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.

LLava just hit 3800 stars on Github. It's a multimodal Large Language-and-Vision Assistant that can understand images and text. LLava can even handle memes (the same ones GPT-4 demo'ed at launch) and set a new SOTA on Science QA. It also supports LLaMA-2, LoRA training with academia GPUs, higher... show more

Lior Alexander

116,846 subscribers

143,540 views • 3 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

11 Comments

Lior⚡3 years ago

Github: Demo:

Lior⚡3 years ago

By:@imhaotian,@ChunyuanLi,@QingyangWu1,@yong_jae_lee

Linus Ekenstam – eu/acc3 years ago

The rise of these models and the speed of which they are entering the market makes me think we are soon only going to interact with LLM’s

Lior⚡3 years ago

Absolutely, or LLM-assisted websites. The equivalent of intercom on every website.

Charcher3 years ago

So good.

Rob Lennon 🗯 | AI Whisperer3 years ago

Definitely want to play with this soon

Lior⚡3 years ago

Let me know how it goes, about to pip install it

ai geek (wishesh) ⚡️3 years ago

Great find. Looking very promising.

thom3 years ago

@readwise save thread

wwwwg3 years ago

@memdotai mem it

Mem3 years ago

@AlphaSignalAI Saved! Here's the compiled thread: 🪄 AI-generated summary: "LLava is a multimodal Large Language-and-Vision Assistant that can understand images and text, and even handle memes. It has achieved a new SOTA on Science QA and supports LoRA...

Related Videos

🚨 BREAKING: GPT-4 image recognition already has a new competitor. Open-sourced and completely free to use. Introducing LLaVA: Large Language and Vision Assistant. I compared the viral parking space photo on GPT-4 Vision to LLaVa, and it worked flawlessly (see video).

🚨 BREAKING: GPT-4 image recognition already has a new competitor. Open-sourced and completely free to use. Introducing LLaVA: Large Language and Vision Assistant. I compared the viral parking space photo on GPT-4 Vision to LLaVa, and it worked flawlessly (see video).

Rowan Cheung

681,581 views • 2 years ago

🚀Introducing LLaVA Lightning: Train a lite, multimodal GPT-4 with just $40 in 3 hours! With our newly introduced datasets and the efficient design of LLaVA, you can now turbocharge your language model with image reasoning capabilities, in an incredibly affordable way.🧵

🚀Introducing LLaVA Lightning: Train a lite, multimodal GPT-4 with just $40 in 3 hours! With our newly introduced datasets and the efficient design of LLaVA, you can now turbocharge your language model with image reasoning capabilities, in an incredibly affordable way.🧵

Haotian Liu

302,319 views • 3 years ago

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

New short course Multimodal RAG: Chat with Videos, developed with Intel and taught by vasudevlal! In this course, you’ll work with LLaVA (Large Language and Vision Assistant), a Large Vision Language Model (LVLM) that can process both images and text. For example, given an image of a person doing a handstand on a skateboard at the beach, LLaVA doesn't just caption the scene, it’s able to predict possible outcomes, like the person losing balance or falling off. By understanding not just what's in a video frame, but what might happen next, your application can provide more insightful answers to questions about video. You'll build a full multimodal RAG pipeline that can chat about video content: - Use the BridgeTower model to create joint text-image embeddings in a 512-dimensional multimodal semantic space. - Learn video processing techniques to extract keyframes, generate transcripts using Whisper, and create captions. - Use the LanceDB vector database to store and retrieve high-dimensional multimodal embeddings. - Integrate the LLaVA model, combining CLIP's (Contrastive Language Image Pretraining) vision transformer with Llama, for advanced visual-textual reasoning. Your final system will ingest video data, generate embeddings for frames and text, perform similarity searches for relevant content, and use the retrieved multimodal context to inform LVLM-based response generation. The result is a system capable of answering nuanced questions about video content, effectively chatting about the video it has processed. Please sign up here!

