正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Test-time scaling, reasoning, and generally search-like processes clearly drive significant gains in LLMs. Largely owed to the structure of language. One would think the same could apply to non-linguistic domains, like image generation, but that obviously depends on whether the structure of the domain's representation lends itself to search.... show more

Amir Zamir

5,869 subscribers

15,478 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Wow, we can steer diffusion models at inference time! Introducing Diffusion Tree Sampling (DTS): a search-based approach inspired by Monte Carlo Tree Search that turns inference into an anytime, reward-guided optimization process. Diffusion Tree Sampling (DTS) produces asymptotically exact samples from the target distribution in the limit of infinite rollouts, and its greedy variant, Diffusion Tree Search (DTS⋆), performs a global search for high reward samples. The results are pretty impressive: - On MNIST and CIFAR-10 class-conditional generation, DTS matches the FID of the best-performing baseline with up to 10× less compute. - In text-to-image generation and language completion tasks, DTS⋆ effectively searches for high reward samples that match best-of-N with up to 5× less compute.

Wow, we can steer diffusion models at inference time! Introducing Diffusion Tree Sampling (DTS): a search-based approach inspired by Monte Carlo Tree Search that turns inference into an anytime, reward-guided optimization process. Diffusion Tree Sampling (DTS) produces asymptotically exact samples from the target distribution in the limit of infinite rollouts, and its greedy variant, Diffusion Tree Search (DTS⋆), performs a global search for high reward samples. The results are pretty impressive: - On MNIST and CIFAR-10 class-conditional generation, DTS matches the FID of the best-performing baseline with up to 10× less compute. - In text-to-image generation and language completion tasks, DTS⋆ effectively searches for high reward samples that match best-of-N with up to 5× less compute.

机器之心 JIQIZHIXIN

19,037 次观看 • 1 年前

Elon Musk: It’ll probably take around 50,000 H100 servers to power this. That’s the scale of Grok — not just an AI chatbot, but a Colossus-level intelligence engine, running on tens of thousands of NVIDIA H100s every single day. Musk explains that Grok will enable semantic search on 𝕏. That means you don’t just search by words — you ask real questions in natural language, and Grok will understand the meaning, context, and intent, just like a human.

Elon Musk: It’ll probably take around 50,000 H100 servers to power this. That’s the scale of Grok — not just an AI chatbot, but a Colossus-level intelligence engine, running on tens of thousands of NVIDIA H100s every single day. Musk explains that Grok will enable semantic search on 𝕏. That means you don’t just search by words — you ask real questions in natural language, and Grok will understand the meaning, context, and intent, just like a human.

Ian Miles Cheong

35,456 次观看 • 8 个月前

🚨DEEPSEARCH BY xAI: THE SEARCH ENGINE THAT THINKS FOR YOU "DeepSearch is the first generation of agents that not only help engineers, researchers, and scientists with coding, but also assist everyone in answering day-to-day questions. It's like a next-generation search engine that truly helps you understand the universe." Source: xAI Elon Musk

🚨DEEPSEARCH BY xAI: THE SEARCH ENGINE THAT THINKS FOR YOU "DeepSearch is the first generation of agents that not only help engineers, researchers, and scientists with coding, but also assist everyone in answering day-to-day questions. It's like a next-generation search engine that truly helps you understand the universe." Source: xAI Elon Musk

Mario Nawfal

82,488 次观看 • 1 年前

LLM agents have demonstrated promise in their ability to automate computer tasks, but face challenges with multi-step reasoning and planning. Towards addressing this, we propose an inference-time tree search algorithm for LLM agents to explicitly perform exploration and multi-step planning in interactive web environments. It is the first tree search algorithm for LLM agents that shows effectiveness on realistic and complex web environments: on the challenging VisualWebArena benchmark, applying our search algorithm on top of a GPT-4o agent yields a 39.7% relative increase in success rate compared to the same baseline without search, setting a state-of-the-art success rate of 26.4%. On WebArena, search also yields a 28.0% relative improvement over a baseline agent, setting a competitive success rate of 19.2%.

