Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

GEN-1 still works with lights off, and generalizes under harsh lighting conditions. The model uses raw video pixels to make decisions, so strong lighting changes can drastically alter its input distribution. Yet performance still holds. Why? GEN-1 was pre-trained on a massive, diverse dataset of different lighting conditions—everywhere from... show more

Generalist

10,504 subscribers

18,396 Aufrufe • vor 4 Monaten •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

We've improved how GEN-1 learns to adapt to new actuators and new robots at the lowest level, with up to 10-20x gains on internal benchmarks. This significantly boosts performance on high-precision tasks like disassembling parts from a NIST board. Read more about GEN-1 in our blog posts in the comments below.

We've improved how GEN-1 learns to adapt to new actuators and new robots at the lowest level, with up to 10-20x gains on internal benchmarks. This significantly boosts performance on high-precision tasks like disassembling parts from a NIST board. Read more about GEN-1 in our blog posts in the comments below.

Generalist

75,699 Aufrufe • vor 12 Tagen

GEN-1 plays the 🐚 shell game, trained on just 1 hr of robot data. It also generalizes to unseen objects, like berkay 's car keys. Physical AI models should be capable of benchmark tasks like this one. It's interesting for the all the reasons Rhoda AI calls out -- requires visual memory, and the model must track the cups from the very start, at high frame rates. Interestingly, GEN-1 appears to exhibit a degree of "active perception." It's subtle; the hands can sometimes appear to "follow" the cups, using its own movements to help attend to where it thinks the object should be. Read more about GEN-1 in our blog post in the comments below ↓

GEN-1 plays the 🐚 shell game, trained on just 1 hr of robot data. It also generalizes to unseen objects, like berkay 's car keys. Physical AI models should be capable of benchmark tasks like this one. It's interesting for the all the reasons Rhoda AI calls out -- requires visual memory, and the model must track the cups from the very start, at high frame rates. Interestingly, GEN-1 appears to exhibit a degree of "active perception." It's subtle; the hands can sometimes appear to "follow" the cups, using its own movements to help attend to where it thinks the object should be. Read more about GEN-1 in our blog post in the comments below ↓

Generalist

860,208 Aufrufe • vor 3 Monaten

MaterialFusion Enhancing Inverse Rendering with Material Diffusion Priors discuss: Recent works in inverse rendering have shown promise in using multi-view images of an object to recover shape, albedo, and materials. However, the recovered components often fail to render accurately under new lighting conditions due to the intrinsic challenge of disentangling albedo and material properties from input images. To address this challenge, we introduce MaterialFusion, an enhanced conventional 3D inverse rendering pipeline that incorporates a 2D prior on texture and material properties. We present StableMaterial, a 2D diffusion model prior that refines multi-lit data to estimate the most likely albedo and material from given input appearances. This model is trained on albedo, material, and relit image data derived from a curated dataset of approximately ~12K artist-designed synthetic Blender objects called BlenderVault. we incorporate this diffusion prior with an inverse rendering framework where we use score distillation sampling (SDS) to guide the optimization of the albedo and materials, improving relighting performance in comparison with previous work. We validate MaterialFusion's relighting performance on 4 datasets of synthetic and real objects under diverse illumination conditions, showing our diffusion-aided approach significantly improves the appearance of reconstructed objects under novel lighting conditions. We intend to publicly release our BlenderVault dataset to support further research in this field.

MaterialFusion Enhancing Inverse Rendering with Material Diffusion Priors discuss: Recent works in inverse rendering have shown promise in using multi-view images of an object to recover shape, albedo, and materials. However, the recovered components often fail to render accurately under new lighting conditions due to the intrinsic challenge of disentangling albedo and material properties from input images. To address this challenge, we introduce MaterialFusion, an enhanced conventional 3D inverse rendering pipeline that incorporates a 2D prior on texture and material properties. We present StableMaterial, a 2D diffusion model prior that refines multi-lit data to estimate the most likely albedo and material from given input appearances. This model is trained on albedo, material, and relit image data derived from a curated dataset of approximately ~12K artist-designed synthetic Blender objects called BlenderVault. we incorporate this diffusion prior with an inverse rendering framework where we use score distillation sampling (SDS) to guide the optimization of the albedo and materials, improving relighting performance in comparison with previous work. We validate MaterialFusion's relighting performance on 4 datasets of synthetic and real objects under diverse illumination conditions, showing our diffusion-aided approach significantly improves the appearance of reconstructed objects under novel lighting conditions. We intend to publicly release our BlenderVault dataset to support further research in this field.

