Hong Seong Pyo

SabaPivot

·

AI & ML interests

AI Safety

Recent Activity

updated a Space about 6 hours ago

SabaPivot/repro-operator-splitting-with-hamilton-jacobi-based-proximals

published a Space about 6 hours ago

SabaPivot/repro-operator-splitting-with-hamilton-jacobi-based-proximals

updated a Space about 6 hours ago

SabaPivot/repro-prescriptive-scaling-reveals-the-evolution-of-language-model-capabilities

View all activity

Organizations

SabaPivot 's Spaces 201

Reproduction: Finite-time Convergence Analysis of Actor-Critic with Evolving Reward

Explore experiment logs and collaborate with an AI agent

Reproduction: Operator Splitting with Hamilton-Jacobi-based Proximals

Explore experiment logs, traces, and workspace in a web UI

Reproduction: Prescriptive Scaling Reveals the Evolution of Language Model Capabilities

Explore logs, traces, and workspace in a web view

Reproduction: Learning-Augmented Online Minimization with Dual Predictions

Explore project logs, traces, and workspace in a web UI

Reproduction: Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving

Explore code logs and collaborate with an AI agent

Reproduction: Provably Data-driven Lagrangian Relaxation for Mixed Integer Linear Programming

Explore experiment logs, code, and traces in an interactive web UI

Reproduction: Budget-Feasible Mechanisms for Submodular Welfare Maximization in Procurement Auctions

Browse code, traces, and workspace in an interactive logbook

Reproduction: Unifying Low Dimensional Spectra in Deep Learning

Explore experiment logs, code, and traces in a web UI

Reproduction: Continuous Variable Hamiltonian Learning at Heisenberg Limit via Displacement-Random Unitary Transformation

Explore code logs and traces with an interactive logbook

Reproduction: MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification

Explore project logs, traces and workspace in a web UI

Reproduction: A theory of learning data statistics in diffusion models, from easy to hard

Explore experiment logs and collaborate with an AI agent

Reproduction: Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling

Explore code, traces, and workspace with collaborative agent support

Reproduction: Context-free Recognition with Transformers

Explore code logs, traces, and workspace in an interactive webbook

Reproduction: Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions

Reproduction: Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis

Explore project logs, traces, and workspace in a web UI

Reproduction: Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates

Explore project logs, code, and traces in an interactive webbook

Reproduction: Formalizing and Falsifying Causal Pathways of Rare Events

Explore and manage reproducible code logs with AI collaboration

Reproduction: Innovation: An Almost Characterization of Hallucination

View and collaborate on code logs with your AI agent

Reproduction: Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints

Explore project logs, traces, and workspace via a web logbook

Reproduction: Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks

Reproduction: Sinkhorn Normalization of Diffusion Kernels

Explore code, traces, and workspace in an interactive logbook

Reproduction: Variational inference via Gaussian interacting particles in the Bures-Wasserstein geometry

Explore and manage research logbooks with interactive traces

Reproduction: The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks

Explore experiment logs and code in an interactive logbook

Reproduction: Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks

Browse experiment logs, traces, and workspace interactively