Government
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
Large Language Models (LLMs) are distinguished by their massive parameter counts, which typically result in significant redundancy.
Neural Isometries: Taming Transformations for Equivariant ML
Specifically, we regularize the latent space such that maps between encodings preserve a learned inner product and commute with a learned functional operator, in the same manner as rigid-body transformations commute with the Laplacian.
BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
Alignment method inspired by an analogy with the concept of backdoor attacks. In particular, service providers will construct prefixed safety examples with a secret prompt, acting as a "backdoor trigger".
Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
Recent studies have revealed that properties of training trajectories can be indicative of generalization.
SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting
However, the cloud induced-variability of solar radiation reaching the earth's surface presents a challenge for integrating solar power into the grid (e.g., storage and backup management).
