Sensitive content

This media may contain sensitive content.

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。

CVPR 2025 papers pt. 1 - Gaze-LLE Gaze-LLE simplifies gaze target estimation by building on top of a frozen DINOv2 visual foundation model; SOTA performance; open source code and model more papers: ↓ more

SkalskiP

36,304 subscribers

96,057 次观看 • 1 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 条评论

SkalskiP @ CVPR2025 🇺🇸 的头像

SkalskiP @ CVPR2025 🇺🇸1 年前

- paper: - code: - HF demo by @fffiloni:

SkalskiP @ CVPR2025 🇺🇸 的头像

SkalskiP @ CVPR2025 🇺🇸1 年前

traditional gaze target estimation models use complex pipelines with multiple encoders and extra networks for pose or depth, making them heavy and slow to train. Gaze-LLE streamlines this with a single frozen DINOv2 encoder and a simple head prompt to indicate whose gaze to estimate.

SkalskiP @ CVPR2025 🇺🇸 的头像

SkalskiP @ CVPR2025 🇺🇸1 年前

Gaze-LLE achieves state-of-the-art results with only about 2.8M trainable parameters, which is 10–50x fewer than previous methods.

SkalskiP @ CVPR2025 🇺🇸 的头像

SkalskiP @ CVPR2025 🇺🇸1 年前

the heatmaps produced by Gaze-LLE represent the probability that each pixel in the scene is the target of a person’s gaze.

Rainmaker 的头像

Rainmaker2 年前

Here I share an XGBoost model that delivers a 25% CAGR with minimal drawdown on Visa stock. In this free Substack post I share code and commentary for a powerful Machine Learning strategy that delivers powerful returns.

T 的头像

T1 年前

This is already implemented in moondream btw

SkalskiP @ CVPR2025 🇺🇸 的头像

SkalskiP @ CVPR2025 🇺🇸1 年前

I know! I remember @vikhyatk got inspired by it and added gaze target estimation in few days!

Brian Reynolds 的头像

Brian Reynolds1 年前

dont show this to palantir, yikes

Wesxdz 的头像

Wesxdz1 年前

I want to see one of those interviews where the gaze is into the camera.

相关视频

The latest Visual Studio Code release brings auto model selection (preview) - a way to have the best model picked for you based on current capacity and performance. Currently being rolled out to all GitHub Copilot users in Visual Studio Code starting with individuals. Learn more:

The latest Visual Studio Code release brings auto model selection (preview) - a way to have the best model picked for you based on current capacity and performance. Currently being rolled out to all GitHub Copilot users in Visual Studio Code starting with individuals. Learn more:

Visual Studio Code

67,645 次观看 • 10 个月前

Introducing Ψ₀ ( — an open foundation model for universal humanoid loco-manipulation. 🏆 Outperforms GR00T N1.6 by 40%+ overall success rate 📉 Uses only ~10% of the pre-training data 📦 Fully open-source: model, data, code, and deployment pipeline 1/10

Introducing Ψ₀ ( — an open foundation model for universal humanoid loco-manipulation. 🏆 Outperforms GR00T N1.6 by 40%+ overall success rate 📉 Uses only ~10% of the pre-training data 📦 Fully open-source: model, data, code, and deployment pipeline 1/10

Yue Wang

20,173 次观看 • 4 个月前

Tomorrow I'll talk at the #ICRA workshop on "Enhancing human mobility" on recent 3D human estimation works from our group led by Gerard Pons-Moll. And I've released PyTorch training code for NLF, and more tools. Here's a preview of the even stronger upcoming DINOv2-ViTg-based NLF

Tomorrow I'll talk at the #ICRA workshop on "Enhancing human mobility" on recent 3D human estimation works from our group led by Gerard Pons-Moll. And I've released PyTorch training code for NLF, and more tools. Here's a preview of the even stronger upcoming DINOv2-ViTg-based NLF

István Sárándi

12,124 次观看 • 1 年前

Finally! Codellama-70b as Copilot in VSCode! 😱 You can now harness the power of the most advanced code generation model, Code Llama 70B, right in Visual Studio Code with Perplexity This model has outperformed even GPT-4 in code writing, and it's now seamlessly integrated into our editor 🥳 Do you anticipate the emergence of more open-source models that surpass GPT-4?

Finally! Codellama-70b as Copilot in VSCode! 😱 You can now harness the power of the most advanced code generation model, Code Llama 70B, right in Visual Studio Code with Perplexity This model has outperformed even GPT-4 in code writing, and it's now seamlessly integrated into our editor 🥳 Do you anticipate the emergence of more open-source models that surpass GPT-4?

