1

Compares LoRA versus full-parameter finetuning on challenging code and math tasks; sheds light on the learning-forgetting tradeoffs. Showing that LoRA usually underperforms full finetuning in a new target domain while forgetting less of the source domain.

Small on-device LMs guided by frontier cloud-hosted LMs to solve workloads on device at the fraction of the cost.

a collective work of many labs to understand whole-brain-scale electrophysiological recordings.

Introduces a semi-supervised approach to pose estimation, using physically-informed inductive biases to improve generalization with fewer labels. Poses are further refined by combining deep ensembles with state-space models. Open-sourcing a deep learning system that is optimized for efficiency, building on PyTorch Lightning and NVIDIA DALI.

Deriving systematic biases in scalable GPs; eliminating them using Russian-Roulette estimators.

Estimate pose using a CNN; Model pose as a rigid-body system; infer its angular dynamics AND the external torques acting on it using a new nested variant of VSMC.

Use autoencoders to learn latent representations of behavior in videos. Decode neural activity into behavior. Segment behavior into discrete behavioral syllables using AR-HMM.