Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

📢 Introducing DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models Compared to vanilla DPO, we improve paired data construction and preference label granularity, leading to better visual quality and motion strength with only 1/3 of the data. 🧵

Ziyi Wu

1,242 subscribers

35,402 görüntüleme • 1 yıl önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

Our course recommendation of the day is “Post-training of LLMs, ” where you’ll learn how to customize pre-trained language models using Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL). You'll learn when to use each method, how to curate training data, and implement them in code to shape model behavior effectively. Enroll here:

DeepLearning.AI

29,369 görüntüleme • 8 ay önce

In case you missed it, we recently launched "Post-training of LLMs," a short course where you'll: ✅ Understand when and why to use post-training methods like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning. ✅ Learn the concepts underlying the three post-training methods of SFT, DPO, and Online RL, their common use-cases, and how to curate high-quality data to effectively train a model using each method. ✅ Download a pre-trained model and implement post-training pipelines to turn a base model into an instruct model, change the identity of a chat assistant, and improve a model’s math capabilities. Learn more and enroll for free:

In case you missed it, we recently launched "Post-training of LLMs," a short course where you'll: ✅ Understand when and why to use post-training methods like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning. ✅ Learn the concepts underlying the three post-training methods of SFT, DPO, and Online RL, their common use-cases, and how to curate high-quality data to effectively train a model using each method. ✅ Download a pre-trained model and implement post-training pipelines to turn a base model into an instruct model, change the identity of a chat assistant, and improve a model’s math capabilities. Learn more and enroll for free:

DeepLearning.AI

16,746 görüntüleme • 11 ay önce

Loopy Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency paper page: With the introduction of diffusion-based video generation techniques, audio-conditioned human video generation has recently achieved significant breakthroughs in both the naturalness of motion and the synthesis of portrait details. Due to the limited control of audio signals in driving human motion, existing methods often add auxiliary spatial signals to stabilize movements, which may compromise the naturalness and freedom of motion. In this paper, we propose an end-to-end audio-only conditioned video diffusion model named Loopy. Specifically, we designed an inter- and intra-clip temporal module and an audio-to-latents module, enabling the model to leverage long-term motion information from the data to learn natural motion patterns and improving audio-portrait movement correlation. This method removes the need for manually specified spatial motion templates used in existing methods to constrain motion during inference. Extensive experiments show that Loopy outperforms recent audio-driven portrait diffusion models, delivering more lifelike and high-quality results across various scenarios.

AK

128,797 görüntüleme • 1 yıl önce

AI only exists today because it is trained on real data. The better the data input, The better the AI output. We capture incredibly high-quality raw data of real humans, in 3D, from all angles. You do the Math ✍🏻 Our data can vastly improve and expand the capabilities of AI

AI only exists today because it is trained on real data. The better the data input, The better the AI output. We capture incredibly high-quality raw data of real humans, in 3D, from all angles. You do the Math ✍🏻 Our data can vastly improve and expand the capabilities of AI

Metahero.io

24,523 görüntüleme • 2 yıl önce

Language following is a tough problem for VLAs: while these models can follow complex language, in practice getting datasets that enable language following is hard. We developed a method to counterfactually and automatically label data to improve language following! 🧵👇

Language following is a tough problem for VLAs: while these models can follow complex language, in practice getting datasets that enable language following is hard. We developed a method to counterfactually and automatically label data to improve language following! 🧵👇

Sergey Levine

44,176 görüntüleme • 9 ay önce

Introducing the #WELL3Ring: Elevating Health Data to On-Chain Assets🔘 At #WELL3, we are leading a transformative shift in how health data is valued and monetized. We cordially invite our #WELLID holders to be the first to experience the benefits of this DePIN wearable. By donning the WELL3 Ring and sharing your health data, you will gain access to unlimited and exclusive rewards🧵

Introducing the #WELL3Ring: Elevating Health Data to On-Chain Assets🔘 At #WELL3, we are leading a transformative shift in how health data is valued and monetized. We cordially invite our #WELLID holders to be the first to experience the benefits of this DePIN wearable. By donning the WELL3 Ring and sharing your health data, you will gain access to unlimited and exclusive rewards🧵

WELL3

223,003 görüntüleme • 2 yıl önce

It is really hard to get robot policies that are both precise (small margins for error) and general (robust to env variations). We just released ViSk, where skin sensing is used to train fine-grained policies with ~1 hour of data. Below is a single-take video.

It is really hard to get robot policies that are both precise (small margins for error) and general (robust to env variations). We just released ViSk, where skin sensing is used to train fine-grained policies with ~1 hour of data. Below is a single-take video.

