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。

Adding vision to a language model is more than one extra modality. With large images or long video, the vision encoder can use more compute than the language model itself, so efficient models need a different design. Our VLM team, including ryan, Tianshu Yu, Sina Semnani, and Sam Stevens,... show more

Liquid AI

46,252 subscribers

11,633 次观看 • 2 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

19 条评论

Joshua Timothy 的头像

Joshua Timothy2 天前

@rshubert98 @TianshuYu6 This VLM is so good!

luis 的头像

luis2 天前

@rshubert98 @TianshuYu6 @Presidentlin

Humayun 的头像

Humayun2 天前

@rshubert98 @TianshuYu6 ran d1 on a plain cpu box and loved it, vision next please

Majsans bästa kusin 的头像

Majsans bästa kusin1 天前

@rshubert98 @TianshuYu6 You guys are a gang to watch

K4Rambo 的头像

K4Rambo2 天前

@rshubert98 @TianshuYu6 The Liquid team did a really good job. The model's capability far exceeds what previous 1.7B and 2B vision models could do. Huge success! You guys are on the frontier of making Artificial Intelligence free for everyone.

Rithesh 的头像

Rithesh1 天前

@rshubert98 @TianshuYu6 Tested and created this video

Elyria l4 的头像

Elyria l42 天前

@rshubert98 @TianshuYu6 @grok so does this latest lfm3 latest vision encoder can stream higher than 30fps or real time video understanding and able to identify events in industrial applications than general vlms ? General vlms down sample native rate and lose context and how come this can be different?

Veera Tech info 的头像

Veera Tech info2 天前

@rshubert98 @TianshuYu6 Teaching AI to truly see smarter, faster vision for the next generation!

Synapse 的头像

Synapse2 天前

@rshubert98 @TianshuYu6 Wow, as someone in the field, I can say @liquidai is gonna be a huge protagonist in the future of AI.

Pratik Gandhi 的头像

Pratik Gandhi2 天前

@rshubert98 @TianshuYu6 love this! how much of the compute does the encoder take on long video?

ReignSwords 的头像

ReignSwords2 天前

@rshubert98 @TianshuYu6 The compute flip is the key insight — once the vision encoder eats more FLOPs than the LM, bolting on a standard ViT stops being free. Makes me wonder how much of LFM3's efficiency actually comes from the encoder design vs. the language backbone.

David Liu 的头像

David Liu2 天前

@rshubert98 @TianshuYu6 🔥

JG 🇮🇪 的头像

JG 🇮🇪2 天前

@rshubert98 @TianshuYu6 Vision encoder outspending the LLM is the bit nobody budgets for. At what image size does that flip?

Ernesto Davila Tirado 的头像

Ernesto Davila Tirado2 天前

@rshubert98 @TianshuYu6 goats

PELLUET Guillaume - Ph.D. 的头像

PELLUET Guillaume - Ph.D.1 天前

@rshubert98 @TianshuYu6 Mid-training into a custom vision encoder is the move to watch. When vision tokens cost more than language, the mix has to change with resolution, not just with epoch. 🎛️

Dominik 的头像

Dominik2 天前

@rshubert98 @TianshuYu6 an encoder that out-spends the language model on long video quietly changes how you size everything

jimerrors 的头像

jimerrors2 天前

@rshubert98 @TianshuYu6 Mid-training to a custom encoder for LFM3 is the jump I'm watching — long video is where most bolted-on vision setups start to hurt.

HEISGIFT 的头像

HEISGIFT2 天前

@rshubert98 @TianshuYu6 encoder out-costing the llm on long video

IronaX 的头像

IronaX2 天前

@rshubert98 @TianshuYu6 We spent years moving everything to the cloud. Now the biggest flex is that nothing leaves your phone.

相关视频

🚀 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

163,663 次观看 • 1 年前

Pretraining is essential for good performance on a wide variety of robotics tasks, and so most vision-language-action models build off of a vision language model (VLM) trained on a wide variety of image-language data. But how does the choice of VLM translate to downstream robotics performance? Jianke Zhang and @GYanjiang join us to talk about this key part of the robot policy, looking at a wide variety of different VLMs and how they perform. Interestingly, they see that performance on auxiliary tasks like quesiton answering did not lead to downstream improvements in control. To learn more, watch episode 65 of RoboPapers now, with Chris Paxton and Jiafei Duan!

Pretraining is essential for good performance on a wide variety of robotics tasks, and so most vision-language-action models build off of a vision language model (VLM) trained on a wide variety of image-language data. But how does the choice of VLM translate to downstream robotics performance? Jianke Zhang and @GYanjiang join us to talk about this key part of the robot policy, looking at a wide variety of different VLMs and how they perform. Interestingly, they see that performance on auxiliary tasks like quesiton answering did not lead to downstream improvements in control. To learn more, watch episode 65 of RoboPapers now, with Chris Paxton and Jiafei Duan!

