Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Introducing Video Language Planning! By planning across the space of generated videos/language, we can synthesize long-horizon video plans and solve much longer horizon tasks than existing baseline (such as RT-2 and PALM-E). (1/5)

Yilun Du

13,278 subscribers

90,272 просмотров • 3 лет назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Yilun Du

Yilun Du3 лет назад

Video Language Planning (VLP) combines the strengths of VLMs and text-to-video models to jointly synthesize detailed video plans of actions to execute using a tree-search procedure. Video plans are then converted to actions using a goal-conditioned policy. (2/5)

Фото профиля Yilun Du

Yilun Du3 лет назад

Planning substantially improves the performance of VLP. Below, we illustrate generated video plans to construct a line by either: (1) using a single text-to-video model, (2) using a VLM + text-to-video model without search, (3) using a VLM+text-to-video with search. (3/5)

Фото профиля Yilun Du

Yilun Du3 лет назад

By planning and refining a sequence of actions, on long-horizon tasks, VLP substantially outperforms existing approaches such as RT-2 or PALM-E which autoregressively predict actions and often get stuck at OOD states The importance of model based planning @ylecun! (4/5)

Фото профиля Yilun Du

Yilun Du3 лет назад

Work done with amazing collaborators @mengjiao_yang , @peteflorence , @xf1280, @ayzwah, @brian_ichter, Pierre Sermanet, @TianheYu, @pabbeel, Josh Tenenbaum, Leslie Kaelbling, @andyzeng_, Jonathan Thompson (5/5)

Фото профиля Xidong Feng

Xidong Feng3 лет назад

can i interpret it as a combination or rollout policy, critic function and learned dynamic model, by these things we can do muzero style planning.

Фото профиля Yilun Du

Yilun Du3 лет назад

yup, where the rollouts are surprisingly super consistent even after many number of steps

Фото профиля Rufus

Rufus3 лет назад

@Scobleizer Incredible, this is a mind-blowing innovation.

Фото профиля William Lamkin

William Lamkin3 лет назад

Awesome work! 🦾🤖✨

Фото профиля Jaisurya

Jaisurya3 лет назад

Wow that's great

Фото профиля lucas

lucas3 лет назад

Beautiful! You guys are on fire!

Похожие видео

What can we learn from demonstrations of long-horizon tasks? I am presenting our #CoRL2024 paper "Learning Compositional Behaviors from Demonstration and Language" today, showing we can learn a library of behaviors that can be composed to solve new tasks.

What can we learn from demonstrations of long-horizon tasks? I am presenting our #CoRL2024 paper "Learning Compositional Behaviors from Demonstration and Language" today, showing we can learn a library of behaviors that can be composed to solve new tasks.

Weiyu Liu

10,091 просмотров • 1 год назад

Day 1 of Wave 10! We are introducing Planning Mode, a new way to work with Cascade on longer-horizon tasks. Available on all paid plans at no extra cost. Also we’ve made o3 way cheaper - now only 1x credits for both medium and high reasoning (prev 10x credits). Enjoy!

Day 1 of Wave 10! We are introducing Planning Mode, a new way to work with Cascade on longer-horizon tasks. Available on all paid plans at no extra cost. Also we’ve made o3 way cheaper - now only 1x credits for both medium and high reasoning (prev 10x credits). Enjoy!

Devin Desktop

137,653 просмотров • 1 год назад

Need help in the real world? RoboVQA can guide robots and humans through long-horizon tasks on a phone via Google Meet. We release a dataset of 800k (video, question/answer) with robots & humans doing various long-horizon tasks. Data: Google DeepMind

Need help in the real world? RoboVQA can guide robots and humans through long-horizon tasks on a phone via Google Meet. We release a dataset of 800k (video, question/answer) with robots & humans doing various long-horizon tasks. Data: Google DeepMind

Pierre Sermanet

64,369 просмотров • 2 лет назад

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models paper page: Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduce JARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all within the popular yet challenging open-world Minecraft universe. Specifically, we develop JARVIS-1 on top of pre-trained multimodal language models, which map visual observations and textual instructions to plans. The plans will be ultimately dispatched to the goal-conditioned controllers. We outfit JARVIS-1 with a multimodal memory, which facilitates planning using both pre-trained knowledge and its actual game survival experiences. In our experiments, JARVIS-1 exhibits nearly perfect performances across over 200 varying tasks from the Minecraft Universe Benchmark, ranging from entry to intermediate levels. JARVIS-1 has achieved a completion rate of 12.5% in the long-horizon diamond pickaxe task. This represents a significant increase up to 5 times compared to previous records. Furthermore, we show that JARVIS-1 is able to self-improve following a life-long learning paradigm thanks to multimodal memory, sparking a more general intelligence and improved autonomy.