Daniel San

69,499 次观看 • 2 年前

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

🔉 Introducing SAM Audio, the first unified model that isolates any sound from complex audio mixtures using text, visual, or span prompts. We’re sharing SAM Audio with the community, along with a perception encoder model, benchmarks and research papers, to empower others to explore new forms of expression and build applications that were previously out of reach. 🔗 Learn more:

AI at Meta

1,250,268 次观看 • 7 个月前

.Vogent Voicelab is a high-performance API to run top open-source voice models, like Sesame CSM-1B, Dia, and more. Voicelab optimizes inference for each model so you can run them quickly and scalably— and they post-train select models to improve performance and reliability.

.Vogent Voicelab is a high-performance API to run top open-source voice models, like Sesame CSM-1B, Dia, and more. Voicelab optimizes inference for each model so you can run them quickly and scalably— and they post-train select models to improve performance and reliability.

Y Combinator

55,257 次观看 • 1 年前

Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds. Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AI— check it out (more videos, details, and code in the thread):

Today we’re launching our first homegrown AI model: an open source turn detection model for building voice agents. Instead of relying solely on voice activity detection (VAD), which only considers when a user is speaking, our model also considers what has and is being said in the context of a conversation and predicts when a user is finished expressing their thoughts before the agent responds. Conversations with AI voice agents using this new model flow much more naturally without constant interruptions from the AI— check it out (more videos, details, and code in the thread):

LiveKit

126,860 次观看 • 1 年前

Introducing Open TTS Tracker! 🗣️ *sound on* A one-stop shop to track all open access/ source TTS models! Ranging from XTTS to Pheme, OpenVoice to VITS, and more... ⚡ For each model, we compile: 1. Souce-code 2. Checkpoints 3. License 4. Fine-tuning code 5. Languages supported 6. Paper 7. Demo Help us make it more complete! Let's 2024 the year of open TTS models! ❤️

Introducing Open TTS Tracker! 🗣️ sound on A one-stop shop to track all open access/ source TTS models! Ranging from XTTS to Pheme, OpenVoice to VITS, and more... ⚡ For each model, we compile: 1. Souce-code 2. Checkpoints 3. License 4. Fine-tuning code 5. Languages supported 6. Paper 7. Demo Help us make it more complete! Let's 2024 the year of open TTS models! ❤️

Vaibhav (VB) Srivastav

68,037 次观看 • 2 年前

BOOM! Starting today you can use open source frontier LLMs in Visual Studio Code with HF Inference Providers! 🔥 Use your inference credits on SoTA llms like GLM 4.5, Qwen3 Coder, DeepSeek 3.1 and more All of it packaged in one simple extension - try it out today 🤗

BOOM! Starting today you can use open source frontier LLMs in Visual Studio Code with HF Inference Providers! 🔥 Use your inference credits on SoTA llms like GLM 4.5, Qwen3 Coder, DeepSeek 3.1 and more All of it packaged in one simple extension - try it out today 🤗

Vaibhav (VB) Srivastav

41,201 次观看 • 10 个月前

We are now Cult.Repo. The original creators behind the iconic Open Source documentaries (Vue, React, GraphQL) are back together! Honeypot is now called Cult.Repo and is independently-owned. We are on a mission to document the complete history of every major open source language ever created. With 250K subscribers and over 15M views, we're building on our foundation as creators of the acclaimed Open Source Origin Story documentary format. Coming in 2025: Python Software Foundation, Vite ⚡ documentaries and much more. Our independence is core to our mission. We believe the human stories behind open source deserve authentic, in-depth storytelling. Our new model is powered directly by: - Community support from viewers - Sponsorships from organizations that champion open source This transition represents our commitment to independent, meaningful tech storytelling that honours the collaborative spirit of open source itself.

We are now Cult.Repo. The original creators behind the iconic Open Source documentaries (Vue, React, GraphQL) are back together! Honeypot is now called Cult.Repo and is independently-owned. We are on a mission to document the complete history of every major open source language ever created. With 250K subscribers and over 15M views, we're building on our foundation as creators of the acclaimed Open Source Origin Story documentary format. Coming in 2025: Python Software Foundation, Vite ⚡ documentaries and much more. Our independence is core to our mission. We believe the human stories behind open source deserve authentic, in-depth storytelling. Our new model is powered directly by: - Community support from viewers - Sponsorships from organizations that champion open source This transition represents our commitment to independent, meaningful tech storytelling that honours the collaborative spirit of open source itself.

Cult.Repo

70,793 次观看 • 1 年前

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯 It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW! Demo (+ source code) 👇

Xenova

88,747 次观看 • 2 年前

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

The most effective AI systems don't rely on a single model. Frontier models provide state-of-the-art performance for complex tasks, while routers automatically select lightweight, open-source models for simpler jobs to optimize accuracy, latency, and cost. Learn more:

NVIDIA AI

12,152 次观看 • 4 个月前

Don't talk directly to a model. You can make your application 10x more flexible by simply adding one intermediate layer between your code and the model. This is the simplest trick you can use to improve the architecture of whatever you are building.