LLM agents have demonstrated promise in their ability to automate computer tasks, but face challenges with multi-step reasoning and planning. Towards addressing this, we propose an inference-time tree search algorithm for LLM agents to explicitly perform exploration and multi-step planning in interactive web environments. It is the first tree search algorithm for LLM agents that shows effectiveness on realistic and complex web environments: on the challenging VisualWebArena benchmark, applying our search algorithm on top of a GPT-4o agent yields a 39.7% relative increase in success rate compared to the same baseline without search, setting a state-of-the-art success rate of 26.4%. On WebArena, search also yields a 28.0% relative improvement over a baseline agent, setting a competitive success rate of 19.2%.

Jing Yu Koh

124,878 次观看 • 2 年前

New Gemini Robotics 1.5 models will enable robots to better reason, plan ahead, use digital tools like Search, and transfer learning from one kind of robot to another. Our next big step towards general-purpose robots that are truly helpful — you can see how the robot reasons as it sorts laundry in the video below.

New Gemini Robotics 1.5 models will enable robots to better reason, plan ahead, use digital tools like Search, and transfer learning from one kind of robot to another. Our next big step towards general-purpose robots that are truly helpful — you can see how the robot reasons as it sorts laundry in the video below.

Sundar Pichai

496,365 次观看 • 10 个月前

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 次观看 • 1 年前

the reason promptwatch became so big is simple: we invested in tracking real AI traffic at scale we have already collected 99,897,119+ chatgpt (and other LLMs), citations, clicks, and search bots from real users → track chatgpt citations in real time → monitor prompts that actually are used → optimize content that gets traffic our thesis: - all search will be AI search - personalization in search will move the tracking to the client site (hence our investment in analytics) - a lot of the traditional SEO methods will stay the same, but tracking will completely change - impact of social media on search will increase

the reason promptwatch became so big is simple: we invested in tracking real AI traffic at scale we have already collected 99,897,119+ chatgpt (and other LLMs), citations, clicks, and search bots from real users → track chatgpt citations in real time → monitor prompts that actually are used → optimize content that gets traffic our thesis: - all search will be AI search - personalization in search will move the tracking to the client site (hence our investment in analytics) - a lot of the traditional SEO methods will stay the same, but tracking will completely change - impact of social media on search will increase

Klaas

48,776 次观看 • 10 个月前

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors paper page: present Magic123, a two-stage coarse-to-fine approach for high-quality, textured 3D meshes generation from a single unposed image in the wild using both2D and 3D priors. In the first stage, we optimize a neural radiance field to produce a coarse geometry. In the second stage, we adopt a memory-efficient differentiable mesh representation to yield a high-resolution mesh with a visually appealing texture. In both stages, the 3D content is learned through reference view supervision and novel views guided by a combination of 2D and 3D diffusion priors. We introduce a single trade-off parameter between the 2D and 3D priors to control exploration (more imaginative) and exploitation (more precise) of the generated geometry. Additionally, we employ textual inversion and monocular depth regularization to encourage consistent appearances across views and to prevent degenerate solutions, respectively. Magic123 demonstrates a significant improvement over previous image-to-3D techniques, as validated through extensive experiments on synthetic benchmarks and diverse real-world images.

AK

305,663 次观看 • 3 年前

Google Reverse Image Search doesn’t work the way you might think. When you search a viral image, the results may show an old date under the image. That doesn’t necessarily mean it’s the actual date of the photo. This happens because the image might have been used in another article. To find the real source, you need to click on the link in the results and check the page itself. For example, when I reverse-searched this photo, one result showed the date March 4, 2026 under the image. But when I clicked the article, Benjamin Netanyahu’s photo wasn’t there. Similarly, another result showed October 11, 2022, but clicking the link revealed that the photo wasn’t in that article either. Here’s another example, one result showed February 28, 2026, but clicking the article opened a March 17, 2026 post, and there the same image appeared.

Google Reverse Image Search doesn’t work the way you might think. When you search a viral image, the results may show an old date under the image. That doesn’t necessarily mean it’s the actual date of the photo. This happens because the image might have been used in another article. To find the real source, you need to click on the link in the results and check the page itself. For example, when I reverse-searched this photo, one result showed the date March 4, 2026 under the image. But when I clicked the article, Benjamin Netanyahu’s photo wasn’t there. Similarly, another result showed October 11, 2022, but clicking the link revealed that the photo wasn’t in that article either. Here’s another example, one result showed February 28, 2026, but clicking the article opened a March 17, 2026 post, and there the same image appeared.