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models paper page: Achieving human-like planning and control with multimodal observations in an open world is a key milestone for more functional generalist agents. Existing approaches can handle certain long-horizon tasks in an open world. However, they still struggle when the number of open-world tasks could potentially be infinite and lack the capability to progressively enhance task completion as game time progresses. We introduce JARVIS-1, an open-world agent that can perceive multimodal input (visual observations and human instructions), generate sophisticated plans, and perform embodied control, all within the popular yet challenging open-world Minecraft universe. Specifically, we develop JARVIS-1 on top of pre-trained multimodal language models, which map visual observations and textual instructions to plans. The plans will be ultimately dispatched to the goal-conditioned controllers. We outfit JARVIS-1 with a multimodal memory, which facilitates planning using both pre-trained knowledge and its actual game survival experiences. In our experiments, JARVIS-1 exhibits nearly perfect performances across over 200 varying tasks from the Minecraft Universe Benchmark, ranging from entry to intermediate levels. JARVIS-1 has achieved a completion rate of 12.5% in the long-horizon diamond pickaxe task. This represents a significant increase up to 5 times compared to previous records. Furthermore, we show that JARVIS-1 is able to self-improve following a life-long learning paradigm thanks to multimodal memory, sparking a more general intelligence and improved autonomy.

AK

141,440 просмотров • 2 лет назад

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 просмотров • 3 лет назад

Can my robot cook my food, rearrange my dresser, tidy my messy table and do so much more without ANY demos or real-world training data? Introducing ManipGen: A generalist agent for manipulation that can solve long-horizon robotics tasks entirely zero shot, from text input! 1/N

Can my robot cook my food, rearrange my dresser, tidy my messy table and do so much more without ANY demos or real-world training data? Introducing ManipGen: A generalist agent for manipulation that can solve long-horizon robotics tasks entirely zero shot, from text input! 1/N

Murtaza Dalal

149,236 просмотров • 1 год назад

State-of-the-art robot policies often need hundreds of hours of data. What if we needed none? Introducing TiPToP: a manipulation system that zero-shots open-world tasks from pixels and language using vision foundation models and GPU-parallelized Task and Motion Planning (TAMP).

State-of-the-art robot policies often need hundreds of hours of data. What if we needed none? Introducing TiPToP: a manipulation system that zero-shots open-world tasks from pixels and language using vision foundation models and GPU-parallelized Task and Motion Planning (TAMP).

Nishanth Kumar

79,566 просмотров • 6 месяцев назад

A few weeks ago, we shared our progress on articulated objects and long-horizon tasks. Here are two representative examples: - We've been steadily expanding our asset library to cover more articulated objects. Articulated objects have always been a challenging asset class to handle in simulation. Interacting with them requires robots to master atomic skills such as pushing, pulling, opening, and closing, and to understand part structure, interaction constraints, and how the object moves. - Long-horizon tasks can now be generated at scale. Long-horizon tasks are the other hard category: they require chaining multiple sub-goals in sequence. A failure early in the task can cascade and make the rest unrecoverable. Axis is scaling along three dimensions at once: data volume, data quality, and task difficulty.

A few weeks ago, we shared our progress on articulated objects and long-horizon tasks. Here are two representative examples: - We've been steadily expanding our asset library to cover more articulated objects. Articulated objects have always been a challenging asset class to handle in simulation. Interacting with them requires robots to master atomic skills such as pushing, pulling, opening, and closing, and to understand part structure, interaction constraints, and how the object moves. - Long-horizon tasks can now be generated at scale. Long-horizon tasks are the other hard category: they require chaining multiple sub-goals in sequence. A failure early in the task can cascade and make the rest unrecoverable. Axis is scaling along three dimensions at once: data volume, data quality, and task difficulty.

Axis Robotics

14,217 просмотров • 3 месяцев назад

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.

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

125,353 просмотров • 3 лет назад

Every wondered if we can model motion as a language? can we tokenize this new language? is it useful? Turns out tremendously! 🚀 In out latest #NeurIPS2024 paper on QueST: Self-Supervised Skill Abstractions for Learning Continuous Control, we find that action tokenization matters a lot! We can learn skill encodings by representing temporal action abstractions with a discrete codebook. This enables 2 things 1. Better Behaviour Cloning: we can better assimilate multi-task data (>9%) over best paper. This is currently best in class BC method! 2. generalization of this language to represent new tasks in 5-shot transfer to longer horizon tasks! Check out the thread by Atharva Mete for more details. And check out more details at: Joint work with Atharva Mete Albert Wilcox Haotian Xue Yongxin Chen Georgia Tech School of Interactive Computing Machine Learning at Georgia Tech Robotics@GT NVIDIA Robotics