Don't talk directly to a model. You can make your application 10x more flexible by simply adding one intermediate layer between your code and the model. This is the simplest trick you can use to improve the architecture of whatever you are building.

Santiago

88,884 次观看 • 3 个月前

🆕 Kimi.ai's Kimi K2.7 Code is now generally available in GitHub Copilot. This is the first open-weight model offered as a selectable option in the Copilot model picker. 🎉 Early testing shows Kimi K2.7 is a lower-cost option with strong performance comparable to highly popular frontier models. Try it out now in Visual Studio Code and look out for it in more GitHub Copilot surfaces. 👇

🆕 Kimi.ai's Kimi K2.7 Code is now generally available in GitHub Copilot. This is the first open-weight model offered as a selectable option in the Copilot model picker. 🎉 Early testing shows Kimi K2.7 is a lower-cost option with strong performance comparable to highly popular frontier models. Try it out now in Visual Studio Code and look out for it in more GitHub Copilot surfaces. 👇

GitHub

194,652 次观看 • 14 天前

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

Researchers at Meta recently shared MAGNeT, a single non-autoregressive transformer model for text-to-music & text-to-sound generation capable of generating audio on-par with the quality of SOTA models — at 7x the speed. MAGNeT is open source as part of AudioCraft. Hear audio samples and get more details on this work ➡️

AI at Meta

122,001 次观看 • 2 年前

If you want to learn more about model books, and how to go about building them in a way proven to be effective, this newsletter is for you. Building Model Books: What, Why and How (Step by Step) Clement Ang on the discretionary trader’s edge Published Saturday, 15 November 2025, 10 am (GMT) on TTRH. 🔗

If you want to learn more about model books, and how to go about building them in a way proven to be effective, this newsletter is for you. Building Model Books: What, Why and How (Step by Step) Clement Ang on the discretionary trader’s edge Published Saturday, 15 November 2025, 10 am (GMT) on TTRH. 🔗

Kyna Kosling

66,345 次观看 • 8 个月前

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

🚀 Meta FAIR is releasing several new research artifacts on our road to advanced machine intelligence (AMI). These latest advancements are transforming our understanding of perception. 1️⃣ Meta Perception Encoder: A large-scale vision encoder that excels across several image & video tasks. 2️⃣ Meta Perception Language Model: A fully open & reproducible vision-language model designed to tackle visual recognition tasks. 3️⃣ Meta Locate 3D: An end-to-end model for accurate object localization in 3D environments. 4️⃣ Releasing model weights for our 8B-parameter Dynamic Byte Latent Transformer, an alternative to traditional tokenization methods with the potential to redefine the standards for language model efficiency and reliability. 5️⃣Collaborative Reasoner: A framework for evaluating & improving collaborative reasoning skills in language models. Download the code, datasets, and research papers and learn more about how these artifacts are paving the way for more efficient and accurate AI systems.➡️

AI at Meta

163,290 次观看 • 1 年前

Introducing Tahoe-x1 (Tx1) by Tahoe Therapeutics. A 3-billion-parameter, single-cell foundation model that learns unified representations of genes, cells, and drugs, achieving state-of-the-art performance across cancer-relevant cell biology benchmarks, open-sourced on Hugging Face. 🧵

Introducing Tahoe-x1 (Tx1) by Tahoe Therapeutics. A 3-billion-parameter, single-cell foundation model that learns unified representations of genes, cells, and drugs, achieving state-of-the-art performance across cancer-relevant cell biology benchmarks, open-sourced on Hugging Face. 🧵

Nima Alidoust

171,805 次观看 • 8 个月前

Turn any world model from World Labs into a multi-user space for exploration and collaboration with FRAME. Voice chat, embodied AI agents, and tons more you can layer on top of the model foundation. This took all of 10 seconds to get going. The metaverse is so back. 😄

Turn any world model from World Labs into a multi-user space for exploration and collaboration with FRAME. Voice chat, embodied AI agents, and tons more you can layer on top of the model foundation. This took all of 10 seconds to get going. The metaverse is so back. 😄

Gabriel Baker

21,608 次观看 • 9 个月前

HunyuanImage 3.0 is officially here. It's the first open-source model with industrial-grade native multimodal architecture and delivers instant, high-quality visual content for every designer and content creator. Watch this quick showcase to see its performance on generating intricate text, detailed comics, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

HunyuanImage 3.0 is officially here. It's the first open-source model with industrial-grade native multimodal architecture and delivers instant, high-quality visual content for every designer and content creator. Watch this quick showcase to see its performance on generating intricate text, detailed comics, and more. 👉🏻Try it now: 🔗GitHub: 🤗Hugging Face:

Tencent Hy

31,048 次观看 • 9 个月前