João Sacramento
15 papers · 2018–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot (3) 🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (12)
🏃
Academic Marathon
(7)
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(12)
🏆
Keyword Champion
(5)
💎
Century Club
(15)
🔥
Unstoppable
(6)
Conferences
NIPS (8)
ICLR (5)
ICML (2)
Top co-authors
Keywords
credit assignment
(5)
neural network optimization
(3)
gauss-newton optimization
(2)
biological plausibility
(2)
recurrent neural network
(2)
synaptic plasticity
(2)
continual learning
(2)
neural network
(2)
local learning
(1)
gradient estimation
(1)
bayesian inference
(1)
posterior distribution
(1)
optimal control
(1)
hierarchical representation
(1)
few-shot learning
(1)
deep learning
(1)
bayesian learning
(1)
cortical circuits
(1)
in-context learning
(1)
gradient descent
(1)
Papers
Attention as a Hypernetwork
ICLR 2025
Multi-agent cooperation through learning-aware policy gradients
ICLR 2025
Discovering modular solutions that generalize compositionally
ICLR 2024
Transformers Learn In-Context by Gradient Descent
ICML 2023
Online learning of long-range dependencies
NIPS 2023
The least-control principle for local learning at equilibrium
NIPS 2022
A contrastive rule for meta-learning
NIPS 2022
Minimizing Control for Credit Assignment with Strong Feedback
ICML 2022
Credit Assignment in Neural Networks through Deep Feedback Control
NIPS 2021
Posterior Meta-Replay for Continual Learning
NIPS 2021
Neural networks with late-phase weights
ICLR 2021
Learning where to learn: Gradient sparsity in meta and continual learning
NIPS 2021
A Theoretical Framework for Target Propagation
NIPS 2020
Continual learning with hypernetworks
ICLR 2020
Dendritic cortical microcircuits approximate the backpropagation algorithm
NIPS 2018