Efficient AI

Model Compression and Efficient AI

Ravid Shwartz-Ziv's research on model compression, task-aware quantization, efficient representations, and reducing AI memory and computation.

Don't Repeat Yourself: Stopping Verbatim Loops at Sampling Time

Reducing verbatim loops during generation by penalizing tokens that continue a previously seen sequence.

XTC: Head-Aware Sampling by Excluding Top Choices

Encouraging varied text by occasionally excluding dominant choices when several plausible next tokens are available.

UAT-LITE: Inference-Time Uncertainty-Aware Attention for Pretrained Transformers

Making pretrained transformer attention sensitive to uncertainty during inference.

You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations

Compressing an LLM for the task it actually needs to perform, allocating precision to the layers that matter.

NdLinear: Preserving Multi-Dimensional Structure for Parameter-Efficient Neural Networks

Reducing parameter costs with linear transformations that preserve the structure of multidimensional inputs.