arXiv AI
Jun 15
Planning with the Views via Scene Self-Exploration
arXiv:2605. 29563v2 Announce Type: replace Abstract: Can VLMs predict how each camera move changes the view, and plan many such moves ahead?
Planning with the Views
arXiv:2605. 29563v3 Announce Type: replace Abstract: Can VLMs predict how each camera move changes the view, and plan many such moves ahead?
Related stories
arXiv AI
Jun 30
LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous Driving
arXiv:2606. 29879v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) provide powerful semantic understanding and commonsense reasoning for End-to-End Autonomous Driving (E2E-AD) planning.
arXiv AI
Sep 21
Visual Navigation Transformer with Pose Attention
arXiv:2609.21212v1 Announce Type: cross Abstract: Learned navigation policies typically consume observations as a temporally ordered history, with positional encodings tying each observation to when...
arXiv AI
Sep 16
Seeing What Matters: Visual Cue Guided Video Planning for Generalizable Robot Navigation
arXiv:2609.16737v1 Announce Type: cross Abstract: Generative video models can serve as a promising backbone for robot navigation by predicting future observations as video plans. Recent approaches of...
arXiv AI
Sep 17
Visual Cue Guided Video Planning for Generalizable Robot Navigation
CueNav is a video model-based navigation framework that uses visual cues—a Bird's-Eye View map for global task context and a body-aware egocentric view for embodiment context—to guide a video planner. The framework couples this planner with an embodiment-specific Inverse-Dynamics Model that translates dense flow fields from the video plan into robot actions. Experiments show that CueNav nearly doubles maze navigation success compared to cue-less planning and achieves 70% success in narrow passages, while also supporting zero-shot semantic-conditioned navigation across different robot platforms.
arXiv Computer Vision
Aug 28
Think3D: Thinking with Space for Spatial Reasoning
Think3D introduces a framework that endows Vision‑Language Models with interactive 3D chain‑of‑thought reasoning by integrating 3D manipulation tools for active spatial exploration. The approach improves performance on benchmarks such as BLINK Multi‑view, MindCube‑1K, and VSI‑Bench‑Tiny for proprietary models like GPT‑4.1 and Gemini 2.5 Pro, and a reinforcement‑learning variant, Think3D‑RL, enables open‑weight models such as Qwen3‑VL‑4B to autonomously learn effective 3D exploration strategies, yielding tool‑use patterns comparable to stronger models and turning a performance drop on MindCube‑1K into a substantial improvement.
Hugging Face Trending Papers
Sep 15
Seeing What Matters: Visual Cue Guided Video Planning for Generalizable Robot Navigation
Generative video models can serve as a promising backbone for robot navigation by predicting future observations as video plans. Recent approaches often condition video planning on short-horizon guida...
arXiv AI
Jul 29
Pictura: Perspective-View Self-Play at Scale for Driving
arXiv:2607. 26005v1 Announce Type: cross Abstract: Self-play in simulation produces robust driving policies at scale.
arXiv AI
Jun 2
Bridging the 2D-3D Gap: A Hierarchical Semantic-Geometric Map for Vision Language Navigation
arXiv:2606. 00095v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) enables embodied agents to reach target locations in unseen environments by following language instructions.
arXiv AI
Jul 24
Robostral Navigate
arXiv:2607. 20785v1 Announce Type: cross Abstract: Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently.
arXiv AI
Jul 24
VoLN: Vision-Only Long-Horizon Navigation---Paradigm, Benchmark, and Method
arXiv:2607. 21400v1 Announce Type: cross Abstract: Vision-and-Language Navigation (VLN) enables embodied agents to follow natural-language instructions.
arXiv AI
Jun 17
TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
arXiv:2606. 17386v1 Announce Type: cross Abstract: End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments.