Robert Francis PRO

MarxistLeninist

·

AI & ML interests

None yet

Recent Activity

updated a model about 18 hours ago

MarxistLeninist/AGILLM-4.3

updated a model 1 day ago

MarxistLeninist/AGILLM-4.3-repretrain-single-file-20260716T091441Z

updated a Space 5 days ago

MarxistLeninist/repro-GAQE4Wr53f

View all activity

Organizations

MarxistLeninist 's Spaces 107

Repro - Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning

Explore code, traces, and workspace in an interactive logbook

Repro - Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits

Explore and manage streaming bandit experiment logs

Repro - All ERMs Can Fail in Stochastic Convex Optimization: Lower Bounds in Linear Dimension

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

Repro - Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and (L0,L1)-Smoothness

Explore and manage experiment logs with AI collaboration

Repro - SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

Explore benchmark logs, traces, and workspace

Reproduction: Revenue Guarantees of No-Swap-Regret Dynamics in First Price Auctions

Explore code, traces, and workspace of research projects

Repro - Combinatorial Sparse PCA Beyond the Spiked Identity Model

Explore code, traces, and workspace in an interactive logbook

Repro - On Densest k-Subgraph Mining and Diagonal Loading: Optimization Landscape and Finite-Step Exact Convergence Analysis

Explore research logs, code, and execution traces in a web UI

Repro - Towards Optimal Robustness in Learning-Augmented Paging

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

Repro - Learning to Theorize the World from Observation

Explore and manage project logs, code traces, and workspace

Repro - Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems

Explore RL experiment logs and traces in an interactive workspace

Repro - Learning-Augmented Online Covering Problems

Explore and manage experiment logs, code, and traces

Repro - Approximating f-Divergences with Rank Statistics

Explore experiment logs and traces in a collaborative workspace

Repro - Balancing Understanding and Generation in Discrete Diffusion Models

Explore code, traces, and workspace in an interactive logbook

Repro - Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance

Explore project logs, code, and traces in a web interface

Repro - Minimum Distance Summaries for Robust Neural Posterior Estimation

Explore and sync code logs with an AI collaborator

Repro - FlashOptim: Optimizers for Memory-Efficient Training

Explore and manage experiment logs with an interactive UI

Repro - Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis

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

Repro - Ranking Free RAG: Replacing Re-ranking with Selection in RAG for Sensitive Domains

Explore and manage RAG experiment logs with AI collaboration

Repro - Transformers Efficiently Perform In-Context Logistic Regression via Normalized Gradient Descent

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

Repro - Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks

Explore research logbooks with code, traces, and workspace views

Repro - Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with Quantization-Aware Scheduling

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

Repro - NorMuon: Making Muon more efficient and scalable

Explore code logs and collaborate with an AI agent

Repro - Latent Collaboration in Multi-Agent Systems

Sync and view agent logs in an interactive workspace