3 papers
cs.CL2026
Lizard: An Efficient Linearization Framework for Large Language Models
Chien Van Nguyen, Huy Nguyen, Ruiyi Zhang +10
We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe co…
cs.LG2025
Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse
Kunjal Panchal, Saayan Mitra, Somdeb Sarkhel +4
Recent advances in video-language models have enabled powerful applications like video retrieval, captioning, and assembly. However, executing such multi-stage pipelines efficientl…
cs.LG2025
DistrAttention: An Efficient and Flexible Self-Attention Mechanism on Modern GPUs
Haolin Jin, Mengbai Xiao, Yuan Yuan +4
The Transformer architecture has revolutionized deep learning, delivering the state-of-the-art performance in areas such as natural language processing, computer vision, and time s…