Vishal Maheshwari

24,282 次观看 • 4 个月前

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

(1/5) Gemini 3, our most intelligent model, is landing in Google Search today – starting with AI Mode. Excited that this is the first time we’re shipping a new Gemini model in Search on day one! 🚀 In Search, Gemini 3 with generative layouts will make it easy to get a rich understanding of anything on your mind. It has state-of-the-art reasoning, deep multimodal understanding and advanced agentic capabilities. That allows the model to shine when you ask it to explain advanced concepts or ideas – it reasons and can code interactive visuals in real-time. It can tackle your toughest questions like advanced science.

Robby Stein

94,877 次观看 • 8 个月前

Elon Musk: Despite starting from scratch six months ago, Grok Imagine now generates more videos and images than everyone else combined. “My prediction is that most of AI compute is going to be real-time video understanding and real-time video generation. And we expect to be the leaders in that. It's worth emphasizing these points that six months ago we had basically nothing, very weak in video and image generation and editing and went in six months to the number one spot and in fact generating more videos and images than everyone else combined. We're going to do the same thing with coding and we're going to do the same thing with Macrohard and. I think people will be pretty impressed with the Grok 4.2 model that's coming out. It's a significant improvement. That's the small version of our new model. So we'll have a medium and a large version that are even more intelligent.” From: xAI All-Hands, February 10, 2026

Elon Musk: Despite starting from scratch six months ago, Grok Imagine now generates more videos and images than everyone else combined. “My prediction is that most of AI compute is going to be real-time video understanding and real-time video generation. And we expect to be the leaders in that. It's worth emphasizing these points that six months ago we had basically nothing, very weak in video and image generation and editing and went in six months to the number one spot and in fact generating more videos and images than everyone else combined. We're going to do the same thing with coding and we're going to do the same thing with Macrohard and. I think people will be pretty impressed with the Grok 4.2 model that's coming out. It's a significant improvement. That's the small version of our new model. So we'll have a medium and a large version that are even more intelligent.” From: xAI All-Hands, February 10, 2026

ELON CLIPS

12,007 次观看 • 5 个月前

I’m very excited to announce AI Autocomplete AI Autocomplete is a breakthrough patented technology that supercharges natural language input = Unlocking 10x faster search and commerce, advertising, and powerful augmented reality. Available for use as an SDK. This solves a fundamental problem of today’s chat interfaces – They are good at single step request, but any multi-step action (like booking a flight or purchasing goods) quickly becomes a back and forth 'game of 10 questions'. While working on our own assistant, we realized the core driver of this problem is a human one: People don’t know everything they need to say upfront, for every action you could do on the internet. And to solve it, we would need to think about how to marry design and technology in a new way. AI Autocomplete solves this, and can now plug into chat interfaces to guide you in real-time, with everything you would need to say, upfront. So you can do anything you can do on the internet in one shot. No more back and forth. As a result, this unlocks multiple AI breakthroughs: 1. 10x faster search and commerce 2. Smarter (and far lower cost) media generation 3. Natural language advertising 4. Powerful, lightweight Augmented Reality From here, we’ll be using this for Hero, but we also want others to use it too since this is an industry-wide problem. So if you have a product that could benefit from AI Autocomplete and want to work with us, reach out below! Shoutout to Seung W. Lee who helped think of and patent this nearly 3 years ago! And shoutout to the entire Hero Assistant team that keeps innovating on the next generation of AI products

I’m very excited to announce AI Autocomplete AI Autocomplete is a breakthrough patented technology that supercharges natural language input = Unlocking 10x faster search and commerce, advertising, and powerful augmented reality. Available for use as an SDK. This solves a fundamental problem of today’s chat interfaces – They are good at single step request, but any multi-step action (like booking a flight or purchasing goods) quickly becomes a back and forth 'game of 10 questions'. While working on our own assistant, we realized the core driver of this problem is a human one: People don’t know everything they need to say upfront, for every action you could do on the internet. And to solve it, we would need to think about how to marry design and technology in a new way. AI Autocomplete solves this, and can now plug into chat interfaces to guide you in real-time, with everything you would need to say, upfront. So you can do anything you can do on the internet in one shot. No more back and forth. As a result, this unlocks multiple AI breakthroughs: 1. 10x faster search and commerce 2. Smarter (and far lower cost) media generation 3. Natural language advertising 4. Powerful, lightweight Augmented Reality From here, we’ll be using this for Hero, but we also want others to use it too since this is an industry-wide problem. So if you have a product that could benefit from AI Autocomplete and want to work with us, reach out below! Shoutout to Seung W. Lee who helped think of and patent this nearly 3 years ago! And shoutout to the entire Hero Assistant team that keeps innovating on the next generation of AI products

