Загрузка видео...

Не удалось загрузить видео

На главную

Machine Mental Imagery Empower Multimodal Reasoning with Latent Visual Tokens

_akhaliq's profile picture

AK

506,060 subscribers

43,498 просмотров • 1 год назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 4

Фото профиля AK
AK1 год назад

discuss with author:

Фото профиля Tablo | AI Meeting Notes
Tablo | AI Meeting Notes1 год назад

Multimodal reasoning's next frontier? Love seeing this exploration.

Фото профиля Gaëtan
Gaëtan1 год назад

cool

Фото профиля Himanshu Kumar
Himanshu Kumar1 год назад

Intriguing, could this unlock creativity we didn't know machines had?

Похожие видео

Seeing, Listening, Remembering, and Reasoning A Multimodal Agent with Long-Term Memory
3:57

Seeing, Listening, Remembering, and Reasoning A Multimodal Agent with Long-Term Memory

AK

19,923 просмотров • 11 месяцев назад

Multimodal Reasoning AI Agents are here with Gemini 2.0 Flash Thinking I built a multimodal AI agent that can reason and understand images using gemini flash reasoning LLM. 100% Opensource Code with step-by-step tutorial.
0:20

Multimodal Reasoning AI Agents are here with Gemini 2.0 Flash Thinking I built a multimodal AI agent that can reason and understand images using gemini flash reasoning LLM. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

36,596 просмотров • 1 год назад

Empower powerful research and content creation with our new multimodal Gemini 2.5 researcher, built together with LangChain.
14:03

Empower powerful research and content creation with our new multimodal Gemini 2.5 researcher, built together with LangChain.

Google AI Developers

63,325 просмотров • 1 год назад

What if robots could think longer on harder problems without saying a single word?🤔 We introduce RD-VLA (Recurrent-Depth VLA): a latent, iterative reasoning architecture for robot control. ❌No Chain-of-Thought tokens. ❌No extra memory overhead. ✅Just reasoning—directly in latent space. 🧠🤖 Project page: 👇🧵
1:22

What if robots could think longer on harder problems without saying a single word?🤔 We introduce RD-VLA (Recurrent-Depth VLA): a latent, iterative reasoning architecture for robot control. ❌No Chain-of-Thought tokens. ❌No extra memory overhead. ✅Just reasoning—directly in latent space. 🧠🤖 Project page: 👇🧵

Jiafei Duan

13,833 просмотров • 5 месяцев назад

co-seeing art with machine: an interactive demo where i browse the visual responses of a multimodal llm to prompts about the painting, from “who’s in here?” and to “what’s unusual about this painting?” the model replies not just with words, but with visual annotations as well.
0:24

co-seeing art with machine: an interactive demo where i browse the visual responses of a multimodal llm to prompts about the painting, from “who’s in here?” and to “what’s unusual about this painting?” the model replies not just with words, but with visual annotations as well.

Kat ⊷ the Poet Engineer

37,359 просмотров • 1 год назад

Gemini 2.5 is driving new advancements in robotics with its strong coding, spatial reasoning, and multimodal capabilities. 🦾
0:20

Gemini 2.5 is driving new advancements in robotics with its strong coding, spatial reasoning, and multimodal capabilities. 🦾

Google AI Developers

36,119 просмотров • 1 год назад

We introduce HumanOmniV2, an omni-modal model designed to address two core problems in multimodal reasoning: insufficient global context understanding and the shortcut problem. By analyzing visual, auditory, and textual signals, the model performs deep reasoning on complex human intentions, emotions, and social interactions.
0:55

We introduce HumanOmniV2, an omni-modal model designed to address two core problems in multimodal reasoning: insufficient global context understanding and the shortcut problem. By analyzing visual, auditory, and textual signals, the model performs deep reasoning on complex human intentions, emotions, and social interactions.

Tongyi Lab

1,221,672 просмотров • 1 год назад

Demis Hassabis on the next 12 Months: - Full multimodal convergence: Models like Gemini will seamlessly take in and output text, images, audio, and video, with cross-pollination that boosts reasoning + creativity. - Breakthrough visual intelligence: Image models like Nano Banana Pro will produce highly accurate infographics and show near-human visual understanding. - Language + video fusion: Video models integrated with LLMs unlock richer analysis, storytelling, and step-by-step visual reasoning. - World models go mainstream like Genie 3 - Agents become reliable
1:26

