Hong Seong Pyo

SabaPivot

·

AI & ML interests

AI Safety

Recent Activity

updated a bucket 4 minutes ago

SabaPivot/repro-robust-rhi-upgrades

updated a bucket 4 minutes ago

SabaPivot/repro-context-free-recognition-upgrades

published a bucket 4 minutes ago

SabaPivot/repro-context-free-recognition-upgrades

View all activity

Organizations

SabaPivot 's Spaces 221

Reproduction: A Perturbation Approach to Unconstrained Linear Bandits

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

Reproduction: Floating-Point Networks with Automatic Differentiation Can Represent Almost All Floating-Point Functions and Their Gradients

Explore code logs and trace runs in an interactive workspace

Reproduction: Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality

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

Reproduction: The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity

Explore project logs, code, and traces interactively

Reproduction: Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond

Explore logbooks with code, traces, and workspace view

Reproduction: Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification

Explore and manage experiment logs with an interactive web UI

Reproduction: Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence

Explore code logs, traces, and workspace with AI collaboration

Reproduction: Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation

Explore research logbook with code, traces, and workspace

Reproduction: Improved Stochastic Optimization of LogSumExp

Explore experiment logs and traces in an interactive dashboard

Reproduction: Robust and Consistent Ski Rental with Distributional Advice

Explore experiment logs and code traces in an interactive UI

Reproduction: Rotary Position Encodings for Graphs

Explore code, traces, and workspace in an interactive logbook

Reproduction: HybridFlow: Resource-Adaptive Subtask Routing for Efficient Edge-Cloud LLM Inference

View and collaborate on experiment logs with an AI agent

Reproduction: DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents

Explore project logs, code, and traces with AI collaboration

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

Explore AI experiment logs and trace executions

Reproduction: Prior Diffusiveness and Regret in the Linear-Gaussian Bandit

Explore code logs, traces, and workspace with collaborative logbook

Reproduction: Joint Learning in the Gaussian Single Index Model

Explore code, traces, and workspace in an interactive logbook

Reproduction: High-Probability Convergence Guarantees of Decentralized SGD

Explore code logs, traces, and workspace in a web logbook

Reproduction: Parameter-free Dynamic Regret: Time-varying Movement Costs, Delayed Feedback, and Memory

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

Reproduction: Is Spurious Correlation Removal Always Learnable?

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

Reproduction: Graph Alignment for Benchmarking Graph Neural Networks and Learning Positional Encodings

Explore code, traces and workspace in an interactive logbook

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

Track research findings with an AI‑assisted logbook

Reproduction: Token Sample Complexity of Attention

Explore code logs and collaborate with an AI agent

Reproduction: Are Two Datasets Close Enough With Statistical Significance? A Kernel Distributional Closeness Testing Approach

Explore experiment logs, view code and collaborate with an AI agent

Reproduction: Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in Modern Transformers

Explore experiment logs and sync findings with an AI agent