Superman's banner
Superman's profile picture

Superman

@thesupermanmx • 9,717 subscribers

AI & Neuroscience

Shorts

China open-sourced a peanut-sized OCR that parses entire 100-page PDFs in one shot.. It's called Unlimited-OCR. Only 3B params. Runs locally. Every other OCR tool chops your doc into pages and loses the thread. this one reads the whole thing in a single pass. → One-shot "long-horizon" parsing (32K context window) → Multilingual, out of the box → 93% on the standard parsing benchmark (+6 over baseline) → <0.11 error rate past 40 pages → Runs 100% locally on your own hardware → Works with Transformers, vLLM, SGLang, Docker, Ollama, llama.cpp Traditional cloud OCR (Textract, Google Vision, Azure Doc Intelligence) costs $1.50–$15 per 1,000 pages. This runs on your machine. For free. Forever. Baidu built it explicitly to push DeepSeek-OCR one step further. Already at 1.9M downloads on Hugging Face and most people have no idea it exists yet. 100% open source.

China open-sourced a peanut-sized OCR that parses entire 100-page PDFs in one shot.. It's called Unlimited-OCR. Only 3B params. Runs locally. Every other OCR tool chops your doc into pages and loses the thread. this one reads the whole thing in a single pass. → One-shot "long-horizon" parsing (32K context window) → Multilingual, out of the box → 93% on the standard parsing benchmark (+6 over baseline) → <0.11 error rate past 40 pages → Runs 100% locally on your own hardware → Works with Transformers, vLLM, SGLang, Docker, Ollama, llama.cpp Traditional cloud OCR (Textract, Google Vision, Azure Doc Intelligence) costs $1.50–$15 per 1,000 pages. This runs on your machine. For free. Forever. Baidu built it explicitly to push DeepSeek-OCR one step further. Already at 1.9M downloads on Hugging Face and most people have no idea it exists yet. 100% open source.

1,101,919 次观看

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

NVIDIA open-sourced a 600M model that transcribes 40 languages in real-time at 80ms latency and it costs $0. that's faster than you can blink. across mandarin, arabic, hindi, portuguese, tagalog, whatever,from a SINGLE checkpoint. → 17x more concurrent streams than buffered ASR on the same H100. → punctuation + capitalization built-in. no post-processing. → runs on your own GPU. no API bill 100% Open Source.

104,663 次观看

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

someone literally vibe-coded "twitch" for running 🤯 you stream your run live and people watch your dot move across a 3d map of the city in real time. → live 3d map tracking your exact route → pace, distance, heart rate updating live on screen → live graphs for elevation and heart rate → viewers chat with you mid-run and yell at you to push up the hill 100% free..
0:47
thesupermanmx's profile picture

someone literally vibe-coded "twitch" for running 🤯 you stream your run live and people watch your dot move across a 3d map of the city in real time. → live 3d map tracking your exact route → pace, distance, heart rate updating live on screen → live graphs for elevation and heart rate → viewers chat with you mid-run and yell at you to push up the hill 100% free..

Superman

1,596,803 次观看 • 2 天前

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.
1:10
thesupermanmx's profile picture

China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time. one camera. no LiDAR. 10,000+ frames without falling apart. just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps. → runs at ~20 FPS on a single GPU → Stable over 10,000+ frames → Beats optimization-based methods on benchmarks → Works on drone footage, driving videos, indoor walkthroughs 100% open source.

Superman

1,453,932 次观看 • 1 个月前

someone open-sourced a tool that turns any phone video into a full 3D world in real time. you record a walk around your house, drop the mp4 in, and the entire scene comes back as a walkable 996k-point world at 60fps on your local GPU. no cloud. no subscription. runs 100% locally. 100% open source.
0:33
thesupermanmx's profile picture

someone open-sourced a tool that turns any phone video into a full 3D world in real time. you record a walk around your house, drop the mp4 in, and the entire scene comes back as a walkable 996k-point world at 60fps on your local GPU. no cloud. no subscription. runs 100% locally. 100% open source.

