activity
20242026
collaborators

6 papers

cs.LG2026

The Key to Going Linear: Analysis-Driven Transformer Linearization

Anna Kuzina, Paul N. Whatmough, Babak Ehteshami Bejnordi

The quadratic cost of causal self-attention severely bottlenecks long-context transformer inference. While numerous post hoc linearization pipelines exist, it is difficult to ident…

cs.LG2026

Efficient Reasoning on the Edge

Yelysei Bondarenko, Thomas Hehn, Rob Hesselink +15

Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art performance across complex problem-solving tasks, but their verbose reasoning traces and large…

cs.LG2026

KaVa: Latent Reasoning via Compressed KV-Cache Distillation

Anna Kuzina, Maciej Pioro, Paul N. Whatmough +1

Large Language Models (LLMs) excel at multi-step reasoning problems with explicit chain-of-thought (CoT), but verbose traces incur significant computational costs and memory overhe…

cs.LG2025

Dirichlet-Prior Shaping: Guiding Expert Specialization in Upcycled MoEs

Leyla Mirvakhabova, Babak Ehteshami Bejnordi, Gaurav Kumar +3

Upcycling pre-trained dense models into sparse Mixture-of-Experts (MoEs) efficiently increases model capacity but often suffers from poor expert specialization due to naive weight…

cs.LG2025

Mixture of Cache-Conditional Experts for Efficient Mobile Device Inference

Andrii Skliar, Ties van Rozendaal, Romain Lepert +5

Mixture of Experts (MoE) LLMs have recently gained attention for their ability to enhance performance by selectively engaging specialized subnetworks or "experts" for each input. H…

cs.CL2024

Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design

Ruisi Cai, Yeonju Ro, Geon-Woo Kim +4

The proliferation of large language models (LLMs) has led to the adoption of Mixture-of-Experts (MoE) architectures that dynamically leverage specialized subnetworks for improved e…