brad

303,751 次观看 • 8 个月前

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

Our research team just released Flex-Forcing: a video generation method that lets a single model switch between generation methods at inference time. Right now there are two main approaches to video generation. Bidirectional diffusion models attend to every frame at once, holding structure well at the cost of speed. Autoregressive models generate frame by frame, so they stream fast and scale to long clips, but accumulate error and drift over time. Flex-Forcing trains a single model to do both, letting you choose from the range at inference based on your compute budget.

NVIDIA AI

31,412 次观看 • 20 天前

Traditional (SQL) databases rely primarily on keyword-based searches to retrieve information. These searches match the exact words or phrases in your query to the text stored in the database. While effective for many applications, this method has limitations when it comes to understanding context or finding relevant information that doesn’t include the exact keywords. Hybrid search combines the strengths of traditional keyword-based BM25 search with the advanced capabilities of semantic search. To effectively implement a hybrid search, a vector database is essential. Vector databases go beyond just words; they understand the meaning behind the data. They transform data such as text, images, or audio into numerical representations called vectors. These vector embeddings enable the database to find similar items, even if they don't share exact keywords. When you integrate hybrid search with Retrieval-Augmented Generation (RAG) systems, you can achieve higher accuracy in retrieved context and better output in generated responses. Learn more about RAG systems in this video with Victoria Slocum:

Traditional (SQL) databases rely primarily on keyword-based searches to retrieve information. These searches match the exact words or phrases in your query to the text stored in the database. While effective for many applications, this method has limitations when it comes to understanding context or finding relevant information that doesn’t include the exact keywords. Hybrid search combines the strengths of traditional keyword-based BM25 search with the advanced capabilities of semantic search. To effectively implement a hybrid search, a vector database is essential. Vector databases go beyond just words; they understand the meaning behind the data. They transform data such as text, images, or audio into numerical representations called vectors. These vector embeddings enable the database to find similar items, even if they don't share exact keywords. When you integrate hybrid search with Retrieval-Augmented Generation (RAG) systems, you can achieve higher accuracy in retrieved context and better output in generated responses. Learn more about RAG systems in this video with Victoria Slocum:

Femke Plantinga

140,618 次观看 • 2 年前

Made a short music visual that felt less like “AI generation” and more like a real performance, with full video production handled in one place. Expressions, timing, and movement actually listened to the song instead of sitting on top of it. What surprised me most was how naturally the visuals evolved with the lyrics, almost like the track was directing itself. The best part: short production time, and it’s all in one workflow, no tool-switching. Created with Drama.land_official →

Made a short music visual that felt less like “AI generation” and more like a real performance, with full video production handled in one place. Expressions, timing, and movement actually listened to the song instead of sitting on top of it. What surprised me most was how naturally the visuals evolved with the lyrics, almost like the track was directing itself. The best part: short production time, and it’s all in one workflow, no tool-switching. Created with Drama.land_official →

