Search papers, labs, and topics across Lattice.
3
1
7
3
LLM agents can enhance training-data strategies in over half of their attempts, but their inconsistency reveals critical limitations in recursive self-improvement.
Video generators may convincingly simulate real-world dynamics, but they often fail to understand the underlying causal relationships, revealing a critical gap in their reasoning capabilities.
LLMs can learn to generate high-quality symbolic world models by interacting with a multi-agent system that provides adaptive, behavior-aware feedback, closing the gap between static validation and interactive execution.
