Running
Reproduction: On the Theory of Continual Learning with Gradient Descent for Neural Networks
🎯
Explore project logs, traces, and workspace in a web UI
Hong Seong Pyo
SabaPivot
AI & ML interests
AI Safety
Recent Activity
updated a Space 9 days ago
SabaPivot/repro-a-formal-comparison-between-chain-of-thought-and-latent-thought updated a Space 9 days ago
SabaPivot/repro-facts-in-stats-impacts-of-pretraining-diversity-on-language-model-generalization updated a Space 9 days ago
SabaPivot/repro-dissecting-multimodal-in-context-learning-modality-asymmetries-and-circuit-dynamics-in-modOrganizations
Running
Repro — Doubly Regularized Markov Decision Processes for Robust Reinforcement Learning
🛡
Track RL experiments and sync findings with an AI agent
Running
Repro — Dense associative memory on the Bures-Wasserstein space
🎯
Browse and collaborate on experiment logs with an AI agent
Running
Reproduction: Loss-Aware Distributionally Robust Optimization via Trainable Optimal Transport Ambiguity Sets
🎯
Explore research logs and collaborate with an AI agent
Running
Reproduction: Learning U-Statistics with Active Inference
🎯
Track and explore your research experiments in a web logbook
Running
Repro - The Geometry of Projection Heads: Conditioning, Invariance, and Collapse
🎯
Browse and collaborate on a research logbook with an AI agent
Running
Reproduction: Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
🎯
Explore experiment logs and collaborate with an AI agent
Running
Reproduction: Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation
🎯
Browse experiment logs, code, and traces with an interactive logbook
Running
Reproduction: Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
🎯
Browse code logs, traces, and workspace with AI collaboration
Running
Reproduction: Delayed Momentum Aggregation: Communication-efficient Byzantine-robust Federated Learning with Partial Participation
🎯
Explore code, traces, and workspace in an interactive logbook
Running
Repro - Deep Networks Learn to Parse Uniform-Depth Context-Free Languages from Local Statistics
🎯
Browse experiment logs and collaborate with your agent
Running
Repro - Adaptive Personalized Federated Learning via Multi-task Averaging of Kernel Mean Embeddings
🎯
Track research findings with an interactive logbook
Running
Repro — Average Percentile Upper Bound (APUB) for Data-Driven Stochastic Programming
🎯
Explore and share experiment logs with your coding agent
Running
Repro — Bandit Social Learning with Exploration Episodes (EpiBSL)
🎯
Explore and collaborate on experiment logbooks online
Running
Repro — Human-AI Collaborative Uncertainty Quantification
🎯
Collaborate with an AI agent via a shared logbook
Running
Repro - SoftJAX & SoftTorch: Empowering Automatic Differentiation Libraries with Informative Gradients
🎯
Collaborate on a coding logbook with your AI agent
Running
Repro — Full-Batch GD Outperforms One-Pass SGD (Single-Index Learning)
🎯
Explore research logs and sync notes with your coding agent
Running
Repro - On the Convergence Rate of LoRA Gradient Descent
🎯
Explore research logbook and sync notes with a coding agent
Running
Repro - Upper-Linearizability of Online Non-Monotone DR-Submodular Maximization over Down-Closed Convex Sets
🎯
View and sync research logs with a coding agent
Running
Repro — Optimal Transport under Group Fairness Constraints (FairSinkhorn)
🎯
Explore experiment logs and sync findings with an AI agent
Running
Repro — Incentivized Exploration with Stochastic Covariates (RCB)
🎯
Explore and sync experiment logs with an AI coding agent
Running
Repro - VLM-RobustBench
🖼
Log and share experiment findings with an AI agent
Running
Repro - SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework
🎯
Collaborate on a project logbook with an AI agent
Running
Reproduction: CodeTaste: Can LLMs Generate Human-Level Code Refactorings?
🎯
Explore code logs, traces and collaborate with an AI agent