Загрузка видео...

Не удалось загрузить видео

На главную

Voice AI has an evaluation problem. Models look strong on public benchmarks, then collapse on real-world audio. Introducing a recipe-driven evaluation framework for low-resource languages, real-world audio, and production failure modes. Details ↓

psdnai's profile picture

Poseidon

25,810 subscribers

33,978 просмотров • 1 месяц назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:
0:14

🔥Spatial intelligence requires world generation, and now we have the first comprehensive evaluation benchmark📏 for it! Introducing WorldScore: Unifying evaluation for 3D, 4D, and video models on world generation! 🧵1/7 Web: arxiv:

Hong-Xing (Koven) Yu

66,701 просмотров • 1 год назад

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵
2:39

New research from BlackForestLabsAI - Unofficial 🥳 Meet Self-Flow: our self-supervised framework for image, audio, video & world models 🤖 Do generative models really need DINO to learn strong representations? We propose teaching them directly via a joint framework instead 🧵

Hila Chefer

67,648 просмотров • 3 месяцев назад

AI was trained on the open internet, but the data that matters most lives in the real world. Introducing early access to Numo, an app built to collect the next generation of AI training data. Starting with voice data collection in Bengali, Hindi, Tamil, and Telugu. Details ↴
0:19

AI was trained on the open internet, but the data that matters most lives in the real world. Introducing early access to Numo, an app built to collect the next generation of AI training data. Starting with voice data collection in Bengali, Hindi, Tamil, and Telugu. Details ↴

Poseidon

1,240,151 просмотров • 2 месяцев назад

Advice for AI engineers 💡 A small Audio Language Model transcribes audio in real-time on your device, without internet connection or cloud costs. For example, LFM2-Audio-1.5B by ↓
0:14

Advice for AI engineers 💡 A small Audio Language Model transcribes audio in real-time on your device, without internet connection or cloud costs. For example, LFM2-Audio-1.5B by ↓

Pau Labarta Bajo

31,993 просмотров • 7 месяцев назад

Introducing $SAHARA — the native utility token of Sahara AI. Designed for real-world function, $SAHARA powers a new economic model for AI. One that is collaborative, open, and built to reward real contributors. Utility, distribution, and claim details below 🧵👇
0:17

Introducing $SAHARA — the native utility token of Sahara AI. Designed for real-world function, $SAHARA powers a new economic model for AI. One that is collaborative, open, and built to reward real contributors. Utility, distribution, and claim details below 🧵👇

Sahara AI 🔆

845,494 просмотров • 1 год назад

To be honest. Evaluation in robotics has always been a challenge unlike in vision or language: not enough DATA, not enough TASKS, and too much reliance on FIXED benchmarks. PlayGround pushes us beyond static datasets and predefined tasks, moving robotics evaluation into the era of dynamic evaluation in structure physical domain one at a time. *Can't wait to see how the community scale on this!
0:11

To be honest. Evaluation in robotics has always been a challenge unlike in vision or language: not enough DATA, not enough TASKS, and too much reliance on FIXED benchmarks. PlayGround pushes us beyond static datasets and predefined tasks, moving robotics evaluation into the era of dynamic evaluation in structure physical domain one at a time. *Can't wait to see how the community scale on this!

Jiafei Duan

10,506 просмотров • 2 месяцев назад

Bengali is spoken by ~280M people. Yet when we tested frontier models on Bengali transcript review, they rarely agreed on what was incorrect. The results point to a broader challenge for AI in low-resource languages ↓
0:16

Bengali is spoken by ~280M people. Yet when we tested frontier models on Bengali transcript review, they rarely agreed on what was incorrect. The results point to a broader challenge for AI in low-resource languages ↓

Poseidon

15,940 просмотров • 13 дней назад

Introducing Find the best local models based on real data 1. People run and submit benchmarks 2. Stats aggregated over models / devices 3. Find the best model for you `npx whatcanirun`, fully open-source
0:16

Introducing Find the best local models based on real data 1. People run and submit benchmarks 2. Stats aggregated over models / devices 3. Find the best model for you `npx whatcanirun`, fully open-source

⁵⁄₉

133,355 просмотров • 3 месяцев назад

Announcing Bespoke-MiniChart-7B, a new SOTA in chart understanding for models of comparable size on seven benchmarks, on par with Gemini-1.5-Pro and Claude-3.5! 🚀 Beyond its real-world applications, chart understanding is a good challenging problem for VLMs, since it requires both mathematical as well as visual reasoning. 1/n🧵
0:14

Announcing Bespoke-MiniChart-7B, a new SOTA in chart understanding for models of comparable size on seven benchmarks, on par with Gemini-1.5-Pro and Claude-3.5! 🚀 Beyond its real-world applications, chart understanding is a good challenging problem for VLMs, since it requires both mathematical as well as visual reasoning. 1/n🧵

