Search papers, labs, and topics across Lattice.
4
0
7
2
Model scale is no longer the sole bottleneck for complex causal analysis: pairing RL with simulator-synthesized interventions allows a 35B parameter model to surpass Claude Opus 5 on real-world diagnostic tasks.
This paper proposes World Model RL (WMRL), which replaces environment execution with a world model to remove this bottleneck and accelerates training by 3-4x on various tasks at different agent scales, while exceeding the performance of standard RL baselines.
Non-Lambertian scenes can now be accurately decomposed into reflectance and photometric components without auxiliary inputs, revolutionizing hyperspectral imaging analysis.
Sustained self-improvement in LLM agents is achievable through a novel adaptive framework that outperforms traditional methods in dynamic task environments.
