Hong Seong Pyo

SabaPivot

·

AI & ML interests

AI Safety

Recent Activity

updated a Space about 18 hours ago

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

updated a Space about 18 hours ago

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

updated a Space about 19 hours ago

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

View all activity

Organizations

SabaPivot 's Spaces 321

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: Improved Bounds for Private and Robust Alignment

Explore logs and sync notes with an AI coding agent

Repro - Generalized (Ỹ-tilde) Convex Functions and Their Gradients

Explore convex functions and gradients in an interactive logbook

Reproduction: Facts in Stats: Impacts of Pretraining Diversity on Language Model Generalization

Explore project logs, traces, and workspace in one view

Reproduction: Beyond Rational Illusion: Behaviorally Realistic Strategic Classification

Explore project logs, code, and traces in an interactive web logbook

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

Explore and sync a research logbook with your AI agent

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

Explore research logbook and sync with AI agent

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

Explore and manage project logs, code, and traces

Reproduction: Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP

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

Reproduction: LILO: Bayesian Optimization with Natural Language Feedback

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

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

Explore logs, traces, and workspace in a collaborative UI

Reproduction: Distributed Direct Preference Optimization

Explore and collaborate on research logbooks online

Reproduction: GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent

Explore and manage experiment logs in a collaborative UI

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

Explore code, traces, and workspace in an interactive logbook

Reproduction: Computationally-efficient Graph Modeling with Refined Graph Random Features

Explore experiment logs and collaborate with a coding agent

Reproduction — Exact Unlearning in Reinforcement Learning

Explore experiment logs and sync notes with your coding agent

Reproduction: A Capacity-Based Rationale for Multi-Head Attention

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

Repro - Scalable Bayesian Inference for Nonlinear Conservation Laws (GP-FVM)

Explore and collaborate on your research logbook

Repro — Non-Euclidean Gradient Descent Operates at the Edge of Stability

Explore and share experiment logs with an AI agent

Reproduction: Statistical Early Stopping for Reasoning Models

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

Reproduction: Efficient Bayesian Inference from Noisy Pairwise Comparisons

Explore code, traces, and workspace in an interactive logbook

Reproduction: MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems

Explore code, traces, and workspace in an interactive logbook

Reproduction: HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models

Explore research logs, code, and traces in an interactive web logbook