Papers 7

Condensed text with original figures, tables, and equations.

GaussVLA: Geometry-Aware Spatial Reasoning for Vision-Language-Action Model

Robotics · Spatial reasoning · 8 min · 43 citations
Improving Policy Learning via Language-Guided State Representation in World Models

Robotics · 4 min · 47 citations
Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language Models

Language models · 3 min · 43 citations
DELE-w0.5: Inferring Action from Future Latent State for Robotic Manipulation

Robotics · 5 min · 55 citations
HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses

Scientific discovery · 6 min · 55 citations
CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views

Human collaboration · 6 min · 97 citations
GeomVLA: Unifying Scene, Motion, and Action in 3D

Robotics · 6 min · 60 citations