AK

22,959 Aufrufe • vor 1 Jahr

Castlevania: Legacy Of Darkness (1999) Recompiled for PC! This is a WIP recompilation project that improves on many of the criticisms of the original release, improving on its visuals (Resolution and lighting) and performance issues along with bugfixes and quality of life changes! You can check out video coverage below! Download link to the project is included here>>>

Castlevania: Legacy Of Darkness (1999) Recompiled for PC! This is a WIP recompilation project that improves on many of the criticisms of the original release, improving on its visuals (Resolution and lighting) and performance issues along with bugfixes and quality of life changes! You can check out video coverage below! Download link to the project is included here>>>

Stormslayer 🔜QUAKECON 2026 -HD Remasters/Gamedev

23,006 Aufrufe • vor 2 Monaten

Everyday for the past 2 weeks, we've been sharing something new from GEN-1, our latest milestone in scaling robot learning. This has never been done before. Going from ideas to skills in days (or faster) is what physical AI models should deliver. More coming. Stay tuned. Read more about it in our blog post in the comments below ↓

Everyday for the past 2 weeks, we've been sharing something new from GEN-1, our latest milestone in scaling robot learning. This has never been done before. Going from ideas to skills in days (or faster) is what physical AI models should deliver. More coming. Stay tuned. Read more about it in our blog post in the comments below ↓

Generalist

39,593 Aufrufe • vor 3 Monaten

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

Our vision is for AI that uses world models to adapt in new and dynamic environments and efficiently learn new skills. We’re sharing V-JEPA 2, a new world model with state-of-the-art performance in visual understanding and prediction. V-JEPA 2 is a 1.2 billion-parameter model, trained on video, that can enable zero-shot planning in robots—allowing them to plan and execute tasks in unfamiliar environments. Learn more about V-JEPA 2 ➡️ As we continue working toward our goal of achieving advanced machine intelligence (AMI), we’re also releasing three new benchmarks for evaluating how well existing models can reason about the physical world from video. Learn more and download the new benchmarks ➡️

AI at Meta

310,281 Aufrufe • vor 1 Jahr

🧵1/3 I partnered with Kling to make a promo for their new 3.0 model. I came up with the concept, created it and delivered it all on my own in 3 days of early access, I wanted to make something that showed how Kling could be used to tell a diverse range of stories in a diverse range of styles. I've honestly been blown away be how incredible the model is and I haven't even scratched the surface of features like the new 3.0 OMNI model. For me Kling 2.6 was already best in class for most things but 3.0 sees massive improvements to video quality and detail (no need to add grain to mask imperfections) and prompt adherence. Also you can time your generations to be as long as 15 seconds and as short as 3, this is fantastic for pacing your scenes. Read on to find out more about the new Performance and Multi shot features!👇

🧵1/3 I partnered with Kling to make a promo for their new 3.0 model. I came up with the concept, created it and delivered it all on my own in 3 days of early access, I wanted to make something that showed how Kling could be used to tell a diverse range of stories in a diverse range of styles. I've honestly been blown away be how incredible the model is and I haven't even scratched the surface of features like the new 3.0 OMNI model. For me Kling 2.6 was already best in class for most things but 3.0 sees massive improvements to video quality and detail (no need to add grain to mask imperfections) and prompt adherence. Also you can time your generations to be as long as 15 seconds and as short as 3, this is fantastic for pacing your scenes. Read on to find out more about the new Performance and Multi shot features!👇

