🧠 AI Research - CWhiting · Scour

NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding ✨Gaussian Splatting

A Deep Layer Limit Analysis of Transformer 🤖LLM

global-sci.com·1d

Congratulations, Dr. Patris! ♟️Game Theory

11011110.github.io·4d

Rejoinder: The ICML 2023 Ranking Experiment: Examining Author Self-Assessment in ML/AI Peer Review 🏆LLM Benchmarking

Is Backpropagation Optimal? When Synthetic Gradients Improve Sample Efficiency ⚡LLM Optimization

LLM-as-a-Reviewer: Benchmarking Their Ability, Divergence, and Prompt Injection Resistance as Paper Reviewers 🏆LLM Benchmarking

SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? 🔬AI for Science

AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training 🏗️LLM Infrastructure

PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers 🏆LLM Benchmarking

Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images 🔌Neural Interfaces

Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation 🤖Game AI

Genetic algorithm vs. gradient descent for training a neural network architecture dedicated to low data regimes in small medical datasets ⚡LLM Optimization

FormInv: A Measurement Protocol for Semantic Invariance in Mathematical Reasoning Benchmarks 🏆LLM Benchmarking

E3: Issue-Level Backtesting for Automated Research Critique 🤨AI Skepticism

Active Continual Learning with Metaplastic Binary Bayesian Neural Networks 🎲Probabilistic Programming

Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption 🌐Archive Topology

Time Series Causal Discovery via Context-Conditioned and Causality-Augmented Pretraining 🧠AI Attribution

Spectral Guidance for Flexible and Efficient Control of Diffusion Models 🎨AI Image Gen

MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR Settings 🏗️LLM Infrastructure

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions 🧠Context Engineering

Log in to enable infinite scrolling