Andrew Ng

107,825 views • 1 year ago

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

LLaVA-3D A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness Recent advancements in Large Multimodal Models (LMMs) have greatly enhanced their proficiency in 2D visual understanding tasks, enabling them to effectively process and understand images and videos. However, the development of LMMs with 3D-awareness for 3D scene understanding has been hindered by the lack of large-scale 3D vision-language datasets and powerful 3D encoders. In this paper, we introduce a simple yet effective framework called LLaVA-3D. Leveraging the strong 2D understanding priors from LLaVA, our LLaVA-3D efficiently adapts LLaVA for 3D scene understanding without compromising 2D understanding capabilities. To achieve this, we employ a simple yet effective representation, 3D Patch, which connects 2D CLIP patch features with their corresponding positions in 3D space. By integrating the 3D Patches into 2D LMMs and employing joint 2D and 3D vision-language instruction tuning, we establish a unified architecture for both 2D image understanding and 3D scene understanding. Experimental results show that LLaVA-3D converges 3.5x faster than existing 3D LMMs when trained on 3D vision-language datasets. Moreover, LLaVA-3D not only achieves state-of-the-art performance across various 3D tasks but also maintains comparable 2D image understanding and vision-language conversation capabilities with LLaVA.

AK

41,747 views • 1 year ago

OpenAI just announced "GPT-4o". It can reason with voice, vision, and text. The model is 2x faster, 50% cheaper, and has 5x higher rate limit than GPT-4 Turbo. It will be available for free users and via the API. The voice model can even pick up on emotion and generate emotive voice.

OpenAI just announced "GPT-4o". It can reason with voice, vision, and text. The model is 2x faster, 50% cheaper, and has 5x higher rate limit than GPT-4 Turbo. It will be available for free users and via the API. The voice model can even pick up on emotion and generate emotive voice.

Lior Alexander

485,133 views • 2 years ago

🚀 Introducing Emu3.5 — a large-scale multimodal world model that natively predicts the next vision-language state. 🔥 Trained on over 10T interleaved vision-language tokens and enhanced with reinforcement learning, Emu3.5 achieves powerful multimodal reasoning and generation. ⚡ Powered by our new Discrete Diffusion Adaptation (DiDA) for 20× faster inference. 🔥 Emu3.5 outperforms Nano Banana across image generation, editing, interleaved tasks and more. 🌍 Explore Emu3.5: Github: #Emu3 #MultimodalAI #WorldModel #NextTokenPrediction

🚀 Introducing Emu3.5 — a large-scale multimodal world model that natively predicts the next vision-language state. 🔥 Trained on over 10T interleaved vision-language tokens and enhanced with reinforcement learning, Emu3.5 achieves powerful multimodal reasoning and generation. ⚡ Powered by our new Discrete Diffusion Adaptation (DiDA) for 20× faster inference. 🔥 Emu3.5 outperforms Nano Banana across image generation, editing, interleaved tasks and more. 🌍 Explore Emu3.5: Github: #Emu3 #MultimodalAI #WorldModel #NextTokenPrediction

BAAI

51,880 views • 10 months ago

Introducing "Building with Llama 4." This short course is created with Meta AI at Meta, and taught by Amit Sangani, Director of Partner Engineering for Meta’s AI team. Meta’s new Llama 4 has added three new models and introduced the Mixture-of-Experts (MoE) architecture to its family of open-weight models, making them more efficient to serve. In this course, you’ll work with two of the three new models introduced in Llama 4. First is Maverick, a 400B parameter model, with 128 experts and 17B active parameters. Second is Scout, a 109B parameter model with 16 experts and 17B active parameters. Maverick and Scout support long context windows of up to a million tokens and 10M tokens, respectively. The latter is enough to support directly inputting even fairly large GitHub repos for analysis! In hands-on lessons, you’ll build apps using Llama 4’s new multimodal capabilities including reasoning across multiple images and image grounding, in which you can identify elements in images. You’ll also use the official Llama API, work with Llama 4’s long-context abilities, and learn about Llama’s newest open-source tools: its prompt optimization tool that automatically improves system prompts and synthetic data kit that generates high-quality datasets for fine-tuning. If you need an open model, Llama is a great option, and the Llama 4 family is an important part of any GenAI developer's toolkit. Through this course, you’ll learn to call Llama 4 via API, use its optimization tools, and build features that span text, images, and large context. Please sign up here:

Introducing "Building with Llama 4." This short course is created with Meta AI at Meta, and taught by Amit Sangani, Director of Partner Engineering for Meta’s AI team. Meta’s new Llama 4 has added three new models and introduced the Mixture-of-Experts (MoE) architecture to its family of open-weight models, making them more efficient to serve. In this course, you’ll work with two of the three new models introduced in Llama 4. First is Maverick, a 400B parameter model, with 128 experts and 17B active parameters. Second is Scout, a 109B parameter model with 16 experts and 17B active parameters. Maverick and Scout support long context windows of up to a million tokens and 10M tokens, respectively. The latter is enough to support directly inputting even fairly large GitHub repos for analysis! In hands-on lessons, you’ll build apps using Llama 4’s new multimodal capabilities including reasoning across multiple images and image grounding, in which you can identify elements in images. You’ll also use the official Llama API, work with Llama 4’s long-context abilities, and learn about Llama’s newest open-source tools: its prompt optimization tool that automatically improves system prompts and synthetic data kit that generates high-quality datasets for fine-tuning. If you need an open model, Llama is a great option, and the Llama 4 family is an important part of any GenAI developer's toolkit. Through this course, you’ll learn to call Llama 4 via API, use its optimization tools, and build features that span text, images, and large context. Please sign up here:

Andrew Ng

67,846 views • 1 year ago

InternLM-XComposer-2.5 A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks.

InternLM-XComposer-2.5 A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output We present InternLM-XComposer-2.5 (IXC-2.5), a versatile large-vision language model that supports long-contextual input and output. IXC-2.5 excels in various text-image comprehension and composition applications, achieving GPT-4V level capabilities with merely 7B LLM backend. Trained with 24K interleaved image-text contexts, it can seamlessly extend to 96K long contexts via RoPE extrapolation. This long-context capability allows IXC-2.5 to excel in tasks requiring extensive input and output contexts. Compared to its previous 2.0 version, InternLM-XComposer-2.5 features three major upgrades in vision-language comprehension: (1) Ultra-High Resolution Understanding, (2) Fine-Grained Video Understanding, and (3) Multi-Turn Multi-Image Dialogue. In addition to comprehension, IXC-2.5 extends to two compelling applications using extra LoRA parameters for text-image composition: (1) Crafting Webpages and (2) Composing High-Quality Text-Image Articles. IXC-2.5 has been evaluated on 28 benchmarks, outperforming existing open-source state-of-the-art models on 16 benchmarks. It also surpasses or competes closely with GPT-4V and Gemini Pro on 16 key tasks.

AK

66,472 views • 2 years ago

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 views • 3 years ago

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

MolmoAct2 runs zero-shot on an SO-ARM101, no training required 🦾 Ai2 open Action Reasoning Model is now in LeRobot with the full lifecycle covered: fine-tuning (full or LoRA), evaluation, and real-robot deployment. It pairs a Molmo2-ER vision-language backbone with a flow-matching action expert to turn images, language, and proprioceptive state into action chunks. The best part: ready-made checkpoints ship with calibration correction baked in, so you can point it at your SO-100/101 and just watch it work. Inference fits in ~12GB at bf16, and LoRA fine-tuning runs on a single 24GB GPU. Big thanks to the Ai2 team for building this in the open.

LeRobot

22,200 views • 1 month ago

BREAKING: Claude-2, Anthropic's ChatGPT competitor was just released and it's incredible. It's cheaper, stronger, faster, can handle PDFs, and supports longer conversations. Highlights: 1. Claude is 5x cheaper than GPT-4. 2. It has more recent data. A a mix of websites, licensed data sets from third parties and voluntarily-supplied user data from early 2023. 3. It outperforms GPT4 on the GRE writing and HumanEval coding benchmarks. 3. It features a context window of 100,000 tokens, the largest of any commercially available model. 4. It can analyze roughly 75,000 words, about the length of “The Great Gatsby". 5. It can easily handle any code related tasks.

BREAKING: Claude-2, Anthropic's ChatGPT competitor was just released and it's incredible. It's cheaper, stronger, faster, can handle PDFs, and supports longer conversations. Highlights: 1. Claude is 5x cheaper than GPT-4. 2. It has more recent data. A a mix of websites, licensed data sets from third parties and voluntarily-supplied user data from early 2023. 3. It outperforms GPT4 on the GRE writing and HumanEval coding benchmarks. 3. It features a context window of 100,000 tokens, the largest of any commercially available model. 4. It can analyze roughly 75,000 words, about the length of “The Great Gatsby". 5. It can easily handle any code related tasks.

