activity
20242026
collaborators

6 papers

cs.LG2026

Entropy-Aligned Decoding of LMs for Better Writing and Reasoning

Kareem Ahmed, Sameer Singh

Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generati…

cs.LG2025

Scaling Tractable Probabilistic Circuits: A Systems Perspective

Anji Liu, Kareem Ahmed, Guy Van den Broeck

Probabilistic Circuits (PCs) are a general framework for tractable deep generative models, which support exact and efficient probabilistic inference on their learned distributions.…

cs.CL2025

Where is the signal in tokenization space?

Renato Lui Geh, Honghua Zhang, Kareem Ahmed +2

Large Language Models (LLMs) are typically shipped with tokenizers that deterministically encode text into so-called canonical token sequences, to which the LLMs assign probability…

cs.LG2024

Controllable Generation via Locally Constrained Resampling

Kareem Ahmed, Kai-Wei Chang, Guy Van den Broeck

Autoregressive models have demonstrated an unprecedented ability at modeling the intricacies of natural language. However, they continue to struggle with generating complex outputs…

cs.LG2024

SIMPLE: A Gradient Estimator for -Subset Sampling

Kareem Ahmed, Zhe Zeng, Mathias Niepert +1

-subset sampling is ubiquitous in machine learning, enabling regularization and interpretability through sparsity. The challenge lies in rendering -subset sampling amenable t…

cs.LG2024

Semantic Loss Functions for Neuro-Symbolic Structured Prediction

Kareem Ahmed, Stefano Teso, Paolo Morettin +8

Structured output prediction problems are ubiquitous in machine learning. The prominent approach leverages neural networks as powerful feature extractors, otherwise assuming the in…