Jerzak Labs

community

https://connorjerzak.com/lab

Activity Feed Request to join this org

AI & ML interests

Planetary causal inference // Text-based AI systems // Adversarial dynamics

Recent Activity

cjerzak authored a paper 1 day ago

ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training

Murjani authored a paper about 2 months ago

AlphaRoute: Large Language Models as Semantic Optimizers for Multi-Objective Routing

Murjani authored a paper about 2 months ago

Drive, Pack, Fly: The Travelling Thief Problem with Drone

View all activity

Papers

ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs

View all Papers

JerzakLabs 's papers 11

ExpertMuon-Compass: Alignment-Guided Step Sizes for Mixture-of-Experts Training

JerzakLabs

Submitted by

Connor T. Jerzak

When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs

JerzakLabs

2

Submitted by

Connor T. Jerzak

Queryable LoRA: Instruction-Regularized Routing Over Shared Low-Rank Update Atoms

JerzakLabs

1

Submitted by

Connor T. Jerzak

Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs

JerzakLabs

Detecting and Mitigating Treatment Leakage in Text-Based Causal Inference: Distillation and Sensitivity Analysis

JerzakLabs

Attenuation Bias with Latent Predictors

JerzakLabs

Benchmarking Debiasing Methods for LLM-based Parameter Estimates

JerzakLabs

Submitted by

Connor T. Jerzak

Selecting Optimal Candidate Profiles in Adversarial Environments Using Conjoint Analysis and Machine Learning

JerzakLabs

fastrerandomize: An R Package for Fast Rerandomization Using Accelerated Computing

JerzakLabs

1

Degrees of Randomness in Rerandomization Procedures

JerzakLabs

Linking Datasets on Organizations Using Half A Billion Open Collaborated Records

JerzakLabs