3 citations · 3 across the 4 of their papers we have counts for
5 papers
A Geometric Invariant of Attention Predicts Head Specialization from Weights Alone
Miguel P. Bento
Transformers are built with continuous symmetries in the attention mechanism. We derive , a scalar invariant that measures each head's capacity to couple to rotary positional en…
GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries
Miguel P. Bento, João F. Seabra
Transformers are known to have internal continuous symmetries that leave outputs invariant while altering how activations are distributed across coordinates, and hence how well the…
Solving stiff dark matter equations via Jacobian Normalization with Physics-Informed Neural Networks
M. P. Bento, H. B. Câmara, J. R. Rocha +1
Stiff differential equations pose a major challenge for Physics-Informed Neural Networks (PINNs), often causing poor convergence. We propose a simple, hyperparameter-free method to…
MUSE: Multi-Tenant Model Serving With Seamless Model Updates
Cláudio Correia, Alberto E. A. Ferreira, Lucas Martins +7
In binary classification systems, decision thresholds translate model scores into actions. Choosing suitable thresholds relies on the specific distribution of the underlying model…
Unraveling particle dark matter with Physics-Informed Neural Networks
M. P. Bento, H. B. Câmara, J. F. Seabra
We parametrically solve the Boltzmann equations governing freeze-in dark matter (DM) in alternative cosmologies with Physics-Informed Neural Networks (PINNs), a mesh-free method. T…