collaborators

7 papers

cs.LG2026

Tree-Structured Orthonormal Decomposition of the Aitchison Simplex

Daisuke Yamada, Qijun Zhang, Travis Pence +3

Compositional data -- vectors encoding relative proportions -- arise across scientific domains, including ecology, geochemistry, and genomics. The features in these data often come…

cs.LG2026

Recursive Binding on a Budget: Subspace Carving in Order-p Tensor Memories

Travis Pence, Daisuke Yamada, Vikas Singh

Tensor Product Representations provide the structural fidelity required for symbolic reasoning in models but suffer from exponential dimensionality growth when encoding deep recurs…

cs.LG2026

Composing Linear Layers from Irreducibles

Travis Pence, Daisuke Yamada, Vikas Singh

Contemporary large models often exhibit behaviors suggesting the presence of low-level primitives that compose into modules with richer functionality, but these fundamental buildin…

cs.CL2025

Concept Attractors in LLMs and their Applications

Sotirios Panagiotis Chytas, Vikas Singh

Large language models (LLMs) often map semantically related prompts to similar internal representations at specific layers, even when their surface forms differ widely. We show tha…

cs.LG2025

CafeQ: Calibration-free Quantization via Learned Transformations and Adaptive Rounding

Ziteng Sun, Adrian Benton, Samuel Kushnir +4

Post-training quantization is an effective method for reducing the serving cost of large language models, where the standard approach is to use a round-to-nearest quantization leve…

cs.LG2025

FoGE: Fock Space inspired encoding for graph prompting

Sotirios Panagiotis Chytas, Rudrasis Chakraborty, Vikas Singh

Recent results show that modern Large Language Models (LLM) are indeed capable of understanding and answering questions about structured data such as graphs. This new paradigm can…