Superman

817,989 次观看 • 1 个月前

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source
0:28
thesupermanmx's profile picture

Microsoft open-sourced a 4B model that turns any image into a production-ready 3D asset in 3 seconds. It’s called TRELLIS.2, a fully textured, physically accurate 3D models with PBR textures out of the box. → Full PBR (base color, roughness, metallic, opacity) → Handles hair, cloth, glass, non-manifold geometry → Exports .glb ready for Unity/Unreal/Blender → Runs locally, ships in 3 seconds It's not a demo or a research preview. The full training codebase is public. You can fine-tune it on your own asset library and get a model that generates in your studio's exact style. 100% Open Source

Superman

282,217 次观看 • 1 个月前

ssomeone vibe-coded a video stream that is secretly 100% text so it can't be blocked. It’s called ASCIline. It renders streams 360p video at 30fps with zero video element on the page. every frame is colored text characters painted on a canvas. 100% Open Source.
0:34
thesupermanmx's profile picture

ssomeone vibe-coded a video stream that is secretly 100% text so it can't be blocked. It’s called ASCIline. It renders streams 360p video at 30fps with zero video element on the page. every frame is colored text characters painted on a canvas. 100% Open Source.

Superman

53,731 次观看 • 1 个月前

Someone just built a tool that turns any object image into a fully coded, animation-ready 3d model in your browser. just drop a photo and it sculpts the object in pure Three.js code, animation-ready with pivots, physics anchors, and PBR materials. 100% free.
0:20
thesupermanmx's profile picture

Someone just built a tool that turns any object image into a fully coded, animation-ready 3d model in your browser. just drop a photo and it sculpts the object in pure Three.js code, animation-ready with pivots, physics anchors, and PBR materials. 100% free.

Superman

37,025 次观看 • 1 个月前

Someone open-sourced a 66M parameter model that beats ElevenLabs, OpenAI, and Gemini and runs entirely offline on a Raspberry Pi. it's called Supertonic, a text-to-speech model so fast it turns an entire webpage into audio in under 1 second. locally. offline. for free. text-to-speech has lived in the cloud for years. every spoken character was an API call and a fraction of a cent. Supertonic 3 kills that entirely. the model is 99M parameters. ships as a single ONNX file. hits 167× faster than real-time on a laptop CPU. that's ~1,263 characters of speech per second. other open systems sit at 55–287. no cloud. no API. no GPU. → 31 languages, no separate adapters → works inside a browser tab (WebGPU/WASM) → handles phone numbers, currency, dates — no preprocessing → inline tags for laugh and breath → Turns an entire webpage into audio in under 1 second → 44.1kHz studio-grade WAV, no upsampler needed` and on real-world text, "$5.2M", "(212) 555-0142 ext. 402", "30kph”, it's the only one that reads them correctly. ElevenLabs Flash, OpenAI TTS-1, Gemini 2.5 Flash all fail. Supertonic passes. 11.2k stars. 100% Open Source.
1:00
thesupermanmx's profile picture

Someone open-sourced a 66M parameter model that beats ElevenLabs, OpenAI, and Gemini and runs entirely offline on a Raspberry Pi. it's called Supertonic, a text-to-speech model so fast it turns an entire webpage into audio in under 1 second. locally. offline. for free. text-to-speech has lived in the cloud for years. every spoken character was an API call and a fraction of a cent. Supertonic 3 kills that entirely. the model is 99M parameters. ships as a single ONNX file. hits 167× faster than real-time on a laptop CPU. that's ~1,263 characters of speech per second. other open systems sit at 55–287. no cloud. no API. no GPU. → 31 languages, no separate adapters → works inside a browser tab (WebGPU/WASM) → handles phone numbers, currency, dates — no preprocessing → inline tags for laugh and breath → Turns an entire webpage into audio in under 1 second → 44.1kHz studio-grade WAV, no upsampler needed` and on real-world text, "$5.2M", "(212) 555-0142 ext. 402", "30kph”, it's the only one that reads them correctly. ElevenLabs Flash, OpenAI TTS-1, Gemini 2.5 Flash all fail. Supertonic passes. 11.2k stars. 100% Open Source.

Superman

30,416 次观看 • 1 个月前

没有更多内容可加载