3 papers
cs.LG2026
FLARE++: Low-rank attention with dynamic attention routing
Vedant Puri, Yongjie Jessica Zhang, Levent Burak Kara
Full self-attention is a strong token mixer for PDE surrogates on irregular domains, but its quadratic cost limits its use on high-resolution problems. Efficient latent-attention m…
cs.LG2026
FLARE: Fast Low-rank Attention Routing Engine
Vedant Puri, Aditya Joglekar, Sri Datta Ganesh Bandreddi +4
The quadratic complexity of self-attention limits the scalability of transformers on long sequences. We introduce Fast Low-rank Attention Routing Engine (FLARE), a token-mixing ope…
physics.flu-dyn2024
SNF-ROM: Projection-based nonlinear reduced order modeling with smooth neural fields
Vedant Puri, Aviral Prakash, Levent Burak Kara +1
Reduced order modeling lowers the computational cost of solving PDEs by learning a low-order spatial representation from data and dynamically evolving these representations using m…