Search papers, labs, and topics across Lattice.
Affiliation:
7
0
11
Categorical value learning can significantly enhance the performance of PPO critics in reinforcement learning, leading to better calibration and lower variance in advantage estimation.
General LLMs struggle with enzyme classification, but leveraging external knowledge can dramatically improve their performance, revealing hidden gaps in reasoning capabilities.
WorldEvolver redefines LLM agent planning by achieving unprecedented prediction accuracy and decision-making success through self-evolving memory mechanisms.
Flash-WAM achieves real-time inference for world-action models by reducing latency from 8.1 seconds to 348 milliseconds without sacrificing performance.
DKnownAI Guard blows away AWS, Azure, and Lakera in head-to-head security tests for AI agents.
Unlock geometric reasoning in MLLMs by parsing diagrams into a unified formal language that spans both 2D and 3D geometry.