RoboPapers

23,905 次观看 • 8 个月前

Introducing Meta Perception Language Model (PLM): an open & reproducible vision-language model tackling challenging visual tasks. Learn more about how PLM can help the open source community build more capable computer vision systems. Read the research paper, and download the code and dataset:

Introducing Meta Perception Language Model (PLM): an open & reproducible vision-language model tackling challenging visual tasks. Learn more about how PLM can help the open source community build more capable computer vision systems. Read the research paper, and download the code and dataset:

AI at Meta

94,534 次观看 • 1 年前

Introducing Meta Perception Encoder: a vision encoder setting new standards in image & video tasks. It excels in zero-shot classification & retrieval, surpassing existing models. Learn more about Meta Perception Encoder, read the research paper, and download the code and dataset

Introducing Meta Perception Encoder: a vision encoder setting new standards in image & video tasks. It excels in zero-shot classification & retrieval, surpassing existing models. Learn more about Meta Perception Encoder, read the research paper, and download the code and dataset

AI at Meta

74,689 次观看 • 1 年前

Excited to introduce 𝐋𝐀𝐏𝐀: the first unsupervised pretraining method for Vision-Language-Action models. Outperforms SOTA models trained with ground-truth actions 30x more efficient than conventional VLA pretraining 📝: 🧵 1/9

Excited to introduce 𝐋𝐀𝐏𝐀: the first unsupervised pretraining method for Vision-Language-Action models. Outperforms SOTA models trained with ground-truth actions 30x more efficient than conventional VLA pretraining 📝: 🧵 1/9

Joel Jang

46,154 次观看 • 2 年前

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.

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 次观看 • 9 个月前

#M5StackNew 🎊 The LLM630 Compute Kit is an #AI large language model (#LLM) inference development kit, powered by the #Axera #AX630C SoC with a 3.2 TOPs NPU, it delivers efficient AI inference for tasks like computer vision (CV) and LLM processing.

#M5StackNew 🎊 The LLM630 Compute Kit is an #AI large language model (#LLM) inference development kit, powered by the #Axera #AX630C SoC with a 3.2 TOPs NPU, it delivers efficient AI inference for tasks like computer vision (CV) and LLM processing.

M5Stack

16,859 次观看 • 1 年前

Check out our 2025 highlights in computer vision! 🚀Five new *St3R models (MASt3R-SfM, MUSt3R, PanSt3R, HAMSt3R, HOSt3R ) 🤩Anny parametric 3D human model (Apache 2.0) 🤟Universal encoder for all-in-one vision FM More info ▶️

Check out our 2025 highlights in computer vision! 🚀Five new *St3R models (MASt3R-SfM, MUSt3R, PanSt3R, HAMSt3R, HOSt3R ) 🤩Anny parametric 3D human model (Apache 2.0) 🤟Universal encoder for all-in-one vision FM More info ▶️

NAVER LABS Europe

12,612 次观看 • 10 个月前

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

3D-VLA A 3D Vision-Language-Action Generative World Model Recent vision-language-action (VLA) models rely on 2D inputs, lacking integration with the broader realm of the 3D physical world. Furthermore, they perform action prediction by learning a direct mapping from

AK

85,570 次观看 • 2 年前

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Chinese robotics company Astribot released their latest World-Action Model (WAM), Lumo-2. Technical breakdown: - based on a frozen 🥶 Qwen-3.5 4B VLM - trained in 3 progressive stages: 1. Action is aligned with latent world dynamics (an abstract representation of action). Real-world actions are anchored to physical constraints, while the latent space is guided to focus on motion-relevant changes. This bidirectional relationship makes the model physically grounded -> critical for a world model. 2. Action is aligned with vision and language. Reusing the vision backbone and action encoder from the frozen VLM, the authors add a custom vocabulary (for new actions), a semantic module, an action decoder, and an action projector. This aligns the (new) action representations with the (existing) vision-language semantic space. Most importantly: it builds a direct mapping from natural-language instructions to motor execution. 3. End-to-end training on language, video, and robot data. Only the new modules (everything outside the frozen backbone) are trained end-to-end across temporal reasoning, physical understanding, long-horizon, and dexterous manipulation. At the end of the day, Lumo-2 is not the best on benchmarks, but that's not the point. What's genuinely new: - a way to combine latent world modeling and action generation through progressive alignment - a physically-grounded latent dynamics space - it lifts performance on unseen objects using un-annotated human egocentric video + Vision Pro captures, no special transfer algorithm needed Why it matters: - the whole model is thin trainable adapters (semantic module, action decoder/projector) on a frozen 4B backbone (cheap) - that scale is suited for real-time embedded inference (~2.71× decode speedup, no accuracy loss) - its real moat is long-horizon execution, where the added temporal memory pays off far more than on any other task As a result, this robot can now make your latte (5x sped up video):

Léo

32,513 次观看 • 3 个月前

🚨 UNCANNY VALLEY: LANGUAGE MODEL TECH IS NOW DRIVING AI THAT CAN SEE AND REASON TOO Swupnil Sahai 🎾🧠: “The new architecture that’s come out for these language models works really well for vision now too. So the kind of math you can use to go from that input to be output is becoming the same now. We’re actually using much lighter weight models. So it’s a slightly different architecture, but it’s the same concept.”