Demis Hassabis on the next 12 Months: - Full multimodal convergence: Models like Gemini will seamlessly take in and output text, images, audio, and video, with cross-pollination that boosts reasoning + creativity. - Breakthrough visual intelligence: Image models like Nano Banana Pro will produce highly accurate infographics and show near-human visual understanding. - Language + video fusion: Video models integrated with LLMs unlock richer analysis, storytelling, and step-by-step visual reasoning. - World models go mainstream like Genie 3 - Agents become reliable

Chubby♨️

89,236 просмотров • 7 месяцев назад

Vision-language models (VLMs) can see well, but they struggle to reason. In this episode, Antonia Wüst (PhD researcher, TU Darmstadt) explains how combining VLMs with program synthesis yields more reliable visual reasoning, with fewer tokens than chain-of-thought.
0:46

Vision-language models (VLMs) can see well, but they struggle to reason. In this episode, Antonia Wüst (PhD researcher, TU Darmstadt) explains how combining VLMs with program synthesis yields more reliable visual reasoning, with fewer tokens than chain-of-thought.

Ndea

22,130 просмотров • 5 месяцев назад

The GeoAI Python package now supports interactive segmentation of remote sensing imagery with the Moondream AI Vision Language Models (VLMs), which provides powerful and efficient visual reasoning. A great alternative to Meta's SAM 3. GitHub: Notebook example: #GeoAI #geospatial #AI #opensource
0:59

The GeoAI Python package now supports interactive segmentation of remote sensing imagery with the Moondream AI Vision Language Models (VLMs), which provides powerful and efficient visual reasoning. A great alternative to Meta's SAM 3. GitHub: Notebook example: #GeoAI #geospatial #AI #opensource

Qiusheng Wu

11,655 просмотров • 7 месяцев назад

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health.
2:00

Multimodal reasoning with Phi-4-reasoning-vision, new work on scaling LLM inference, benchmarking AI agents in network operations, cinematic video generation, adaptive evaluation for LLMs, and using AI to improve individual and population health.

Microsoft Research

11,672 просмотров • 4 месяцев назад

Meta presents TUNA Taming Unified Visual Representations for Native Unified Multimodal Models
1:11

Meta presents TUNA Taming Unified Visual Representations for Native Unified Multimodal Models

AK

32,717 просмотров • 7 месяцев назад

🚨 MiniCPM-o 2.6, an 8B multimodal LLM, outperforms GPT-4o, Gemini 1.5 Pro, and Sonnet in visual (70.2 avg on OpenCompass, 1.8M pixel - 1344 x 1344), speech (bilingual realtime, beats GPT-4o-realtime in ASR/STT), with 75% fewer vision tokens, supporting 30+ languages 🔥
6:40

🚨 MiniCPM-o 2.6, an 8B multimodal LLM, outperforms GPT-4o, Gemini 1.5 Pro, and Sonnet in visual (70.2 avg on OpenCompass, 1.8M pixel - 1344 x 1344), speech (bilingual realtime, beats GPT-4o-realtime in ASR/STT), with 75% fewer vision tokens, supporting 30+ languages 🔥

Vaibhav (VB) Srivastav

42,009 просмотров • 1 год назад

🚀 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
2:10

🚀 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 просмотров • 8 месяцев назад

Start building with Gemini 3 Pro, our most intelligent model with state-of-the-art reasoning and complex multimodal understanding, as well as powerful agentic and vibe coding capabilities. See more below:
0:20

Start building with Gemini 3 Pro, our most intelligent model with state-of-the-art reasoning and complex multimodal understanding, as well as powerful agentic and vibe coding capabilities. See more below:

Google AI Developers

104,898 просмотров • 7 месяцев назад

1.🚀 Baidu’s ERNIE 4.5 VL-28B-A3B-Thinking — an open-source MoE beast. With just 3B active params, it delivers SOTA multimodal reasoning: visual logic (MathVista 72.6), grounding, tool-calling, and more. The full family spans 12 models (0.3B → 424B). 🔗 Try it here: 💬 What’s your favorite “Thinking Mode” trick? #ERNIE45 #MultimodalAI
0:22

1.🚀 Baidu’s ERNIE 4.5 VL-28B-A3B-Thinking — an open-source MoE beast. With just 3B active params, it delivers SOTA multimodal reasoning: visual logic (MathVista 72.6), grounding, tool-calling, and more. The full family spans 12 models (0.3B → 424B). 🔗 Try it here: 💬 What’s your favorite “Thinking Mode” trick? #ERNIE45 #MultimodalAI

Helena AI

53,547 просмотров • 6 месяцев назад