Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
Decoupling student rollout generation from teacher supervision kernels enables stable on-policy distillation for few-step flow models, outperforming multi-reward GRPO while accelerating convergence.
Frontier coding agents can now write 100% functionally correct GPU physics simulations, yet they match human-expert performance on just 22% of tasks鈥攔evealing a stark capability gap between generating working code and producing performant systems.
Neural PDE solvers no longer need retraining for new boundary conditions: learning domain geometry through its harmonic measure enables zero-shot Poisson solutions via simple re-integration against a single transformer kernel.
