5 papers
The Neverwhere Visual Parkour Benchmark Suite
Ziyu Chen, Henghui Bao, Haoran Chang +12
State-of-the-art visual locomotion controllers are increasingly capable at handling complex visual environments, making evaluating their real-world performance before deployment in…
HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers
Lizhi Yang, Junheng Li, Nehar Poddar +5
Humanoid loco-manipulation benefits from one controller to coordinate locomotion, arm movements, and fall recovery. These behaviors are difficult to learn together from scratch bec…
Lucid-XR: An Extended-Reality Data Engine for Robotic Manipulation
Yajvan Ravan, Adam Rashid, Alan Yu +8
We introduce Lucid-XR, a generative data engine for creating diverse and realistic-looking multi-modal data to train real-world robotic systems. At the core of Lucid-XR is vuer, a…
SpatialTraceGen: High-Fidelity Traces for Efficient VLM Spatial Reasoning Distillation
Gio Huh, Dhruv Sheth, Rayhan Zirvi +1
While Vision-Language Models (VLMs) excel in many areas, they struggle with complex spatial reasoning, which requires problem decomposition and strategic tool use. Fine-tuning smal…
Discovering Hidden Algebraic Structures via Transformers with Rank-Aware Beam GRPO
Jaeha Lee, Gio Huh, Ning Su +1
Recent efforts have extended the capabilities of transformers in logical reasoning and symbolic computations. In this work, we investigate their capacity for non-linear latent patt…