Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
7
0
8
6
Explicit 3D geometry, rendered as text, unlocks superior spatial reasoning in RGB-only VLMs by guiding trajectory correction during distillation.
Visual-native skill cards, directly accessible to VLMs, unlock a self-reinforcing loop of policy improvement and skill accumulation, drastically boosting sample efficiency.
Even the best vision-language models struggle with predictive spatial reasoning, scoring less than 60% on a new benchmark designed to test anticipating unseen outcomes.
Gaussian guidance reveals that optimal trajectory retention depth varies across tasks, leading to a substantial performance boost in reinforcement learning.
Relay-OPD not only corrects reasoning missteps in real-time but also slashes training time by over half, setting a new standard for on-policy distillation efficiency.
Decoupling perception from reasoning in visual tasks leads to a remarkable 93.2% accuracy on V-Star, showcasing a new paradigm for fine-grained visual reasoning.
Forget noisy pseudo-labels: SpatialEvo unlocks self-supervised 3D spatial reasoning by generating perfectly accurate training data directly from scene geometry.