正在加载视频...

视频加载失败

返回首页

Do Vision-Language Models represent space, and how? Spatial terms like "left" or "right" may not be enough to match images with spatial descriptions, as we often overlook the different frames of reference (FoR) used by speakers and listeners. See Figure 1 for examples! Introducing the COnsistent Multilingual Frame Of...

ziqiao_ma's profile picture

Martin Ziqiao Ma

5,368 subscribers

35,606 次观看 • 2 年前 •via X (Twitter)

教育健康养生科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

1 条评论

Martin Ziqiao Ma 的头像
Martin Ziqiao Ma2 年前

Interesting fact: Reasoning across multiple intrinsic frames of reference is quite challenging, even for GPT-4. I adapted Figure 2.5 from Levinson 2003 (Logical Inadequacies of the Intrinsic Frame of Reference) into a yes/no question format, and GPT-4 struggled with both.

相关视频

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.
5:11

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models paper page: github: Recent advancements in text-to-image generation with diffusion models have yielded remarkable results synthesizing highly realistic and diverse images. However, these models still encounter difficulties when generating images from prompts that demand spatial or common sense reasoning. We propose to equip diffusion models with enhanced reasoning capabilities by using off-the-shelf pretrained large language models (LLMs) in a novel two-stage generation process. First, we adapt an LLM to be a text-guided layout generator through in-context learning. When provided with an image prompt, an LLM outputs a scene layout in the form of bounding boxes along with corresponding individual descriptions. Second, we steer a diffusion model with a novel controller to generate images conditioned on the layout. Both stages utilize frozen pretrained models without any LLM or diffusion model parameter optimization. We validate the superiority of our design by demonstrating its ability to outperform the base diffusion model in accurately generating images according to prompts that necessitate both language and spatial reasoning. Additionally, our method naturally allows dialog-based scene specification and is able to handle prompts in a language that is not well-supported by the underlying diffusion model.

AK

83,681 次观看 • 3 年前

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.
0:50

3D-LLM: Injecting the 3D World into Large Language Models paper page: Large language models (LLMs) and Vision-Language Models (VLMs) have been proven to excel at multiple tasks, such as commonsense reasoning. Powerful as these models can be, they are not grounded in the 3D physical world, which involves richer concepts such as spatial relationships, affordances, physics, layout, and so on. In this work, we propose to inject the 3D world into large language models and introduce a whole new family of 3D-LLMs. Specifically, 3D-LLMs can take 3D point clouds and their features as input and perform a diverse set of 3D-related tasks, including captioning, dense captioning, 3D question answering, task decomposition, 3D grounding, 3D-assisted dialog, navigation, and so on. Using three types of prompting mechanisms that we design, we are able to collect over 300k 3D-language data covering these tasks. To efficiently train 3D-LLMs, we first utilize a 3D feature extractor that obtains 3D features from rendered multi- view images. Then, we use 2D VLMs as our backbones to train our 3D-LLMs. By introducing a 3D localization mechanism, 3D-LLMs can better capture 3D spatial information. Experiments on ScanQA show that our model outperforms state-of-the-art baselines by a large margin (e.g., the BLEU-1 score surpasses state-of-the-art score by 9%). Furthermore, experiments on our held-in datasets for 3D captioning, task composition, and 3D-assisted dialogue show that our model outperforms 2D VLMs. Qualitative examples also show that our model could perform more tasks beyond the scope of existing LLMs and VLMs.

AK

250,112 次观看 • 3 年前

World Labs' Dr. Fei-Fei Li on why the 3D world and spatial intelligence are fundamentally different from language models: "Language is fundamentally a purely generated signal. There's no language out there. You don't go out in the nature and there's words written in the sky for you." "Whatever data you feed in, you pretty much can just somehow regurgitate with enough generalizability the same data out, and that's language to language." "But the 3D world is not. There is a 3D world out there that follows laws of physics, that has its own structures due to materials and many other things. And to fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing similar ideas or useful ideas from language and LLMs, but this is fundamentally philosophically, to me, a different problem." Fei-Fei Li
1:03