Lior Alexander

255,648 views • 3 years ago

Andrej Karpathy just built GPT-2 from scratch on camera! Every line. Every component. Every optimization decision. Transformer blocks. Self-attention. MLP. Mixed precision. Flash Attention. AdamW. Distributed training across GPUs. 4 hours. Free. Not a lecture about how GPT-2 was built. The actual build. Running. Training. Evaluated against the original OpenAI checkpoints. The engineers who watch this do not just understand language models. They understand them at the level required to build the next one. The gap between using AI and being capable of building it is not a PhD program. It is 4 hours with the person who makes this look like something any determined engineer can do.

Andrej Karpathy just built GPT-2 from scratch on camera! Every line. Every component. Every optimization decision. Transformer blocks. Self-attention. MLP. Mixed precision. Flash Attention. AdamW. Distributed training across GPUs. 4 hours. Free. Not a lecture about how GPT-2 was built. The actual build. Running. Training. Evaluated against the original OpenAI checkpoints. The engineers who watch this do not just understand language models. They understand them at the level required to build the next one. The gap between using AI and being capable of building it is not a PhD program. It is 4 hours with the person who makes this look like something any determined engineer can do.

NeilXbt

37,778 views • 4 months ago

Finally, a RAG solution that works with complex documents! Real-world documents can be messy, filled with text, tables, images, and intricate flow charts. Traditional parsing and chunking methods struggle to handle these. So, what’s the solution? We need smart techniques that can intuitively chunk relevant context and understand what’s inside each chunk, whether it's text, images, or diagrams. In this video, I’ll walk you through a breakthrough technique for extracting structured information from complex documents. It's unlike any other technique you've seen before.✨ It takes any unstructured (text, tables, images, flow-charts) input and parses it into a JSON format that LLMs can easily process. I used EyeLevel.AI's GroundX platform for this – a powerful tool that allows you to build a RAG application in just 3 steps. It also comes with a nice Python SDK and can be easily deployed on-premise (K8s cluster)! Try it yourself:

Finally, a RAG solution that works with complex documents! Real-world documents can be messy, filled with text, tables, images, and intricate flow charts. Traditional parsing and chunking methods struggle to handle these. So, what’s the solution? We need smart techniques that can intuitively chunk relevant context and understand what’s inside each chunk, whether it's text, images, or diagrams. In this video, I’ll walk you through a breakthrough technique for extracting structured information from complex documents. It's unlike any other technique you've seen before.✨ It takes any unstructured (text, tables, images, flow-charts) input and parses it into a JSON format that LLMs can easily process. I used EyeLevel.AI's GroundX platform for this – a powerful tool that allows you to build a RAG application in just 3 steps. It also comes with a nice Python SDK and can be easily deployed on-premise (K8s cluster)! Try it yourself:

Akshay 🚀

102,660 views • 1 year ago

an infinitely large model trained on infinite data still cannot go below 1.69 GPT-4 burned three months on twenty five thousand GPUs inching toward it plot every model ever trained, error against compute on a log scale, and none of them gets below one straight line. runs ten trillion times cheaper than GPT-4 press up against the very same line that line never reaches zero. it flattens, and the number it flattens at is DeepMind's estimate for general web text the floor also moves with what you feed it. code and math sit lower because they are more predictable. scraped web sits higher that floor is the part of a text that nothing before it can predict so either we have found something like an ideal gas law for AI, or we have found the shape of the only method we know bookmark this

an infinitely large model trained on infinite data still cannot go below 1.69 GPT-4 burned three months on twenty five thousand GPUs inching toward it plot every model ever trained, error against compute on a log scale, and none of them gets below one straight line. runs ten trillion times cheaper than GPT-4 press up against the very same line that line never reaches zero. it flattens, and the number it flattens at is DeepMind's estimate for general web text the floor also moves with what you feed it. code and math sit lower because they are more predictable. scraped web sits higher that floor is the part of a text that nothing before it can predict so either we have found something like an ideal gas law for AI, or we have found the shape of the only method we know bookmark this

helicerat

66,560 views • 13 days ago

OpenAI Dev Day Just kicked off and it was the biggest day for AI since the launch of GPT-4 in April. Here's a 3 minute video with everything you need to know and a full summary: 1. GPT-4 Turbo is released. It is much better than GPT-4, can accept up to 128k characters and is 3x cheaper. The knowledge cut off is now April 2023 2. Text to Speech is also being released. They offer 6 hyper-realistic voice models that are the best I've heard from any other AI t-t-s software on the market. 3. Copyright Shield. OpenAI will actually defend your legal costs if you get sued for copyright infringement using their API! 4. GPTs. Maybe the most exciting IMHO, you can now create custom "GPTs" by training your own model of GPT and selling it on their store. This will create a massive shakeup of the current AI software landscape and is the first step towards autonomous agents.

