Search papers, labs, and topics across Lattice.
Georgia Institute of Technology ,
5
0
6
48
A single controller can now robustly learn stochastic transport across a range of initial distribution shifts, outperforming standard SB and noise augmentation on challenging tasks.
A novel inference-time sampling strategy unlocks frontier LLM reasoning capabilities in smaller models by resolving the exploration-exploitation dilemma.
Achieving 6.18-9.44x faster trajectory optimization in multi-agent robotics by dynamically tuning hyperparameters at solve-time could revolutionize real-time robotic applications.
Information-theoretic limits on control performance are now computable even when feedback matters most, thanks to a new bound that self-consistently accounts for the controller's impact on sensor information.
Achieve up to 139x speedup in robust trajectory optimization by exploiting GPU parallelism with custom CUDA kernels and novel optimization architectures.
