🧠 AI Research - obaqueiro · Scour

Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway

⚙️ML Engineering Academic

Second-Order Path Kernel Interpolation Formulas in Machine Learning

⚙️ML Engineering Academic

Exploring the Design Space of Reward Backpropagation for Flow Matching

🤖AI Academic

Multilevel Stochastic Gradient Descent for Risk-Averse PDE-Constrained Optimization

🎓Computer Science Academic

SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration

🛡️AI Safety Academic

From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments

🤖AI Academic

Fourier fractal dimension to predict the generalization of deep neural networks

⚙️ML Engineering Academic

In Defense of Information Leakage in Concept-based Models

⚙️ML Engineering Academic

Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences

💬LLMs Academic

Divide-and-Conquer Modeling for the CTF-4-Science Lorenz Benchmark

⚙️MLOps Academic

IR3DE: A Linear Router for Large Language Models

💬LLMs Academic

PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning

🏗️System Design Academic

Uniform Stability and Generalization Error of GD and SGD on Fixed-Point Parameters

⚙️ML Engineering Academic

Exact Unlearning in Reinforcement Learning

🤖AI Academic

Dynamic Linear Attention

🤖AI Academic

FAIR-Calib: Frontier-Aware Instability-Reweighted Calibration for Post-Training Quantization of Diffusion Large Language Models

⚙️ML Engineering Academic

Overcoming Rank Collapse in Feedback Alignment

⚙️ML Engineering Academic

Skip a Layer or Loop It? Learning Program-of-Layers in LLMs

💬LLMs Academic

A prism hierarchy of learning regimes in large linear autoencoders

💬LLMs Academic

ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity

🛡️AI Safety Academic

arxiv.org··Hacker News

Log in to enable infinite scrolling