Bespoke Labs

19,871 просмотров • 1 год назад

Dubbing is dead Introducing Instant AI video dubbing This works by taking the actor/audio from the original video and fine-tuning a voice model. Then overlaps the AI generated dubbed audio onto the original video. This one is huge for creators 🧵
0:19

Dubbing is dead Introducing Instant AI video dubbing This works by taking the actor/audio from the original video and fine-tuning a voice model. Then overlaps the AI generated dubbed audio onto the original video. This one is huge for creators 🧵

Linus ✦ Ekenstam

358,191 просмотров • 2 лет назад

NEWS: Grok dominates real-world voice AI benchmarks 🔥 τ-voice Bench 🥇 • 🏆 #1 Overall → 67.3% • 🏆 #1 Retail → 62.3% • 🏆 #1 Airline → 66% • 🏆 #1 Telecom → 73.7%
0:19

NEWS: Grok dominates real-world voice AI benchmarks 🔥 τ-voice Bench 🥇 • 🏆 #1 Overall → 67.3% • 🏆 #1 Retail → 62.3% • 🏆 #1 Airline → 66% • 🏆 #1 Telecom → 73.7%

DogeDesigner

605,049 просмотров • 2 месяцев назад

How can robots reliably place objects in diverse real-world tasks? 🤖🔍 Placement is tough—objects vary in shape and placement modes (such as stacking, hanging, and insertion), making it a challenging problem. We introduce AnyPlace, a two-stage method trained purely on synthetic data to predict diverse placement poses of unseen objects for real-world tasks. Read on for more👇
0:19

How can robots reliably place objects in diverse real-world tasks? 🤖🔍 Placement is tough—objects vary in shape and placement modes (such as stacking, hanging, and insertion), making it a challenging problem. We introduce AnyPlace, a two-stage method trained purely on synthetic data to predict diverse placement poses of unseen objects for real-world tasks. Read on for more👇

Animesh Garg

24,662 просмотров • 1 год назад

Introducing Super Gacha on Base The shake-to-pull machine for real-world collectibles, fully onchain. Powered by Chainlink VRF. Shake here: Details & launching events below 👇
0:12

Introducing Super Gacha on Base The shake-to-pull machine for real-world collectibles, fully onchain. Powered by Chainlink VRF. Shake here: Details & launching events below 👇

Raflux

12,690 просмотров • 22 дней назад

4/ Finally, I think future iterations of models like Genie 3 will have a significant impact on accelerating robotics and real-world AI. Here's a glimpse of what that could look like: an agent pursuing a goal (go to tomatoes) in an environment generated by our model.
0:13

4/ Finally, I think future iterations of models like Genie 3 will have a significant impact on accelerating robotics and real-world AI. Here's a glimpse of what that could look like: an agent pursuing a goal (go to tomatoes) in an environment generated by our model.

Agrim Gupta

21,958 просмотров • 10 месяцев назад

🎤ElevenLabs v3 is now available on fal! The most expressive Text-to-Speech model with dialogue mode, multi-speaker support, and enhanced voice control across 70+ languages. Create audio that feels real, natural & expressive!
0:10

🎤ElevenLabs v3 is now available on fal! The most expressive Text-to-Speech model with dialogue mode, multi-speaker support, and enhanced voice control across 70+ languages. Create audio that feels real, natural & expressive!

fal

44,525 просмотров • 10 месяцев назад

From the outside it looks like a car, but on the inside, it’s the most intelligent real-world AI driving robot on wheels the world has ever seen
0:14

From the outside it looks like a car, but on the inside, it’s the most intelligent real-world AI driving robot on wheels the world has ever seen

Teslaconomics

31,339 просмотров • 3 месяцев назад

India can’t be left behind in AI. कृत्रिम has accelerated efforts to develop world class AI. As first step, our cloud now has DeepSeek models live, hosted on Indian servers. Pricing lowest in the world Details on our AI lab, SOTA model and research progress, open source drops on 4th Feb!
0:12

India can’t be left behind in AI. कृत्रिम has accelerated efforts to develop world class AI. As first step, our cloud now has DeepSeek models live, hosted on Indian servers. Pricing lowest in the world Details on our AI lab, SOTA model and research progress, open source drops on 4th Feb!

Bhavish Aggarwal

379,427 просмотров • 1 год назад

just made it possible to evaluate generalist robotics models like Octo at 60-100x real world evaluation speeds via gpu simulation and rendering (~10x faster than original cpu sim code). All videos below are from our open source ManiSkill GPU sim!
0:12

just made it possible to evaluate generalist robotics models like Octo at 60-100x real world evaluation speeds via gpu simulation and rendering (~10x faster than original cpu sim code). All videos below are from our open source ManiSkill GPU sim!

Stone Tao

13,456 просмотров • 1 год назад

Introducing Aniportrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
0:10

Introducing Aniportrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Halim Alrasihi

14,545 просмотров • 2 лет назад