PACK KWAN LOW PRO
AI & ML interests
Recent Activity
Organizations
NET-01 Boundary Observer
Reproduction: DIYHealth Suite: Dataset, Model, and Benchmark for Health Management at Home
Explore health project logs and collaborate with an agent
Reproduction: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
Explore code, traces, and workspace in an interactive logbook
Reproduction: On the Ability of Transformers to Verify Plans
Explore logs, traces, and workspace with an interactive web logbook
Reproduction: Allocating Variance to Maximize Expectation
Explore project logs, code, and execution traces
HF TOKEN1
Host a simple static web page
Reproduction: A Stronger Benchmark for Online Bilateral Trade: From Fixed Prices to Distributions
Explore code logs, traces, and workspace
Reproduction: A Fully First-Order Layer for Differentiable Optimization
Explore project logs, code, and traces with AI collaboration
Reproduction: A Tight Theory of Error Feedback Algorithms in Distributed Optimization
Explore code, traces, and workspace in an interactive logbook
Reproduction: Social Hippocampus Memory Learning
Explore code logs, traces and workspace with AI collaboration
Reproduction: A Geometric Analysis of Small-sized Language Model Hallucinations
Explore project logs, traces, and workspace in a web UI
Reproduction: (Doubly) Exponential Lower Bounds for Follow the Regularized Leader in Potential Games
Explore code, traces, and workspace in an interactive logbook
Reproduction: Grokking Finite-Dimensional Algebra
Explore project logs, traces and collaborate with an AI agent
Reproduction: Olaf-World: Orienting Latent Actions for Video World Modeling
Explore project logs, code, and traces in an interactive UI
Reproduction: Learning Compressed Shape-Aware Molecular Representations for Virtual Screening
Explore code, traces, and workspace via an interactive logbook
Reproduction: BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series
Explore and manage reproducible research code, traces, and workspace
Reproduction: Probing RLVR Training Instability through the Lens of Objective-Level Hacking
Explore experiment logs, traces, and workspace in a web UI
Reproduction: Curriculum Reinforcement Learning for Black-Box Prompt Tuning via Large Language Models
Explore project logbook: code, traces, workspace
Reproduction: Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
Reproduction: To Grok Grokking: Provable Grokking in Ridge Regression
Explore research logbooks with interactive code and traces
Reproduction: Effective Reasoning Chains Reduce Intrinsic Dimensionality
Explore code logs, traces, and workspace with collaborative logbook
Reproduction: An Interactive Paradigm for Deep Research
Explore research logs and collaborate with your coding agent
Reproduction: CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare
Explore experiment logs and traces in a web interface