SARAH

66,758 次观看 • 5 个月前

Introducing Sharpe Search: On-Chain Search AI Agent Powered by Hive Intelligence We’re thrilled to announce the launch of Sharpe Search, a crypto search AI agent powered by Hive Intelligence Designed to simplify blockchain data interaction, Sharpe Search represents a significant step toward making crypto more accessible and actionable for users at every level. Sharpe Search leverages Hive Intelligence’s advanced search API to provide real-time, actionable insights across the blockchain ecosystem. Here’s a detailed look at what Sharpe Search is, how it works: What Is Sharpe Search? At its core, Sharpe Search is an AI agent purpose-built for querying and analyzing on-chain data. It takes the complexity out of blockchain exploration by enabling users to ask questions in plain language and receive detailed, accurate responses. Whether you’re looking to monitor wallet activity, track portfolio positions, or analyze transaction history, Sharpe Search ensures that the answers are at your fingertips—accurate, comprehensive, and delivered instantly. How Does Sharpe Search Work? Sharpe Search is powered by Hive Intelligence, a search engine API designed to make blockchain data easily accessible and AI-ready. Here’s a breakdown of how it enables Sharpe Search to function effectively: 1. LLM-Optimized Query Processing Sharpe Search leverages Hive Intelligence's optimized responses for large language models. This ensures that AI agents can process blockchain data in a structured format, delivering precise answers to complex user queries. 2. Natural Language Interaction Forget the need for technical knowledge. Sharpe Search supports natural language queries, making it as simple as typing: - “What tokens are in my wallet? Am I eligible for any airdrop I haven't claimed yet?” - “Check me my last 100 transactions, tell me if I interacted with any protocol with recent hacks” - “Track my wallet activity over the past month, suggest optimised portfolio based on best stable yields available” 3. Real-Time Insights Across Multi-Chains Using Hive Intelligence, Sharpe Search connects to over 20 chains and 5000+ Protocols. This real-time access ensures that the AI agent provides up-to-date and actionable insights, no matter how dynamic the blockchain environment. 4. Unified API Access Sharpe Search consolidates fragmented blockchain data through Hive’s unified API. Instead of dealing with multiple integrations, Sharpe Search uses a single access point to aggregate and query data, reducing complexity for both users and developers. Technical Depth: The AI Agent Advantage Sharpe Search's design philosophy revolves around the principle of creating an intuitive, AI-driven experience. Here’s what makes its technology stand out: Data Indexing and Aggregation: Hive Intelligence employs advanced indexing algorithms to aggregate data from multiple chains. This ensures that Sharpe Search can retrieve information within milliseconds, even when querying vast datasets. Dynamic Updates: Blockchain data is volatile. Sharpe Search processes dynamic updates in real time, enabling users to act on the most recent metrics, transactions, and balances without delays. Contextual Understanding: The AI agent parses natural language queries and contextualizes them to blockchain-specific scenarios. For instance, when querying “Show portfolio details,” Sharpe Search understands the underlying requirements—fetching wallet holdings, token values, and current positions. Hive Intelligence: The Backbone of Sharpe Search While Sharpe Search takes center stage, Hive Intelligence provides the critical infrastructure to make it all possible. Its LLM-ready responses and multi-chain support ensure that Sharpe Search operates at the forefront of blockchain data accessibility. By launching Hive Intelligence through Sharpe Launchpad, Sharpe reinforces its commitment to supporting innovation in the blockchain space. Hive’s infrastructure not only powers Sharpe Search but also lays the groundwork for future AI agents to thrive in the ecosystem. What’s Next for Sharpe Search? Currently in invite-only access, Sharpe Search is preparing for a broader public release. Future updates will include: - Expanded Blockchain Coverage: More chains and protocols will be added. - Enhanced Query Flexibility: Even more advanced natural language capabilities. Stay tuned for the public launch and get ready to explore crypto like never before!