Every wondered if we can model motion as a language? can we tokenize this new language? is it useful? Turns out tremendously! 🚀 In out latest #NeurIPS2024 paper on QueST: Self-Supervised Skill Abstractions for Learning Continuous Control, we find that action tokenization matters a lot! We can learn skill encodings by representing temporal action abstractions with a discrete codebook. This enables 2 things 1. Better Behaviour Cloning: we can better assimilate multi-task data (>9%) over best paper. This is currently best in class BC method! 2. generalization of this language to represent new tasks in 5-shot transfer to longer horizon tasks! Check out the thread by Atharva Mete for more details. And check out more details at: Joint work with Atharva Mete Albert Wilcox Haotian Xue Yongxin Chen Georgia Tech School of Interactive Computing Machine Learning at Georgia Tech Robotics@GT NVIDIA Robotics

Animesh Garg

26,252 просмотров • 2 лет назад

Introducing Yell At Your Robot (YAY Robot!) 🗣️- a fun collaboration b/w Stanford University and UC Berkeley 🤖 We enable robots to improve on-the-fly from language corrections: robots rapidly adapt in real-time and continuously improve from human verbal feedback. YAY Robot enables long-horizon, dexterous manipulation tasks like preparing trail-mix, packing a ziploc bag, and cleaning dishes:

Introducing Yell At Your Robot (YAY Robot!) 🗣️- a fun collaboration b/w Stanford University and UC Berkeley 🤖 We enable robots to improve on-the-fly from language corrections: robots rapidly adapt in real-time and continuously improve from human verbal feedback. YAY Robot enables long-horizon, dexterous manipulation tasks like preparing trail-mix, packing a ziploc bag, and cleaning dishes:

Lucy Shi

122,827 просмотров • 2 лет назад

Can we simplify video generation by decomposing it into interleaved text-video co-generation? Would explicit, repeated thinking in language improve generation in pixels? We introduce TV2TV: a unified model that jointly learns - language modeling (next-token prediction) - video flow matching (next-frame prediction) At inference, TV2TV dynamically alternates between textual thinking and video generation. Model generations below: interleaved text plans and video slices (~1–2s) are co-generated over time, conditioned on a single frame per sport. 📖

Can we simplify video generation by decomposing it into interleaved text-video co-generation? Would explicit, repeated thinking in language improve generation in pixels? We introduce TV2TV: a unified model that jointly learns - language modeling (next-token prediction) - video flow matching (next-frame prediction) At inference, TV2TV dynamically alternates between textual thinking and video generation. Model generations below: interleaved text plans and video slices (~1–2s) are co-generated over time, conditioned on a single frame per sport. 📖

Xiaochuang Han

32,552 просмотров • 9 месяцев назад

Show it a single human demonstration of a long-horizon task and the robot performs it right away. No fine-tuning, no retraining. Skild has released S1, a robot foundation model where you specify the task with a video demonstration instead of a language instruction. Why video, not language Language works for "hand me the mug." It falls apart for anything delicate or long-horizon. You don't learn to fold a fitted sheet from a sentence. So S1 takes a video demo into its context window and translates it to its own body and scene. What it does - Tasks up to 10 minutes, dozens of sequential steps - Unseen tasks: potting plants, pour-over coffee, kit assembly, pancakes. Skild says even the underlying primitives, like flipping a pancake, weren't in pre-training - Recovers from its own mistakes without being trained to - Improves on flawed demos. Demonstrator drops an egg, S1 doesn't make that mistake. It reads the demo as a goal, not a trajectory to copy.

Show it a single human demonstration of a long-horizon task and the robot performs it right away. No fine-tuning, no retraining. Skild has released S1, a robot foundation model where you specify the task with a video demonstration instead of a language instruction. Why video, not language Language works for "hand me the mug." It falls apart for anything delicate or long-horizon. You don't learn to fold a fitted sheet from a sentence. So S1 takes a video demo into its context window and translates it to its own body and scene. What it does - Tasks up to 10 minutes, dozens of sequential steps - Unseen tasks: potting plants, pour-over coffee, kit assembly, pancakes. Skild says even the underlying primitives, like flipping a pancake, weren't in pre-training - Recovers from its own mistakes without being trained to - Improves on flawed demos. Demonstrator drops an egg, S1 doesn't make that mistake. It reads the demo as a goal, not a trajectory to copy.

