activity
20242026
collaborators

9 papers

cs.AR2026

Architecture Carbon Tool v3: Enabling Sustainability-aware Silicon System Design Exploration

Vincent T. Lee, Bilge Acun, Zachary Lewis +1

As the carbon cost of manufacturing and operating semiconductor devices has come into sharper focus, sustainability has gradually emerged as a new system architecture design metric…

cs.AI2026

Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design

Alberto Pepe, Chien-Yu Lin, Despoina Magka +5

Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-framework approach: AIRA-Com…

cs.CL2026

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights

Sangmin Bae, Bilge Acun, Chien-Yu Lin +5

Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a co…

cs.LG2026

Composer: A Search Framework for Hybrid Neural Architecture Design

Bilge Acun, Prasoon Sinha, Newsha Ardalani +7

Hybrid model architectures that combine computational primitives (e.g., Attention, MLP) in different ratios have shown promising performance beyond Transformers. Some studies have…

cs.CL2026

Scalable LLM Reasoning Acceleration with Low-rank Distillation

Harry Dong, Bilge Acun, Beidi Chen +1

Due to long generations, large language model (LLM) math reasoning demands significant computational resources and time. While many existing efficient inference methods have been d…

cs.LG2026

Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths

Xuezhe Ma, Shicheng Wen, Linghao Jin +11

Designing a unified neural network to efficiently and inherently process sequential data with arbitrary lengths is a central and challenging problem in sequence modeling. The desig…