Uncanny Harry AI

29,194 Aufrufe • vor 6 Monaten

Robotics is almost solved! Pun intended. Sunday published a "Solve" standard. They declared the scope (garment types, lighting, surfaces, starting configurations) and adaptation cost (zero—no fine-tuning per home) before evaluating. The same model weights run everywhere. This might be the differentiation between a good demo and reliable work of robots. They presented ACT-2, a robot foundation model that folds laundry at 99.1% success across unseen homes. Different houses, lighting, bed types, garment sizes. According to them scaling pre-training closes the generalization gap. Train on massive, high-quality human data. When you do that right, what you learn in-house actually transfers to unseen homes. Even wilder is that the model learns new folding techniques from a single example and generalizes them to new environments. Memo goes to homes later this year. Would you adopt this cutie? 🥹 Read more here: Great work Tony Zhao and team! 🧡 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Robotics is almost solved! Pun intended. Sunday published a "Solve" standard. They declared the scope (garment types, lighting, surfaces, starting configurations) and adaptation cost (zero—no fine-tuning per home) before evaluating. The same model weights run everywhere. This might be the differentiation between a good demo and reliable work of robots. They presented ACT-2, a robot foundation model that folds laundry at 99.1% success across unseen homes. Different houses, lighting, bed types, garment sizes. According to them scaling pre-training closes the generalization gap. Train on massive, high-quality human data. When you do that right, what you learn in-house actually transfers to unseen homes. Even wilder is that the model learns new folding techniques from a single example and generalizes them to new environments. Memo goes to homes later this year. Would you adopt this cutie? 🥹 Read more here: Great work Tony Zhao and team! 🧡 ~~ ♻️ Join the weekly robotics newsletter, and never miss any news →

Lukas Ziegler

36,518 Aufrufe • vor 1 Monat

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Small Language Models (SML) are the future of AI. "Small" (SML) instead of "Large" (LLM). These small models are highly specialized models with superhuman abilities on specific tasks. Here are two techniques to build these models: • Spectrum • Model Merging I give you a short introduction in the attached video, but here is a quick summary: Spectrum helps us identify the most relevant layers to solve one specific task. We can ignore everything else and focus on fine-tuning these layers. Using Spectrum, we can fine-tune models in a heartbeat. Model Merging combines multiple models into a unique, much better model than any of the individual input models. You can also combine models specialized in different tasks and get a model with multiple abilities. This is the state of the art of productizing models. It's what Arcee.ai's platform does behind the scenes. Arcee collaborated with me on this post and is sponsoring it. There are three main steps to produce a model for your particular use case: 1. You create a dataset by uploading your data. 2. You train a model. At this step, Arcee uses Spectrum and Model Merging to produce a highly specialized model for your task. 3. You can deploy that model to any environment you want. Three important notes: • Training process is 2x faster and 2x cheaper than regular fine-tuning. • Resultant models are smaller and have higher accuracy. • They create these specialized models from open-source models. Check this site so you can fully appreciate how this works: If you want to fine-tune an open-source model, consider Arcee's platform. This is the state of the art.

Santiago

164,162 Aufrufe • vor 2 Jahren

Most robot demos are scripted. Generalist's GEN-1 is not. > GEN-1 was doing a task > Mid-task, an extra object was thrown into the bin > GEN-1 quickly adapted to the new environment > Still completed the task smoothly This is the difference between a scripted policy (seen in viral launch videos) and a real foundation model. GEN-1 was trained on 500,000 hours of proprietary, real-world dexterous manipulation data. It has NEVER seen that exact scenario before. This was the coolest demo at Automate Show Generalist Flexiv Robotics

Most robot demos are scripted. Generalist's GEN-1 is not. > GEN-1 was doing a task > Mid-task, an extra object was thrown into the bin > GEN-1 quickly adapted to the new environment > Still completed the task smoothly This is the difference between a scripted policy (seen in viral launch videos) and a real foundation model. GEN-1 was trained on 500,000 hours of proprietary, real-world dexterous manipulation data. It has NEVER seen that exact scenario before. This was the coolest demo at Automate Show Generalist Flexiv Robotics

mete

11,514 Aufrufe • vor 1 Monat

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

AI at Meta

2,265,524 Aufrufe • vor 1 Jahr

Asked by Todd Lewis on what is the biggest challenge in putting together the new PGA Tour schedule, Tiger Woods said this: "I think it's trying to serve literally everyone, from the player side of it, from our media partners, from all of our title sponsors, from the local communities or even changing venues and going to bigger markets. It's what do we need to do from a competitive model to make our tour the best product it can possibly be each and every year and still have room for development. How do we do all of that at the same time."