Introducing Sharpe Search: On-Chain Search AI Agent Powered by Hive Intelligence We’re thrilled to announce the launch of Sharpe Search, a crypto search AI agent powered by Hive Intelligence Designed to simplify blockchain data interaction, Sharpe Search represents a significant step toward making crypto more accessible and actionable for users at every level. Sharpe Search leverages Hive Intelligence’s advanced search API to provide real-time, actionable insights across the blockchain ecosystem. Here’s a detailed look at what Sharpe Search is, how it works: What Is Sharpe Search? At its core, Sharpe Search is an AI agent purpose-built for querying and analyzing on-chain data. It takes the complexity out of blockchain exploration by enabling users to ask questions in plain language and receive detailed, accurate responses. Whether you’re looking to monitor wallet activity, track portfolio positions, or analyze transaction history, Sharpe Search ensures that the answers are at your fingertips—accurate, comprehensive, and delivered instantly. How Does Sharpe Search Work? Sharpe Search is powered by Hive Intelligence, a search engine API designed to make blockchain data easily accessible and AI-ready. Here’s a breakdown of how it enables Sharpe Search to function effectively: 1. LLM-Optimized Query Processing Sharpe Search leverages Hive Intelligence's optimized responses for large language models. This ensures that AI agents can process blockchain data in a structured format, delivering precise answers to complex user queries. 2. Natural Language Interaction Forget the need for technical knowledge. Sharpe Search supports natural language queries, making it as simple as typing: - “What tokens are in my wallet? Am I eligible for any airdrop I haven't claimed yet?” - “Check me my last 100 transactions, tell me if I interacted with any protocol with recent hacks” - “Track my wallet activity over the past month, suggest optimised portfolio based on best stable yields available” 3. Real-Time Insights Across Multi-Chains Using Hive Intelligence, Sharpe Search connects to over 20 chains and 5000+ Protocols. This real-time access ensures that the AI agent provides up-to-date and actionable insights, no matter how dynamic the blockchain environment. 4. Unified API Access Sharpe Search consolidates fragmented blockchain data through Hive’s unified API. Instead of dealing with multiple integrations, Sharpe Search uses a single access point to aggregate and query data, reducing complexity for both users and developers. Technical Depth: The AI Agent Advantage Sharpe Search's design philosophy revolves around the principle of creating an intuitive, AI-driven experience. Here’s what makes its technology stand out: Data Indexing and Aggregation: Hive Intelligence employs advanced indexing algorithms to aggregate data from multiple chains. This ensures that Sharpe Search can retrieve information within milliseconds, even when querying vast datasets. Dynamic Updates: Blockchain data is volatile. Sharpe Search processes dynamic updates in real time, enabling users to act on the most recent metrics, transactions, and balances without delays. Contextual Understanding: The AI agent parses natural language queries and contextualizes them to blockchain-specific scenarios. For instance, when querying “Show portfolio details,” Sharpe Search understands the underlying requirements—fetching wallet holdings, token values, and current positions. Hive Intelligence: The Backbone of Sharpe Search While Sharpe Search takes center stage, Hive Intelligence provides the critical infrastructure to make it all possible. Its LLM-ready responses and multi-chain support ensure that Sharpe Search operates at the forefront of blockchain data accessibility. By launching Hive Intelligence through Sharpe Launchpad, Sharpe reinforces its commitment to supporting innovation in the blockchain space. Hive’s infrastructure not only powers Sharpe Search but also lays the groundwork for future AI agents to thrive in the ecosystem. What’s Next for Sharpe Search? Currently in invite-only access, Sharpe Search is preparing for a broader public release. Future updates will include: - Expanded Blockchain Coverage: More chains and protocols will be added. - Enhanced Query Flexibility: Even more advanced natural language capabilities. Stay tuned for the public launch and get ready to explore crypto like never before!

Sharpe AI

263,278 次观看 • 1 年前

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing abs: paper page: present the content deformation field CoDeF as a new type of video representation, which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i.e., rendered from the canonical content field) to each individual frame along the time axis.Given a target video, these two fields are jointly optimized to reconstruct it through a carefully tailored rendering pipeline.We advisedly introduce some regularizations into the optimization process, urging the canonical content field to inherit semantics (e.g., the object shape) from the video.With such a design, CoDeF naturally supports lifting image algorithms for video processing, in the sense that one can apply an image algorithm to the canonical image and effortlessly propagate the outcomes to the entire video with the aid of the temporal deformation field.We experimentally show that CoDeF is able to lift image-to-image translation to video-to-video translation and lift keypoint detection to keypoint tracking without any training.More importantly, thanks to our lifting strategy that deploys the algorithms on only one image, we achieve superior cross-frame consistency in processed videos compared to existing video-to-video translation approaches, and even manage to track non-rigid objects like water and smog.

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing abs: paper page: present the content deformation field CoDeF as a new type of video representation, which consists of a canonical content field aggregating the static contents in the entire video and a temporal deformation field recording the transformations from the canonical image (i.e., rendered from the canonical content field) to each individual frame along the time axis.Given a target video, these two fields are jointly optimized to reconstruct it through a carefully tailored rendering pipeline.We advisedly introduce some regularizations into the optimization process, urging the canonical content field to inherit semantics (e.g., the object shape) from the video.With such a design, CoDeF naturally supports lifting image algorithms for video processing, in the sense that one can apply an image algorithm to the canonical image and effortlessly propagate the outcomes to the entire video with the aid of the temporal deformation field.We experimentally show that CoDeF is able to lift image-to-image translation to video-to-video translation and lift keypoint detection to keypoint tracking without any training.More importantly, thanks to our lifting strategy that deploys the algorithms on only one image, we achieve superior cross-frame consistency in processed videos compared to existing video-to-video translation approaches, and even manage to track non-rigid objects like water and smog.

