arXiv AI
Aug 5
UniNav: A Unified World-Action Diffusion Model for Visual Navigation
arXiv:2608. 03244v1 Announce Type: new Abstract: Image-goal visual navigation is a fundamental capability for embodied agents.
UniNav: A Unified World-Action Diffusion Model for Visual Navigation
Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but lack visual foresight, while navigation world models can anticipate future observations but often require costly planning rollouts.
Related stories
arXiv AI
Jun 30
Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
arXiv:2606. 29908v1 Announce Type: cross Abstract: Existing world model-based planners for visual navigation typically follow a verification-centric paradigm, decoupling goal intent from trajectory synthesis.
arXiv AI
2d ago
DiffWAM: A Fast and Efficient Navigation World Action Model
DiffWAM is a geometry‑conditioned navigation world‑action model that transforms predictive features from a frozen video foundation model into continuous camera trajectories, eliminating the need for future‑video synthesis and multi‑frame reconstruction during deployment. Its Grid‑Motion module preserves spatial‑temporal motion associations, while Latent2Pose grounds them with first‑frame geometry to recover metrically meaningful 3D motion. The system, complemented by FastDreamer for asynchronous trajectory handoff, achieves a trajectory RMSE of 0.3492 m and a 74.40 % endpoint success rate on the DiffWAM‑1000 benchmark, with real‑world tests showing complex UAV behaviors and an onboard implementation reaching 1.08 s latency on NVIDIA Jetson AGX Thor.
arXiv Computer Vision
5d ago
WALT: Learning World-Model-Aligned Latent Trajectories for Autonomous Driving
WALT introduces a method to align latent trajectories with pretrained driving world models, creating a compact generative trajectory space that preserves action-relevant semantics without altering the original model. The approach uses a dual-branch autoencoder to map raw waypoints into this latent space and transfers visual world knowledge into trajectory representations. Experiments on NAVSIM benchmarks show modest performance gains and a 30.5% reduction in planner FLOPs, indicating that maintaining world representations while extracting action-relevant information can improve trajectory planning efficiency.
Hugging Face Trending Papers
Jun 23
NavWM: A Unified Navigation World Model for Foresight-Driven Planning
Conventional visual navigation policies often struggle with myopic decision-making and mode collapse in complex environments. While world models offer a promising alternative, existing paradigms typically isolate perception, generation, and control, failing to capture their shared spatio-temporal dynamics.
arXiv AI
Jul 17
FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models
arXiv:2607. 14739v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have achieved impressive results in visuomotor policy learning, yet remain fundamentally reactive, mapping current observations and language to actions without explicit forward prediction of world dynamics.
arXiv Machine Learning
Jun 17
VISTA: Scale-Aware Visual Navigation via Action History Conditioning
arXiv:2606. 17294v1 Announce Type: cross Abstract: Vision Navigation Foundation Models (VNMs) promise end-to-end learned navigation policies capable of zero-shot deployment across diverse embodiments and environments.
arXiv Computer Vision
Sep 3
Spatially Aware World Action Model via Geometric Latent Diffusion
The paper introduces Spatially Aware World Action Model (SA‑WAM), a diffusion‑based framework that extends existing World Action Models by incorporating depth information alongside RGB to enable 3‑D‑aware action and future‑state prediction. SA‑WAM repurposes a pretrained video diffusion model, using a nonlinear encoding to map unbounded depth into the tokenizer’s bounded domain, thus preserving pretrained visual priors without 3‑D‑specific fine‑tuning. The model achieves state‑of‑the‑art performance on RoboCasa and LIBERO‑Plus benchmarks and demonstrates superior real‑world performance on a UR5 robotic arm in randomized environments, while also providing analysis linking world‑model prediction quality to rollout success.
Hugging Face Trending Papers
Aug 10
GeoRoute: Geometry-Aware Hybrid Inference for Traffic Future-Frame Prediction
Long-horizon future-frame prediction is important for autonomous driving, traffic surveillance, and intelligent transportation systems, yet remains challenging due to temporal ghosting, geometry drift, and inconsistent object motion. Recent latent video diffusion models have achieved impressive visual quality, but directly applying them to structured traffic scenes often leads to unstable geometry and degraded temporal coherence over extended horizons.
arXiv AI
Jun 8
Beyond Waypoints: A Trajectory-Centric Waypointing Paradigm for Vision-Language Navigation
arXiv:2606. 07244v1 Announce Type: cross Abstract: Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to follow natural-language instructions while navigating in real-world-like environments.
arXiv AI
Jun 6
WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation
arXiv:2606. 06147v1 Announce Type: new Abstract: End-to-end Vision-Language-Action (VLA) models have shown promise in UAV navigation.
arXiv Machine Learning
Jun 17
Can Vision Foundation Models Navigate? Zero-Shot Real-World Evaluation and Lessons Learned
arXiv:2603. 25937v2 Announce Type: replace-cross Abstract: Visual Navigation Models (VNMs) promise generalizable, robot navigation by learning from large-scale visual demonstrations.