future will disappear. Instead of buttons and menus, we will interact with objects. The process itself becomes the feedback. Building software is always a complex craft, but spatial computing is a different beast entirely. It demands a fusion of visual art, logic, and spatial UI where every interaction happens in the air around you. With OPERATOR, built for Apple Vision Pro, we explored this by turning music into a sculpture. The music track isn't a timeline anymore; it’s a 3D object you can walk around, touch, and modify from any angle.

I believe that the interfaces of the future will disappear. Instead of buttons and menus, we will interact with objects. The process itself becomes the feedback. Building software is always a complex craft, but spatial computing is a different beast entirely. It demands a fusion of visual art, logic, and spatial UI where every interaction happens in the air around you. With OPERATOR, built for Apple Vision Pro, we explored this by turning music into a sculpture. The music track isn't a timeline anymore; it’s a 3D object you can walk around, touch, and modify from any angle.

maxim zhestkov

102,915 views • 8 months ago

We have plenty of human demonstration data for movement. We don’t have enough for touch. Without tactile feedback, foundation models can’t feel if an object is slipping, soft, or fragile during complex manipulation. Matrix Inno is bringing three data-collection gloves to IROS 2026: the RigidCore Tactile+EMF, the Fabric Tactile + EMF, and the Fabric Tactile + UltraLite Motion Glove. The hardware tracks pressure and hand pose simultaneously during human demos, mapping exactly where contact happens and how it shifts in real time. Wearables like this are how we finally get real, continuous contact data at scale. Source: Matrix Inno MX MATRIX

We have plenty of human demonstration data for movement. We don’t have enough for touch. Without tactile feedback, foundation models can’t feel if an object is slipping, soft, or fragile during complex manipulation. Matrix Inno is bringing three data-collection gloves to IROS 2026: the RigidCore Tactile+EMF, the Fabric Tactile + EMF, and the Fabric Tactile + UltraLite Motion Glove. The hardware tracks pressure and hand pose simultaneously during human demos, mapping exactly where contact happens and how it shifts in real time. Wearables like this are how we finally get real, continuous contact data at scale. Source: Matrix Inno MX MATRIX

RoboHub🤖

12,372 views • 18 days ago

Choreography Checkpoints: When Dance Becomes Living Art 👯‍♀️✨ These are the choreography checkpoints — the exact moments where dance transforms into pure art. Every sharp pose, every frozen frame, every synchronized breath… it’s not just movement. It’s a painting come to life. A sculpture in motion. A masterpiece made of muscle, timing, and soul. From powerful group formations to stunning solo freezes, watch how these dancers don’t just perform — they create. Art has officially become… 👯‍♀️ Who else gets chills when choreography hits these perfect visual peaks? Drop your favorite dance-art moment below! 🔥

Choreography Checkpoints: When Dance Becomes Living Art 👯‍♀️✨ These are the choreography checkpoints — the exact moments where dance transforms into pure art. Every sharp pose, every frozen frame, every synchronized breath… it’s not just movement. It’s a painting come to life. A sculpture in motion. A masterpiece made of muscle, timing, and soul. From powerful group formations to stunning solo freezes, watch how these dancers don’t just perform — they create. Art has officially become… 👯‍♀️ Who else gets chills when choreography hits these perfect visual peaks? Drop your favorite dance-art moment below! 🔥

NancyH

111,069 views • 5 months ago