Hong Seong Pyo

SabaPivot

·

AI & ML interests

AI Safety

Recent Activity

updated a Space about 1 hour ago

SabaPivot/repro-clipped-asgd

updated a Space about 2 hours ago

SabaPivot/repro-finetuning-without-forgetting-icl

updated a Space about 3 hours ago

SabaPivot/repro-budget-feasible-mechanisms-for-submodular-welfare-maximization-in-procurement-auctions

View all activity

Organizations

SabaPivot 's Spaces 261

Reproduction: A Perturbation Approach to Unconstrained Linear Bandits

Explore and manage experiment logs with agent collaboration

Reproduction: Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo

Explore reproducible research logs in an interactive web UI

Reproduction: Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation

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

Reproduction: A Formal Comparison Between Chain of Thought and Latent Thought

Browse and collaborate on a structured logbook with AI agents

Reproduction: Reward-free Alignment for Conflicting Objectives

Browse experiment logs, code, and traces in an interactive logbook

Repro - Stability Analysis of Sharpness-Aware Minimization

Explore experiment logs and sync findings with your AI agent

Reproduction: Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers

Explore experiment logs and collaborate with an AI agent

Reproduction: Online Social Welfare Function-based Resource Allocation

Track and share research findings with an AI agent

Repro - Lipschitz Continuous Transformers

Explore and sync experiment logbook with your coding agent

Reproduction: Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift

Explore experiment logs, code, and traces in an interactive logbook

Repro - Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models

Collaborate on research notes with an AI coding agent

Reproduction: Beyond Model Ranking: Predictability-Aligned Evaluation for Time Series Forecasting

Explore and manage experiment logs with an interactive web logbook

Reproduction: On the Power of (Approximate) Reward Models for Inference-Time Scaling: Sequential Monte Carlo and Beyond

Explore and manage project logs, traces, and workspace

Reproduction: BlitzRank: Principled Zero-shot Ranking Agents with Tournament Graphs

View and sync experiment logs with an AI coding agent

Reproduction: Olaf-World: Orienting Latent Actions for Video World Modeling

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

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

Explore and sync research logbook with your coding agent

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

Explore research logbook and collaborate with an AI agent

Reproduction: Token Sample Complexity of Attention

View and collaborate on a token‑efficient logbook

Reproduction: Learning, Solving and Optimizing PDEs with TensorGalerkin: an efficient high-performance Galerkin assembly algorithm

Explore code, traces, and workspace with a web logbook

Reproduction: ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters

Explore research logbook with code, traces, and workspace

Reproduction: Beyond Structural Symmetries: Linear Mode Connectivity via Neuron Identifiability

Explore project logs, traces, and workspace online

Reproduction: Richer Bayesian Last Layers with Subsampled NTK Features

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

Reproduction: On the Power of Source Screening for Learning Shared Feature Extractors

Organize and sync research notes with an AI coding agent

Reproduction: Accuracy-First Rényi Differential Privacy and Post-Processing Immunity

Explore project logbook and sync with coding agent