AK

153,241 次观看 • 2 年前

VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams paper page: Neural Radiance Fields (NeRFs) excel in photorealistically rendering static scenes. However, rendering dynamic, long-duration radiance fields on ubiquitous devices remains challenging, due to data storage and computational constraints. In this paper, we introduce VideoRF, the first approach to enable real-time streaming and rendering of dynamic radiance fields on mobile platforms. At the core is a serialized 2D feature image stream representing the 4D radiance field all in one. We introduce a tailored training scheme directly applied to this 2D domain to impose the temporal and spatial redundancy of the feature image stream. By leveraging the redundancy, we show that the feature image stream can be efficiently compressed by 2D video codecs, which allows us to exploit video hardware accelerators to achieve real-time decoding. On the other hand, based on the feature image stream, we propose a novel rendering pipeline for VideoRF, which has specialized space mappings to query radiance properties efficiently. Paired with a deferred shading model, VideoRF has the capability of real-time rendering on mobile devices thanks to its efficiency. We have developed a real-time interactive player that enables online streaming and rendering of dynamic scenes, offering a seamless and immersive free-viewpoint experience across a range of devices, from desktops to mobile phones.

VideoRF: Rendering Dynamic Radiance Fields as 2D Feature Video Streams paper page: Neural Radiance Fields (NeRFs) excel in photorealistically rendering static scenes. However, rendering dynamic, long-duration radiance fields on ubiquitous devices remains challenging, due to data storage and computational constraints. In this paper, we introduce VideoRF, the first approach to enable real-time streaming and rendering of dynamic radiance fields on mobile platforms. At the core is a serialized 2D feature image stream representing the 4D radiance field all in one. We introduce a tailored training scheme directly applied to this 2D domain to impose the temporal and spatial redundancy of the feature image stream. By leveraging the redundancy, we show that the feature image stream can be efficiently compressed by 2D video codecs, which allows us to exploit video hardware accelerators to achieve real-time decoding. On the other hand, based on the feature image stream, we propose a novel rendering pipeline for VideoRF, which has specialized space mappings to query radiance properties efficiently. Paired with a deferred shading model, VideoRF has the capability of real-time rendering on mobile devices thanks to its efficiency. We have developed a real-time interactive player that enables online streaming and rendering of dynamic scenes, offering a seamless and immersive free-viewpoint experience across a range of devices, from desktops to mobile phones.

AK

38,686 次观看 • 2 年前

WE COULD NOT BELIEVE IT WHEN WE SAW THIS We were curious about Kimi K3's massive jump in consumed thinking tokens After taking a closer look, we found that Kimi K3 devotes 10x more thinking tokens to coding during reasoning than any other model we've seen before Not only that, but it has basically memorized all of the image IDs from Unsplash and, without a web search tool call, can reason about images with a higher accuracy than we've seen from any other model The image and video below are visualizations of its (very long) thinking trace for single-turn generation The resulting website selects images with greater relevance and accuracy than we've ever seen on DesignArena Forgive my all-caps heading, but I am excited about this and wanted you to read it too bc this is pretty gnarly Huge congratulations to the Kimi.ai team for this breakthrough and becoming the 1st-place model on Design Arena!

WE COULD NOT BELIEVE IT WHEN WE SAW THIS We were curious about Kimi K3's massive jump in consumed thinking tokens After taking a closer look, we found that Kimi K3 devotes 10x more thinking tokens to coding during reasoning than any other model we've seen before Not only that, but it has basically memorized all of the image IDs from Unsplash and, without a web search tool call, can reason about images with a higher accuracy than we've seen from any other model The image and video below are visualizations of its (very long) thinking trace for single-turn generation The resulting website selects images with greater relevance and accuracy than we've ever seen on DesignArena Forgive my all-caps heading, but I am excited about this and wanted you to read it too bc this is pretty gnarly Huge congratulations to the Kimi.ai team for this breakthrough and becoming the 1st-place model on Design Arena!

Grace Li

56,633 次观看 • 6 天前