Lerrel Pinto

17,040 görüntüleme • 1 yıl önce

🎆Chainbase is building the largest omnichain data network to provide high-quality data for the AGI era. Just like Oracle to Defi, Data to AI We aim to create a decentralized data economy and enhance the crypto world with advanced AI capabilities, where anyone can participate, contribute, and be incentivized. Explore the unique network features with us.🧵👇

🎆Chainbase is building the largest omnichain data network to provide high-quality data for the AGI era. Just like Oracle to Defi, Data to AI We aim to create a decentralized data economy and enhance the crypto world with advanced AI capabilities, where anyone can participate, contribute, and be incentivized. Explore the unique network features with us.🧵👇

Chainbase (💜,💛)

340,649 görüntüleme • 1 yıl önce

Can LLMs invent better ways to train LLMs? At Sakana AI, we’re pioneering AI-driven methods to automate AI research and discovery. We’re excited to release DiscoPOP: a new SOTA preference optimization algorithm that was discovered and written by an LLM! Our method leverages LLMs to propose and implement new preference optimization algorithms. We then train models with those algorithms and evaluate their performance, providing feedback to the LLM. By repeating this process for multiple generations in an evolutionary loop, the LLM discovers many highly-performant and novel preference optimization objectives! Paper: GitHub: Model: We proudly collaborated with the University of Oxford (Foerster Lab for AI Research) and Cambridge University (Mihaela van der Schaar) on this groundbreaking project. Looking ahead, we envision a future where AI-driven research reduces the need for extensive human intervention and computational resources. This will accelerate scientific discoveries and innovation, pushing the boundaries of what AI can achieve.

Can LLMs invent better ways to train LLMs? At Sakana AI, we’re pioneering AI-driven methods to automate AI research and discovery. We’re excited to release DiscoPOP: a new SOTA preference optimization algorithm that was discovered and written by an LLM! Our method leverages LLMs to propose and implement new preference optimization algorithms. We then train models with those algorithms and evaluate their performance, providing feedback to the LLM. By repeating this process for multiple generations in an evolutionary loop, the LLM discovers many highly-performant and novel preference optimization objectives! Paper: GitHub: Model: We proudly collaborated with the University of Oxford (Foerster Lab for AI Research) and Cambridge University (Mihaela van der Schaar) on this groundbreaking project. Looking ahead, we envision a future where AI-driven research reduces the need for extensive human intervention and computational resources. This will accelerate scientific discoveries and innovation, pushing the boundaries of what AI can achieve.

Sakana AI

555,782 görüntüleme • 2 yıl önce

Introducing 𝐃𝐫𝐞𝐚𝐦𝐆𝐞𝐧! We got humanoid robots to perform totally new 𝑣𝑒𝑟𝑏𝑠 in new environments through video world models. We believe video world models will solve the data problem in robotics. Bringing the paradigm of scaling human hours to GPU hours. Quick 🧵

Introducing 𝐃𝐫𝐞𝐚𝐦𝐆𝐞𝐧! We got humanoid robots to perform totally new 𝑣𝑒𝑟𝑏𝑠 in new environments through video world models. We believe video world models will solve the data problem in robotics. Bringing the paradigm of scaling human hours to GPU hours. Quick 🧵

Joel Jang

117,285 görüntüleme • 1 yıl önce

Introducing OlmoEarth 🌍, state-of-the-art AI foundation models paired with ready-to-use open infrastructure to turn Earth data into clear, up-to-date insights within hours—not years.

Introducing OlmoEarth 🌍, state-of-the-art AI foundation models paired with ready-to-use open infrastructure to turn Earth data into clear, up-to-date insights within hours—not years.

Ai2

680,357 görüntüleme • 7 ay önce

(1/12) Introducing Kite AI: a foundational AI layer to open the world to decentralized intelligence. Built by the team behind ZettaBlock, today we are launching to unlock fair access to essential AI assets: data, models and agents for all. Here's how. 🧵👇

(1/12) Introducing Kite AI: a foundational AI layer to open the world to decentralized intelligence. Built by the team behind ZettaBlock, today we are launching to unlock fair access to essential AI assets: data, models and agents for all. Here's how. 🧵👇

KITE AI

3,416,599 görüntüleme • 1 yıl önce

Mecka is excited to power EgoVerse: a growing ecosystem for robot learning from egocentric human data Proven across 4 leading research labs, EgoVerse data consistently boosts robot performance We release the tools for anyone to collect data, inference/train, and contribute! 🧵

Mecka is excited to power EgoVerse: a growing ecosystem for robot learning from egocentric human data Proven across 4 leading research labs, EgoVerse data consistently boosts robot performance We release the tools for anyone to collect data, inference/train, and contribute! 🧵

Josh

101,985 görüntüleme • 2 ay önce

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

What if robots could improve themselves by learning from their own failures in the real-world? Introducing 𝗣𝗟𝗗 (𝗣𝗿𝗼𝗯𝗲, 𝗟𝗲𝗮𝗿𝗻, 𝗗𝗶𝘀𝘁𝗶𝗹𝗹) — a recipe that enables Vision-Language-Action (VLA) models to self-improve for high-precision manipulation tasks. PLD couples real-world residual reinforcement learning with standard supervised fine-tuning — letting robots discover, recover, and distill their own data flywheel. Quick 🧵