OpenAI Dev Day Just kicked off and it was the biggest day for AI since the launch of GPT-4 in April. Here's a 3 minute video with everything you need to know and a full summary: 1. GPT-4 Turbo is released. It is much better than GPT-4, can accept up to 128k characters and is 3x cheaper. The knowledge cut off is now April 2023 2. Text to Speech is also being released. They offer 6 hyper-realistic voice models that are the best I've heard from any other AI t-t-s software on the market. 3. Copyright Shield. OpenAI will actually defend your legal costs if you get sued for copyright infringement using their API! 4. GPTs. Maybe the most exciting IMHO, you can now create custom "GPTs" by training your own model of GPT and selling it on their store. This will create a massive shakeup of the current AI software landscape and is the first step towards autonomous agents.

Mark Gadala-Maria

79,177 views • 2 years ago

Can a $175 board power an offline robot voice assistant? 🤖 It’s cool to see Gemma 4 E2B powering the Reachy Mini robot entirely locally on a Raspberry Pi 5. Inference powered by LiteRT, it handles low latency voice, vision (YOLO) and robot movement completely offline. With text generation 2x normal human speech (~300 words per minute) on just 1.5GB of memory, the Pi 5 + Gemma 4 + LiteRT combo is a demonstration of how lean edge AI can be!

Can a $175 board power an offline robot voice assistant? 🤖 It’s cool to see Gemma 4 E2B powering the Reachy Mini robot entirely locally on a Raspberry Pi 5. Inference powered by LiteRT, it handles low latency voice, vision (YOLO) and robot movement completely offline. With text generation 2x normal human speech (~300 words per minute) on just 1.5GB of memory, the Pi 5 + Gemma 4 + LiteRT combo is a demonstration of how lean edge AI can be!

Google Gemma

30,188 views • 15 days ago

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Microsoft's new Florence 2 is big for Computer Vision. It's a merge between Text and Vision. With a single prompt you can instruct the model to do CV tasks like captioning, object detection, grounding, and segmentation. The best part, it only uses a single backbone to handle everything. ▸ Excels in zero-shot performance ▸ Unified model for detection, captioning, etc. ▸ FLD-5B dataset: 5B+ annotations, 126M images ▸ New benchmarks (>5.5+) on COCO, ADE20K

Lior Alexander

186,583 views • 2 years ago

I made tons of money building websites for people and small companies. Most of that is now gone. You can now generate, customize, and deploy a website using natural language. I recorded myself building a site from scratch using 10Web.io. 4 minutes later, I had a full website generated just for me. Crazy! That's mostly how I paid rent when I graduated college: I'd either build you a new site or make changes to an existing one. It's nuts anyone can do that today by just asking. But this doesn't stop with generating a website. 10Web also released an AI Copilot that you can use to edit a website with a chat-based AI assistant. Here is what you can do with the AI Copilot: 1. You can edit individual elements and widgets on your site by selecting them and describing the changes you want. 2. You can generate new images, create sections, and generate or edit text. 3. You can also add any new elements to the site. The best way to understand how much progress we've made is by looking at the AI Copilot in action: And the funny part is that we are just figuring out how to use AI models. 2025 will be crazy.

I made tons of money building websites for people and small companies. Most of that is now gone. You can now generate, customize, and deploy a website using natural language. I recorded myself building a site from scratch using 10Web.io. 4 minutes later, I had a full website generated just for me. Crazy! That's mostly how I paid rent when I graduated college: I'd either build you a new site or make changes to an existing one. It's nuts anyone can do that today by just asking. But this doesn't stop with generating a website. 10Web also released an AI Copilot that you can use to edit a website with a chat-based AI assistant. Here is what you can do with the AI Copilot: 1. You can edit individual elements and widgets on your site by selecting them and describing the changes you want. 2. You can generate new images, create sections, and generate or edit text. 3. You can also add any new elements to the site. The best way to understand how much progress we've made is by looking at the AI Copilot in action: And the funny part is that we are just figuring out how to use AI models. 2025 will be crazy.

Santiago

57,917 views • 1 year ago