World Labs' Dr. Fei-Fei Li on why the 3D world and spatial intelligence are fundamentally different from language models: "Language is fundamentally a purely generated signal. There's no language out there. You don't go out in the nature and there's words written in the sky for you." "Whatever data you feed in, you pretty much can just somehow regurgitate with enough generalizability the same data out, and that's language to language." "But the 3D world is not. There is a 3D world out there that follows laws of physics, that has its own structures due to materials and many other things. And to fundamentally back that information out and be able to represent it and be able to generate it is just fundamentally quite a different problem." "We will be borrowing similar ideas or useful ideas from language and LLMs, but this is fundamentally philosophically, to me, a different problem." Fei-Fei Li

a16z

53,621 次观看 • 1 个月前

Vision-Language Models (VLMs) can describe the environment, but can they refer within it? Our findings reveal a critical gap: VLMs fall short of pragmatic optimality. We identify 3 key failures of pragmatic competence in referring expression generation with VLMs: (1) cannot uniquely refer to the referent, (2) include excessive or irrelevant information, and (3) misalign with human pragmatic preferences. We introduce RefOI, a new dataset of 1.5k objects, each with 3 written and 2 spoken human-produced referring expressions. We also release RefOI-TLHF, a large dataset of token-level human feedback for 10.6k referring expressions. 👀 📄 Excited to colead this project with the amazing JaneDing, and huge thanks to the dream team Xuejun Zhang Dezhi Luo Diiikee @6SihanXu Yuchen Huang Roihn Run Peng 彭润 ✈ COLM2026 Michigan SLED Lab.
0:43

Vision-Language Models (VLMs) can describe the environment, but can they refer within it? Our findings reveal a critical gap: VLMs fall short of pragmatic optimality. We identify 3 key failures of pragmatic competence in referring expression generation with VLMs: (1) cannot uniquely refer to the referent, (2) include excessive or irrelevant information, and (3) misalign with human pragmatic preferences. We introduce RefOI, a new dataset of 1.5k objects, each with 3 written and 2 spoken human-produced referring expressions. We also release RefOI-TLHF, a large dataset of token-level human feedback for 10.6k referring expressions. 👀 📄 Excited to colead this project with the amazing JaneDing, and huge thanks to the dream team Xuejun Zhang Dezhi Luo Diiikee @6SihanXu Yuchen Huang Roihn Run Peng 彭润 ✈ COLM2026 Michigan SLED Lab.

Martin Ziqiao Ma

20,714 次观看 • 1 年前

Today we’re releasing OpenEQA — the Open-Vocabulary Embodied Question Answering Benchmark. It measures an AI agent’s understanding of physical environments by probing it with open vocabulary questions like “Where did I leave my badge?” More details ➡️ All of today’s state-of-art vision+language models (VLMs) fall well short of human performance. In fact, for questions that require spatial understanding, today’s VLMs are nearly “blind” – access to visual content provides only minor improvements over language-only models. We hope that OpenEQA motivates additional research into helping AI understand and communicate about the world it sees.
1:58

Today we’re releasing OpenEQA — the Open-Vocabulary Embodied Question Answering Benchmark. It measures an AI agent’s understanding of physical environments by probing it with open vocabulary questions like “Where did I leave my badge?” More details ➡️ All of today’s state-of-art vision+language models (VLMs) fall well short of human performance. In fact, for questions that require spatial understanding, today’s VLMs are nearly “blind” – access to visual content provides only minor improvements over language-only models. We hope that OpenEQA motivates additional research into helping AI understand and communicate about the world it sees.

AI at Meta

407,280 次观看 • 2 年前

Demis Hassabis says world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️ This is what Demis and Google Deepmind is trying to solve with Genie. He also says that the video models (Veo) will play a part in training the world models and this is all key for AI robotics.
2:32

Demis Hassabis says world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️ This is what Demis and Google Deepmind is trying to solve with Genie. He also says that the video models (Veo) will play a part in training the world models and this is all key for AI robotics.

