Frontend
HAVANA: A Hierarchical Video-Action Model for Vision-Language Navigation
arXiv cs.RO0 views
arXiv:2610.24122v3 Announce Type: replace-cross Abstract: Vision-Language Navigation (VLN) requires long-horizon instruction-consistent planning and short-horizon path planning grounded in the currently observed geometry. Anticipating how future observations evolve along the instructed route provides predictive guidance beyond the current field of view, motivating video-action models (VAMs) that learn representations of future visual states. However, many existing VAMs couple future visual prediction with action generation during inference, despite their distinct temporal requirements: instruction-conditioned route guidance can be reused across multiple control steps, whereas local trajectories must continuously adapt to fresh observations. To bridge this gap, we introduce HAVANA, a dual-system VAM that decouples predictive reasoning from reactive local planning. A slow system produces a compact language-conditioned latent plan from observation history, while a fast system combines the latest plan with the current observation to generate local trajectories. Their asynchronous execution enables rapid adaptation without repeated future prediction, and no future video is generated during inference. Experiments on OmniNavBench demonstrate state-of-the-art navigation performance over prior baselines, while zero-shot real-world deployments further show robust generalization to unseen environments.
Source:https://arxiv.org/abs/2610.24122PreviousWorld-Model Gradient Refinement in CEM: An Empirical StudyNextLatent Projection for Latent Planning
Related posts
I put my multi-model dispatch queue and its monthly spend beside the Claude Code chat. 1,330 lines, 37 ms.
0dev.to OpenSource

Landing Parking-Garage Gate Events in a Fabric Eventhouse
0dev.to OpenSource
Draft a conventional commit in Claude Code with a /commit slash command
0dev.to Git
I gave Claude a trading desk: building an MCP server that backtests and runs crypto bots
0dev.to TypeScript
Parameter-Dependent LMI Synthesis for Semi-Global Differential ISS Trajectory Tracking of Nonholonomic Mobile Robots Under Multiplicative Wheel Slip
0arXiv cs.RO
Is AWS Blocks Becoming "CDK Blocks"? What the Move to aws/cdk-blocks and the Rename Change
0dev.to AWS