Nate Mauer PRO
AI & ML interests
Recent Activity
Organizations
Reproducing 147 Machine Learning Papers in 16 Days on One Workstation
Waves, queues, and the three free gates
Picking reproducible papers out of a 6,341-paper haystack
A $0 fine-tuned judge, and the eval that assigned its seat
🏁 The challenge has ended — thank you! (winners soon)
FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time
View and collaborate on a structured logbook with an AI agent
SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation
Explore and collaborate on project logbook with an AI agent
Is the Last Layer Sufficient for Uncertainty Quantification?
Explore research logbook and collaborate with an AI agent
PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space
View and sync a collaborative logbook with your coding agent
A Tale of Two Problems: Multi-Task Bilevel Learning Meets Equality Constrained Multi-Objective Optimization
Collaborate on a research logbook with an AI agent
Distributionally Robust Markov Games with Average Reward
Collaborate on a research logbook with an AI coding agent
Optimal Decision-Making Based on Prediction Sets
Collaborate on a project logbook with an AI coding agent
Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints
View and collaborate on research logbooks online
Theoretical Investigation on Inductive Bias of Isolation Forest
Track research findings in an interactive logbook
A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms
Explore and collaborate on research logbooks
On the Provable Suboptimality of Momentum SGD in Nonstationary Optimization
View and collaborate on experiment logbooks online
The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks
Explore and collaborate on research logbooks online
Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality
Explore research logbook and sync findings with an AI agent
A Perturbation Approach to Unconstrained Linear Bandits
View and sync experiment logs with a coding agent