Hong Seong Pyo

SabaPivot

·

AI & ML interests

AI Safety

Recent Activity

updated a Space 2 days ago

SabaPivot/repro-a-formal-comparison-between-chain-of-thought-and-latent-thought

updated a Space 2 days ago

SabaPivot/repro-facts-in-stats-impacts-of-pretraining-diversity-on-language-model-generalization

updated a Space 2 days ago

SabaPivot/repro-dissecting-multimodal-in-context-learning-modality-asymmetries-and-circuit-dynamics-in-mod

View all activity

Organizations

SabaPivot 's Spaces 321

Reproduction: Calibrated Preference Learning: The Case of Label Ranking

Explore code, traces, and workspace in an interactive logbook

Reproduction: Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently

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

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

Explore code, traces, and workspace in an interactive logbook

Reproduction: MASH: Modeling Abstention via Selective Help-Seeking

Explore research logs, traces, and workspace online

Reproduction: Neural Quantum States in Mixed Precision

Explore experiment logs and traces in a web workspace

Reproduction: Provably Learning Attention with Queries

Explore logs, traces, and workspace in an interactive web UI

Reproduction: On the Accuracy of Newton Step and Influence Function Data Attributions

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

Reproduction: Innovation: An Almost Characterization of Hallucination

Explore and collaborate on project logs with an AI agent

Reproduction: Prescriptive Scaling Reveals the Evolution of Language Model Capabilities

Explore logs, traces, and workspace in a web view

Reproduction: Sinkhorn Normalization of Diffusion Kernels

Explore code, traces, and workspace in an interactive logbook

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

Explore experiment logs and code in an interactive logbook

Reproduction: Optimal Design for Multinomial Logit Model with Applications to Best Assortment Identification

Browse project logs, code, and traces interactively

Reproduction: Allocating Variance to Maximize Expectation

Explore and collaborate on code logs and traces

Reproduction: Commit to the Bit: Reactive Reinforcement Learning Done Right

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

Reproduction: Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments

Explore code, traces, and workspace in an interactive logbook

Reproduction: Semi-knockoffs: a model-agnostic conditional independence testing method with finite-sample guarantees

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

Reproduction: Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety

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

Reproduction: Quantifying the noise sensitivity of the Wasserstein metric for images

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

Explore and manage experiment logs with an interactive web UI

Reproduction: Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation

Explore research logbook with code, traces, and workspace

Reproduction: Robust and Consistent Ski Rental with Distributional Advice

Explore experiment logs and code traces in an interactive UI

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

View and collaborate on experiment logs with an AI agent

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

Explore code logs, traces, and workspace with collaborative logbook