A post says success on RoboCasa GR-1 rose from 63.3% to 78.7% as context grew from 0.0 to 19.2 seconds.
A post describes Nvidia’s Long-WAM as a framework for scaling the context of world-action models. It says increasing context from 0.0 to 19.2 seconds raised success on RoboCasa GR-1 from 63.3% to 78.7%.
13.3K
3 Sources, first seen ago
—
Not ranked yet
—
Not ranked yet
@HuggingPapersNVIDIA just released Long-WAM A world-action model that scales visual context for real-time robot control. Access to history is not the same as using it: longer histories pay off far more when the video foundation is pretrained autoregressively.
@AaronWeiHuangExcited to release Long-WAM, our new exploration in embodied AI 🤖！ With memory, Long-WAM precisely perceives how objects move, predicts their trajectories, and gains emergent scaling on long-horizon tasks; our infra runs it fast on edge devices. https://nvlabs.github.io/LongLive/Long-WAM/
@arankomatsuzakiNvidia presents Long-WAM - A framework for scaling the context of world-action models - Increasing context from 0.0 to 19.2 seconds raises success from 63.3% to 78.7% on RoboCasa GR-1@HuggingPapersNVIDIA just released Long-WAM A world-action model that scales visual context for real-time robot control. Access to history is not the same as using it: longer histories pay off far more when the video foundation is pretrained autoregressively.@AaronWeiHuangExcited to release Long-WAM, our new exploration in embodied AI 🤖！ With memory, Long-WAM precisely perceives how objects move, predicts their trajectories, and gains emergent scaling on long-horizon tasks; our infra runs it fast on edge devices. https://nvlabs.github.io/LongLive/Long-WAM/@arankomatsuzakiNvidia presents Long-WAM - A framework for scaling the context of world-action models - Increasing context from 0.0 to 19.2 seconds raises success from 63.3% to 78.7% on RoboCasa GR-1@HuggingPapersNVIDIA just released Long-WAM A world-action model that scales visual context for real-time robot control. Access to history is not the same as using it: longer histories pay off far more when the video foundation is pretrained autoregressively.@AaronWeiHuangExcited to release Long-WAM, our new exploration in embodied AI 🤖！ With memory, Long-WAM precisely perceives how objects move, predicts their trajectories, and gains emergent scaling on long-horizon tasks; our infra runs it fast on edge devices. https://nvlabs.github.io/LongLive/Long-WAM/@arankomatsuzakiNvidia presents Long-WAM - A framework for scaling the context of world-action models - Increasing context from 0.0 to 19.2 seconds raises success from 63.3% to 78.7% on RoboCasa GR-1@HuggingPapersNVIDIA just released Long-WAM A world-action model that scales visual context for real-time robot control. Access to history is not the same as using it: longer histories pay off far more when the video foundation is pretrained autoregressively.@AaronWeiHuangExcited to release Long-WAM, our new exploration in embodied AI 🤖！ With memory, Long-WAM precisely perceives how objects move, predicts their trajectories, and gains emergent scaling on long-horizon tasks; our infra runs it fast on edge devices. https://nvlabs.github.io/LongLive/Long-WAM/@arankomatsuzakiNvidia presents Long-WAM - A framework for scaling the context of world-action models - Increasing context from 0.0 to 19.2 seconds raises success from 63.3% to 78.7% on RoboCasa GR-1