Asked by Todd Lewis on what is the biggest challenge in putting together the new PGA Tour schedule, Tiger Woods said this: "I think it's trying to serve literally everyone, from the player side of it, from our media partners, from all of our title sponsors, from the local communities or even changing venues and going to bigger markets. It's what do we need to do from a competitive model to make our tour the best product it can possibly be each and every year and still have room for development. How do we do all of that at the same time."

Cameron Jourdan

43,474 Aufrufe • vor 6 Monaten

As detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models. Movie Gen Video Bench is the largest and most comprehensive benchmark ever released for evaluating text-to-video generation. It includes a collection of 1,000+ prompts that cover concepts ranging from detailed human activity to animals, physics, unusual subjects and more — with broad coverage across different motion levels. Movie Gen Audio Bench is a first-of-its-kind benchmark aimed at evaluating video-to-audio and (text+video)-to-audio generation. It includes 527 generated videos and associated sound effects and music prompts covering a diverse set of ambient environments and sound effects. To enable fair and easy comparison to our models for future works, these new benchmarks include non cherry-picked generated videos and audio from Movie Gen. In releasing these new benchmarks we hope to promote fair & extensive evaluations in media generation research to enable greater progress in this field.

As detailed in the Meta Movie Gen technical report, today we’re open sourcing Movie Gen Bench: two new media generation benchmarks that we hope will help to enable the AI research community to progress work on more capable audio and video generation models. Movie Gen Video Bench is the largest and most comprehensive benchmark ever released for evaluating text-to-video generation. It includes a collection of 1,000+ prompts that cover concepts ranging from detailed human activity to animals, physics, unusual subjects and more — with broad coverage across different motion levels. Movie Gen Audio Bench is a first-of-its-kind benchmark aimed at evaluating video-to-audio and (text+video)-to-audio generation. It includes 527 generated videos and associated sound effects and music prompts covering a diverse set of ambient environments and sound effects. To enable fair and easy comparison to our models for future works, these new benchmarks include non cherry-picked generated videos and audio from Movie Gen. In releasing these new benchmarks we hope to promote fair & extensive evaluations in media generation research to enable greater progress in this field.

AI at Meta

156,273 Aufrufe • vor 1 Jahr

“Football is to recognise and anticipate on patterns. You see all kinds of patterns when you’re little…and you anticipate on the patterns…” Ruud Gullit 1. He’s seen it over and over (paying attention to the detail in his playing environment) 2. He’s made sense of what he’s seen and remembered it (thought about it to make meaning of it and processed it in both a visual and semantic way) 3. He can then make quicker and more effective decisions in games based upon what he sees in the moment (knowledge-in the game) with relation to what he’s seen and what he’s made sense of in the past (knowledge-of the game) Mastery of anticipation and decision-making… This requires… 1. Coach session design setting problems for players to detect and to solve 2. Coach behaviours that orient players’ attention to the problems to help them think about, work on, solve, and remember in-game problems 3. Player participation - attention, involvement, reflection-in-action, post session reflection-in-action to consolidate memories It’s a coach-player responsibility…

“Football is to recognise and anticipate on patterns. You see all kinds of patterns when you’re little…and you anticipate on the patterns…” Ruud Gullit 1. He’s seen it over and over (paying attention to the detail in his playing environment) 2. He’s made sense of what he’s seen and remembered it (thought about it to make meaning of it and processed it in both a visual and semantic way) 3. He can then make quicker and more effective decisions in games based upon what he sees in the moment (knowledge-in the game) with relation to what he’s seen and what he’s made sense of in the past (knowledge-of the game) Mastery of anticipation and decision-making… This requires… 1. Coach session design setting problems for players to detect and to solve 2. Coach behaviours that orient players’ attention to the problems to help them think about, work on, solve, and remember in-game problems 3. Player participation - attention, involvement, reflection-in-action, post session reflection-in-action to consolidate memories It’s a coach-player responsibility…