The Humanoid Hub

18,995 просмотров • 1 месяц назад

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

What if robots, humans, and video models could all describe action in the same language? Introducing Hydra-0🐍: a generalist world model that represents robot actions as action flow. One interface. Many embodiments, tasks, and environments. 🧵1/7

Hongyu Li

81,511 просмотров • 1 месяц назад

How well do today’s frontier models handle long-horizon, multi-step web agent tasks, such as identifying the top 25 U.S. CS PhD programs with ML/AI faculty likely accepting students and compiling the results into a structured sheet? Check out our new work on Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks Paper: Leaderboard: We introduce Odysseys, a benchmark of 200 long-horizon tasks derived from real browsing sessions and evaluated on the live Internet. We show that binary pass/fail is inadequate in this setting and propose rubric-based evaluation, which better aligns with human judgment and provides more informative signals. Across leading models, the best achieves only 44.5% success, leaving substantial headroom. We further introduce a Trajectory Efficiency metric (rubric score per step) and find efficiency remains extremely low (1.15%), highlighting a key bottleneck. Odysseys provides a realistic benchmark for measuring progress toward web agents capable of sustained, efficient, real-world operation. See a more detailed thread by Jing Yu Koh.

How well do today’s frontier models handle long-horizon, multi-step web agent tasks, such as identifying the top 25 U.S. CS PhD programs with ML/AI faculty likely accepting students and compiling the results into a structured sheet? Check out our new work on Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks Paper: Leaderboard: We introduce Odysseys, a benchmark of 200 long-horizon tasks derived from real browsing sessions and evaluated on the live Internet. We show that binary pass/fail is inadequate in this setting and propose rubric-based evaluation, which better aligns with human judgment and provides more informative signals. Across leading models, the best achieves only 44.5% success, leaving substantial headroom. We further introduce a Trajectory Efficiency metric (rubric score per step) and find efficiency remains extremely low (1.15%), highlighting a key bottleneck. Odysseys provides a realistic benchmark for measuring progress toward web agents capable of sustained, efficient, real-world operation. See a more detailed thread by Jing Yu Koh.

Russ Salakhutdinov

22,518 просмотров • 5 месяцев назад

Introducing SIMA: the first generalist AI agent to follow natural-language instructions in a broad range of 3D virtual environments and video games. 🕹️ It can complete tasks similar to a human, and outperforms an agent trained in just one setting. 🧵

Introducing SIMA: the first generalist AI agent to follow natural-language instructions in a broad range of 3D virtual environments and video games. 🕹️ It can complete tasks similar to a human, and outperforms an agent trained in just one setting. 🧵

Google DeepMind

1,062,434 просмотров • 2 лет назад

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.

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

249,798 просмотров • 3 лет назад

Boston Dynamics has released a new video of their next-generation humanoid robot, Atlas. "We are excited to share some of our progress on developing Large Behavior Models for Atlas. This work is part of a collaboration between AI research teams at Toyota Research Institute (TRI) and Boston Dynamics. We have been building end-to-end language-conditioned policies that enable Atlas to accomplish long-horizon manipulation tasks."

Boston Dynamics has released a new video of their next-generation humanoid robot, Atlas. "We are excited to share some of our progress on developing Large Behavior Models for Atlas. This work is part of a collaboration between AI research teams at Toyota Research Institute (TRI) and Boston Dynamics. We have been building end-to-end language-conditioned policies that enable Atlas to accomplish long-horizon manipulation tasks."

Sawyer Merritt

200,744 просмотров • 1 год назад

Introducing PAN — MBZUAI’s New World Model for Interactive Intelligence Developed by MBZUAI’s Institute of Foundation Models, PAN is built for simulation, prediction, and agentic reasoning. Unlike traditional video generators that only output frames, PAN maintains a persistent internal state that evolves when guided with natural language. Its Generative Latent Prediction architecture combines: • A latent encoder to capture the world state • A dynamics module that evolves that state step-by-step • A video diffusion decoder that visualizes outcomes By decoding at every step using a causal sliding-window diffusion process, PAN stays grounded in real-world physics and maintains long-horizon continuity, a leap beyond single-shot models. Evaluated on action fidelity, long-horizon stability, and simulative planning, PAN delivers state-of-the-art performance compared to open models and rivals leading commercial systems. For robotics, autonomy, and decision support, PAN is a foundation for the next wave of intelligent, foresight-driven AI.

Introducing PAN — MBZUAI’s New World Model for Interactive Intelligence Developed by MBZUAI’s Institute of Foundation Models, PAN is built for simulation, prediction, and agentic reasoning. Unlike traditional video generators that only output frames, PAN maintains a persistent internal state that evolves when guided with natural language. Its Generative Latent Prediction architecture combines: • A latent encoder to capture the world state • A dynamics module that evolves that state step-by-step • A video diffusion decoder that visualizes outcomes By decoding at every step using a causal sliding-window diffusion process, PAN stays grounded in real-world physics and maintains long-horizon continuity, a leap beyond single-shot models. Evaluated on action fidelity, long-horizon stability, and simulative planning, PAN delivers state-of-the-art performance compared to open models and rivals leading commercial systems. For robotics, autonomy, and decision support, PAN is a foundation for the next wave of intelligent, foresight-driven AI.

MBZUAI

98,785 просмотров • 10 месяцев назад