Bearly AI

123,804 次观看 • 10 个月前

Demis on why world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️
2:32

Demis on why world models are his longest standing passion and explains benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️

Bearly AI

78,545 次观看 • 5 个月前

Demis Hassabis on why world models are his longest standing passion and the benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️ *** From the Google DeepMind podcast in December 2025.
2:32

Demis Hassabis on why world models are his longest standing passion and the benefits vs. language models: ▫️ “I think language models are able to understand a lot about the world. More than we expected because language is actually probably richer than we thought. But there's still a lot about the spatial dynamics of the world, spatial awareness and the physical context we're in — and how that works mechanically — that is hard to describe in words and isn't generally described in corpuses of words. Alot of this is allied to learning from experience. There's a lot of things which you can't really describe something. You have to just experience it. Maybe the senses and so on are very hard to put into words. Whether that's motor angles and smell and these kinds of senses, it's very difficult to describe that in any kind of language.”▫️ *** From the Google DeepMind podcast in December 2025.

Bearly AI

65,630 次观看 • 2 个月前

"Visual-spatial intelligence is as fundamental as language." Fei-Fei Li says world models are the key to letting AI see the world, reason about it, interact with it, navigate it, and even 'build civilization upon it.' "It's very natural for me that World Labs' north star is to unlock spatial intelligence. The moment to me is right to do it." "We've got these ingredients—we've got compute, we've got a much deeper understanding of data, way deeper than [the ImageNet days]... and we've got some advancement of algorithms."
1:27

"Visual-spatial intelligence is as fundamental as language." Fei-Fei Li says world models are the key to letting AI see the world, reason about it, interact with it, navigate it, and even 'build civilization upon it.' "It's very natural for me that World Labs' north star is to unlock spatial intelligence. The moment to me is right to do it." "We've got these ingredients—we've got compute, we've got a much deeper understanding of data, way deeper than [the ImageNet days]... and we've got some advancement of algorithms."

a16z

32,387 次观看 • 8 个月前

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)
0:43

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

Wenhu Chen

82,829 次观看 • 1 年前

"We ought to be able to press 1 for English and get somebody on the other end that English is their native tongue. That they understand and speak the language of THIS LAND." President Trump made English the official language of this great country, it is time for everyone to get on board or GET OUT!
0:41

"We ought to be able to press 1 for English and get somebody on the other end that English is their native tongue. That they understand and speak the language of THIS LAND." President Trump made English the official language of this great country, it is time for everyone to get on board or GET OUT!

AmericanPapaBear™

11,255 次观看 • 11 个月前

Introducing Natura-1, our first general foundation model for the physical world. It follows natural-language instructions zero-shot and turns them into action with dexterous hands. Natura-1 is a 50-billion-parameter mixture-of-experts (MoE) model pretrained on one million hours of egocentric human experience. On top of this foundation, we conduct efficient post-training on a limited amount of robot data to adapt pretrained world knowledge to dexterous manipulation, yielding a model that generalizes to a wide range of unseen scenarios. Natura-1 follows complex natural-language instructions zero-shot, reasoning through spatial constraints, multi-object relationships, and negative conditions. It can also autonomously carry out long and continuous workflows to perform long-horizon executions. Natura-1 provides early evidence that generalization—and even emergent behavior—can coexist with the complexity of dexterous hands. Further progress depends on the full stack: infrastructure for faster training and real-time inference, pretraining data at greater scale and coverage, and models that transfer to robots with less adaptation. We expect it to be a long-term research and engineering effort.
3:12

Introducing Natura-1, our first general foundation model for the physical world. It follows natural-language instructions zero-shot and turns them into action with dexterous hands. Natura-1 is a 50-billion-parameter mixture-of-experts (MoE) model pretrained on one million hours of egocentric human experience. On top of this foundation, we conduct efficient post-training on a limited amount of robot data to adapt pretrained world knowledge to dexterous manipulation, yielding a model that generalizes to a wide range of unseen scenarios. Natura-1 follows complex natural-language instructions zero-shot, reasoning through spatial constraints, multi-object relationships, and negative conditions. It can also autonomously carry out long and continuous workflows to perform long-horizon executions. Natura-1 provides early evidence that generalization—and even emergent behavior—can coexist with the complexity of dexterous hands. Further progress depends on the full stack: infrastructure for faster training and real-time inference, pretraining data at greater scale and coverage, and models that transfer to robots with less adaptation. We expect it to be a long-term research and engineering effort.