Daniel Abrahams

45,167 Aufrufe • vor 2 Jahren

Looks like on the visual side, the engine upgrade for S.T.A.L.K.E.R. 2: Heart of Chornobyl will focus on two main aspects: -Overhauled lighting, improving Lumen's indirect lighting and reflections, as well as direct lighting and shadows. -Reworked Landscape and Foliage, which will look denser and more natural. These are all great additions, but I'm more interested in the performance side, especially CPU performance, which was a major issue at launch. I'm planning to cover the new update when it launches, with comparisons between the day-one version (if I can access it) and the newest build, along with the usual in-depth look at the graphics settings and how they affect the visuals and performance. #Stalker2HeartOfChornobyl

Looks like on the visual side, the engine upgrade for S.T.A.L.K.E.R. 2: Heart of Chornobyl will focus on two main aspects: -Overhauled lighting, improving Lumen's indirect lighting and reflections, as well as direct lighting and shadows. -Reworked Landscape and Foliage, which will look denser and more natural. These are all great additions, but I'm more interested in the performance side, especially CPU performance, which was a major issue at launch. I'm planning to cover the new update when it launches, with comparisons between the day-one version (if I can access it) and the newest build, along with the usual in-depth look at the graphics settings and how they affect the visuals and performance. #Stalker2HeartOfChornobyl

BenchmarKing

27,271 Aufrufe • vor 2 Tagen

THE CONTRASTING EFFECTS OF BLUE AND RED/NIR LIGHT ON THE MITOCHONDRIA. - Recent research published this year in Nature: Scientific Reports demonstrates the effects that light in the built environment has on human health. Our modern build environment is dominated by short-wavelength light from LEDs and fluorescent lighting. This can have deleterious effects on the mitochondria. Adding to this effect is the lack of long-wavelength light from sources like the sun and incandescent lighting bulbs. These long light wavelengths have a beneficial effect on mitochondria function and overall human health. The lack of them in our modern built environment, seems to be impacting public health in a delirious fashion. Two recent papers to read: 1. 2.

THE CONTRASTING EFFECTS OF BLUE AND RED/NIR LIGHT ON THE MITOCHONDRIA. - Recent research published this year in Nature: Scientific Reports demonstrates the effects that light in the built environment has on human health. Our modern build environment is dominated by short-wavelength light from LEDs and fluorescent lighting. This can have deleterious effects on the mitochondria. Adding to this effect is the lack of long-wavelength light from sources like the sun and incandescent lighting bulbs. These long light wavelengths have a beneficial effect on mitochondria function and overall human health. The lack of them in our modern built environment, seems to be impacting public health in a delirious fashion. Two recent papers to read: 1. 2.

Jonathan Jarecki

17,850 Aufrufe • vor 6 Monaten

Teaching robots from human video is an important part of overcoming the “data gap” in robotics, but many of the details still need to be worked out. Homanga Bharadhwaj tells us about two recent research papers, Gen2Act and Spider, which go over different aspects of the problem: Gen2Act uses generative video models to create a reference of how a task should be performed given a language prompt; then, it uses a multi-purpose policy that can “translate” from human video to robot motion. However, Gen2Act has its limitations, in particular when it comes to dexterous, contact-rich tasks. That’s where SPIDER comes in: it uses human data together with simulation to train policies across many different humanoid hands and datasets. Also of note is that this is our first episode with our new rotating co-host, Jiafei Duan. To learn more, watch Episode #57 of RoboPapers now, with Chris Paxton and Jiafei Duan!

Teaching robots from human video is an important part of overcoming the “data gap” in robotics, but many of the details still need to be worked out. Homanga Bharadhwaj tells us about two recent research papers, Gen2Act and Spider, which go over different aspects of the problem: Gen2Act uses generative video models to create a reference of how a task should be performed given a language prompt; then, it uses a multi-purpose policy that can “translate” from human video to robot motion. However, Gen2Act has its limitations, in particular when it comes to dexterous, contact-rich tasks. That’s where SPIDER comes in: it uses human data together with simulation to train policies across many different humanoid hands and datasets. Also of note is that this is our first episode with our new rotating co-host, Jiafei Duan. To learn more, watch Episode #57 of RoboPapers now, with Chris Paxton and Jiafei Duan!

RoboPapers

24,286 Aufrufe • vor 7 Monaten