Wenli Xiao

184,496 görüntüleme • 7 ay önce

Introducing FoundationMotion. A large-scale, video-derived motion annotation dataset & auto-labeling pipeline + advanced models for motion understanding. Fully open-source: code, datasets, and models, free to use and build on. Understanding motion is core to physical reasoning, yet today’s leading models still struggle with simple spatial actions like “turn right” or “move up” or “flip the toast” - mainly due to the lack of large, fine-grained motion datasets. We present FoundationMotion, a fully automated pipeline that: • detects & tracks objects in videos • extracts trajectories • uses LLMs + frames to generate rich motion captions & QA pairs → creating large-scale, high-quality motion datasets at scale. After fine-tuning the open-source models Qwen and NVILA on our annotations, these models now outperform the closed-source Gemini-3-Flash and GPT-5.1 on spatial understanding tasks across autonomous driving, robotics, and everyday scenarios. 📜Paper: 🌐Webpage: 💻 Code: 🕸️Model: 📊 Dataset: 👉 Interactive Demo: Let’s move research forward together. FoundationMotion is also referred to as Wolf V2 🐺, the second chapter in the Wolf series:

Introducing FoundationMotion. A large-scale, video-derived motion annotation dataset & auto-labeling pipeline + advanced models for motion understanding. Fully open-source: code, datasets, and models, free to use and build on. Understanding motion is core to physical reasoning, yet today’s leading models still struggle with simple spatial actions like “turn right” or “move up” or “flip the toast” - mainly due to the lack of large, fine-grained motion datasets. We present FoundationMotion, a fully automated pipeline that: • detects & tracks objects in videos • extracts trajectories • uses LLMs + frames to generate rich motion captions & QA pairs → creating large-scale, high-quality motion datasets at scale. After fine-tuning the open-source models Qwen and NVILA on our annotations, these models now outperform the closed-source Gemini-3-Flash and GPT-5.1 on spatial understanding tasks across autonomous driving, robotics, and everyday scenarios. 📜Paper: 🌐Webpage: 💻 Code: 🕸️Model: 📊 Dataset: 👉 Interactive Demo: Let’s move research forward together. FoundationMotion is also referred to as Wolf V2 🐺, the second chapter in the Wolf series:

Boyi Li

66,637 görüntüleme • 5 ay önce

💡Why Vana? “Ultimately, AI models are only as good as their training data. So if you want to build the best AI, you need the best data.” shares the vision behind Vana’s mission, centered on DataDAOs that aggregate specific datasets, reward data owners for their contributions and level up AI models with high-quality data🏆

💡Why Vana? “Ultimately, AI models are only as good as their training data. So if you want to build the best AI, you need the best data.” shares the vision behind Vana’s mission, centered on DataDAOs that aggregate specific datasets, reward data owners for their contributions and level up AI models with high-quality data🏆

vana

108,354 görüntüleme • 1 yıl önce

1/N Most Vision-Language-Action models need tons of data for finetuning, and still fail for new objects and instructions. Introducing OTTER, a lightweight, easy-to-train model that uses text-aware visual features to nail unseen tasks out of the box! Here's how it works 👇

1/N Most Vision-Language-Action models need tons of data for finetuning, and still fail for new objects and instructions. Introducing OTTER, a lightweight, easy-to-train model that uses text-aware visual features to nail unseen tasks out of the box! Here's how it works 👇

Fangchen Liu

68,288 görüntüleme • 1 yıl önce

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

AK

32,840 görüntüleme • 2 yıl önce

DPO Debate: Is RL needed for RLHF? All things as we cannot settle if DPO or RL is better. At least it is a good exercise. 1. Derivations in the DPO paper. Hint, the authors are good at math 2. cDPO, IPO, and related equations 3. Speculation on potential oddities of DPO vs RL 4. Reminders on the state of open RLHF tldr: we have more limitations with data and tooling and evaluation than optimizer choice Slides: Recent blog post of mine on DPO (more next Wed.): DPO Paper: On youtube:

DPO Debate: Is RL needed for RLHF? All things as we cannot settle if DPO or RL is better. At least it is a good exercise. 1. Derivations in the DPO paper. Hint, the authors are good at math 2. cDPO, IPO, and related equations 3. Speculation on potential oddities of DPO vs RL 4. Reminders on the state of open RLHF tldr: we have more limitations with data and tooling and evaluation than optimizer choice Slides: Recent blog post of mine on DPO (more next Wed.): DPO Paper: On youtube:

Nathan Lambert

100,016 görüntüleme • 2 yıl önce