🚨 UNCANNY VALLEY: LANGUAGE MODEL TECH IS NOW DRIVING AI THAT CAN SEE AND REASON TOO Swupnil Sahai 🎾🧠: “The new architecture that’s come out for these language models works really well for vision now too. So the kind of math you can use to go from that input to be output is becoming the same now. We’re actually using much lighter weight models. So it’s a slightly different architecture, but it’s the same concept.”

Mario Nawfal

90,984 次观看 • 1 年前

White Vision comes face-to-face with the original Vision, and their confrontation becomes more than a fight. One has the body, but the other holds the memories. Can Vision make him remember who he truly is?

White Vision comes face-to-face with the original Vision, and their confrontation becomes more than a fight. One has the body, but the other holds the memories. Can Vision make him remember who he truly is?

Stephanie paul

192,118 次观看 • 16 天前

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Large Language Diffusion with Masking (LLaDA) are here - and their generation looks so fucking dope! 🤯 True to Yann LeCun's vision, Ditch the auto-regressive bits and approximate the language distribution via Maximum Likelihood Estimation! So cool to watch the model denoise text from tokens in real time! - The team released their model checkpoints and there's a demo for you to play with it too! Try it out!🤗

Vaibhav (VB) Srivastav

21,410 次观看 • 1 年前

Introducing Figure out which open model is best for your use case. Compare models across coding, agents, long context, vision, finance, and more. Then see how they compare on cost + quality, including what you could save by moving to open models.

Introducing Figure out which open model is best for your use case. Compare models across coding, agents, long context, vision, finance, and more. Then see how they compare on cost + quality, including what you could save by moving to open models.

Hassan

18,655 次观看 • 1 个月前

👀Humans compare images by looking back and forth. Many open-weight VLMs encode each image independently, and defer comparison to the LM. We introduce SVE: Stateful Visual Encoders for Vision-Language Models, where the visual encoder itself becomes change-aware. 🌐Project: 📰Paper: 💻Code: 1/n

👀Humans compare images by looking back and forth. Many open-weight VLMs encode each image independently, and defer comparison to the LM. We introduce SVE: Stateful Visual Encoders for Vision-Language Models, where the visual encoder itself becomes change-aware. 🌐Project: 📰Paper: 💻Code: 1/n

Zirui "Colin" Wang ✈️EMNLP

63,924 次观看 • 5 个月前

Most robot datasets store one sentence per episode: the task. Real problems need more: a plan, a memory, room to answer questions and change course. We just shipped full language support in the LeRobot dataset format. Now lerobot-annotate points a vision-language model at each episode and writes the subtasks, plans, memory, and grounded Q&A itself - roughly $1.20 for 100 episodes. From there, recipes turn the annotated rows into policy-agnostic training messages, so the same dataset can teach planning, memory, tool calls, or low-level control, no dataset redesign required. Read how it all works on the blog:

Most robot datasets store one sentence per episode: the task. Real problems need more: a plan, a memory, room to answer questions and change course. We just shipped full language support in the LeRobot dataset format. Now lerobot-annotate points a vision-language model at each episode and writes the subtasks, plans, memory, and grounded Q&A itself - roughly $1.20 for 100 episodes. From there, recipes turn the annotated rows into policy-agnostic training messages, so the same dataset can teach planning, memory, tool calls, or low-level control, no dataset redesign required. Read how it all works on the blog:

LeRobot

13,451 次观看 • 3 个月前

🔥We're thrilled to announce: ShowUI Local Run!🔥 🧑‍💻Now, you can use our 2B vision-language-action model for Local Computer control! 💰30x Cheaper than Claude! 🔗Model: 🔗Computer Use OOTB: #ComputerUse #Agent #Claude

🔥We're thrilled to announce: ShowUI Local Run!🔥 🧑‍💻Now, you can use our 2B vision-language-action model for Local Computer control! 💰30x Cheaper than Claude! 🔗Model: 🔗Computer Use OOTB: #ComputerUse #Agent #Claude

Kevin Lin

14,587 次观看 • 1 年前

Vision RAG with vector database is all you need. It uses vision language model to embed pages of PDF as directly vectors, without the tedious chunking process. 100% Opensource code.

Vision RAG with vector database is all you need. It uses vision language model to embed pages of PDF as directly vectors, without the tedious chunking process. 100% Opensource code.

Shubham Saboo

106,869 次观看 • 1 年前