activity
20242026
collaborators

9 papers

cs.LG2026

QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction

Vincent Counathe, Ben Athiwaratkun, Christopher De Sa +1

As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential f…

cs.LG2026

Extractable Memorization From First Principles

A. Feder Cooper, Marika Swanberg, Jamie Hayes +5

Recent work on extractable memorization in LLMs suffers from two contrasting validity problems. Some studies overstate extraction, e.g., relying on sequences too short to distingui…

cs.CL2026

Estimating near-verbatim extraction risk in language models with decoding-constrained beam search

A. Feder Cooper, Mark A. Lemley, Christopher De Sa +6

Recent work shows that standard greedy-decoding extraction methods for quantifying memorization in LLMs miss how extraction risk varies across sequences. Probabilistic extraction -…

cs.LG2026

L: Large Lookup Layers

Albert Tseng, Christopher De Sa

Modern sparse language models typically achieve sparsity through Mixture-of-Experts (MoE) layers, which dynamically route tokens to dense MLP "experts." However, dynamic hard routi…

cs.LG2025

Model-Preserving Adaptive Rounding

Albert Tseng, Zhaofeng Sun, Christopher De Sa

The goal of quantization is to produce a compressed model whose output distribution is as close to the original model's as possible. To do this tractably, most quantization algorit…

cs.CL2025

Extracting memorized pieces of (copyrighted) books from open-weight language models

A. Feder Cooper, Mark A. Lemley, Allison Casasola +6

Plaintiffs and defendants in copyright lawsuits over generative AI often make sweeping, opposing claims about the extent to which large language models (LLMs) memorize protected ex…