Search papers, labs, and topics across Lattice.
University of South Florida
4
0
9
Runtime safety detection in coding agents can be achieved through a novel intervention in hidden representations, drastically reducing harmful actions during multi-turn interactions.
Kairos achieves top-tier performance in Physical AI while ensuring efficient state management over extended time horizons, setting a new standard for operational world models.
Current LMMs can't reliably turn complex images into code, failing to preserve structural integrity even in relatively simple scenarios, as shown by the new Omni-I2C benchmark.
LLMs struggle with new code frameworks because they lack training data capturing codebase relationships, but this work shows how to synthesize reasoning-aware data from code graphs to dramatically improve performance.