nature will

1,043,474 次观看 • 21 天前

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI
3:58

Excited to share our latest work on 🎧spatial audio-driven human motion generation. We aim to tackle a largely underexplored yet important problem of enabling virtual humans to move naturally in response to spatial audio—capturing not just what is heard, but also where the sound is coming from. To this end, we introduce the Spatial Audio-Driven Human Motion (SAM) dataset—the first comprehensive dataset featuring paired high-quality human motion and spatial audio recordings. For benchmarking, we develop a generative framework for human MOtion generation driven by SPAtial audio, termed MOSPA, which learns to synthesize realistic and diverse human motions conditioned on spatial audio input. We hope this research could provide a foundation for future research in spatial perception, virtual characters, and embodied AI. The dataset and model will be open-sourced soon. A big thank you to our intern, Shuyang Xu, for the wonderful collaboration! Congratulations, Shuyang! Project page: Paper: Video: #Animation #CG #CV #AIGC #DL #Deeplearning #Motion #Graphics #AI #GenerativeAI

Zhiyang (Frank) Dou

14,728 次观看 • 1 年前

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.
0:48

MotionGPT: Human Motion as a Foreign Language paper page: Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and untouched so far. Fortunately, human motion displays a semantic coupling akin to human language, often perceived as a form of body language. By fusing language data with large-scale motion models, motion-language pre-training that can enhance the performance of motion-related tasks becomes feasible. Driven by this insight, we propose MotionGPT, a unified, versatile, and user-friendly motion-language model to handle multiple motion-relevant tasks. Specifically, we employ the discrete vector quantization for human motion and transfer 3D motion into motion tokens, similar to the generation process of word tokens. Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a specific language. Moreover, inspired by prompt learning, we pre-train MotionGPT with a mixture of motion-language data and fine-tune it on prompt-based question-and-answer tasks. Extensive experiments demonstrate that MotionGPT achieves state-of-the-art performances on multiple motion tasks including text-driven motion generation, motion captioning, motion prediction, and motion in-between.

AK

125,403 次观看 • 3 年前

Shared at our flagship Research@ event today: In a new technical report, we demonstrate how combining domain-specific foundation models, spatial tools, and upfront planning enables a Geospatial Reasoning agent to carry out complex spatial analysis and planetary prediction that standalone LLMs can’t. This and more on the blog →
0:25

Shared at our flagship Research@ event today: In a new technical report, we demonstrate how combining domain-specific foundation models, spatial tools, and upfront planning enables a Geospatial Reasoning agent to carry out complex spatial analysis and planetary prediction that standalone LLMs can’t. This and more on the blog →

Google Research

20,783 次观看 • 19 天前

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!
1:03:46

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

What might a spatial harness look like for robotics? In this recording I show how Auki makes it possible to get multiple robots and devices collaboratively maintaining spatial context, and how we use augmented reality to interface both with the robots and each other.
1:32

What might a spatial harness look like for robotics? In this recording I show how Auki makes it possible to get multiple robots and devices collaboratively maintaining spatial context, and how we use augmented reality to interface both with the robots and each other.

Nils

14,053 次观看 • 18 天前

This is how large language models turn objects to vector representations. In this video, we explore how large language models (LLMs) convert objects into internal representations, especially when translating between languages like English and Hindi. Using real-world examples, we highlight the challenges of gender inference, grammatical structure, and why direct word-to-word translations often fail. If you're curious about how LLMs deal with multilingual contexts and what it takes to improve translation quality across languages, this video is for you. #LLMs #Vectors #LCM
6:57

This is how large language models turn objects to vector representations. In this video, we explore how large language models (LLMs) convert objects into internal representations, especially when translating between languages like English and Hindi. Using real-world examples, we highlight the challenges of gender inference, grammatical structure, and why direct word-to-word translations often fail. If you're curious about how LLMs deal with multilingual contexts and what it takes to improve translation quality across languages, this video is for you. #LLMs #Vectors #LCM

Gaurav Sen

27,368 次观看 • 1 年前