Flame3D enables zero-shot compositional 3D scene reasoning by representing scenes as editable visual-textual memories exposed to agentic MLLMs through composable and synthesizable spatial tools.
Ar surgical navigation with surface tracing: Comparing in-situ visualization with tool-tracking guidance for neurosurgical applications
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
A dual-tower 4D embodied world model called RoboStereo reduces geometric hallucinations and delivers over 97% relative improvement on manipulation tasks via test-time augmentation, imitative learning, and open exploration.
SpaCE derives four theoretical results on spatial capacity, sample complexity, generalization, and bias-variance trade-offs for multi-frame MLLM reasoning, validated on MultiSPA, CA-VQA, and SpatialRGPT.
User study with 30 novices establishes performance baselines for freehand 5D AR trajectory following and shows orientation constraints create cognitive-motor trade-offs that some visual UIs can mitigate.
Head- and eye-based pointing outperform hand-based methods for AR 2D selection across depths, with head remaining most accurate and consistent.
citing papers explorer
-
Hot Wire 5D+: Evaluating Cognitive and Motor Trade-offs of Visual Feedback for 5D Augmented Reality Trajectories
User study with 30 novices establishes performance baselines for freehand 5D AR trajectory following and shows orientation constraints create cognitive-motor trade-offs that some visual UIs can mitigate.