Running
Reproduction: Markov Chain Monte Carlo without Evaluating the Target
🎯
Explore and share experiment logs with interactive traces
Jansen Tang
ai-sherpa
AI & ML interests
None yet
Recent Activity
updated a Space 4 days ago
ai-sherpa/rate-distortion-memory-bound-repro published a Space 4 days ago
ai-sherpa/rate-distortion-memory-bound-repro updated a Space 4 days ago
ai-sherpa/repro-speedbench-openweights-glm-reproOrganizations
Running
Reproduction: Taming the Loss Landscape of PINNs with Noisy Feynman-Kac Supervision
🎯
Explore project logs and collaborate with a coding agent
Running
Reproduction: Computationally-efficient Graph Modeling with Refined Graph Random Features
🎯
Explore research logbook and sync with AI agent
Running
Repro — Hallucination is a Consequence of Space-Optimality (Rate-Distortion Theorem for Membership Testing)
🎯
Explore and collaborate on a token‑efficient research logbook
Running
Improved Stochastic Optimization of LogSumExp — independent reproduction
🎯
Explore experiment logs with code, traces, and workspace views
Running
Repro - Analytic Bijections for Smooth and Interpretable Normalizing Flows
🎯
Explore and share a project logbook with an AI agent
Running
Repro - MedMosaic
🎯
Explore and edit your project logbook online
Running
Repro — Federated Causal Inference on Multi-Site Observational Data via Propensity Score Aggregation
🎯
Collaborate with an AI coding agent via a shared logbook
Running
Repro — A Capacity-Based Rationale for Multi-Head Attention
🎯
Explore and collaborate on a research logbook online
Running
Repro - MORE
🌐
Track project updates and let an AI agent add findings
Running
Repro - Post-Training with Policy Gradients: Optimality and the Base Model Barrier
🎯
Explore and collaborate on research logbooks with an AI agent
Running
Repro — SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
🎯
Collaborate with an AI agent to view and update a software logbook
Running
Repro — Efficient Inference for Noisy LLM-as-a-Judge Evaluation
🎯
Explore and share LLM evaluation logbooks
Running
Repro — On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise
🎯
Explore and collaborate on research logbooks with an AI assistant
Running
Repro - Robust AI Evaluation through Maximal Lotteries
🎯
Explore AI evaluation logs and sync findings with your coding agent
Running
Repro — Coverage Improvement and Fast Convergence of On-policy Preference Learning
🎯
Explore and sync experiment logs with your coding agent
Running
linear-contracts-sample-complexity
🎯
Explore a logbook and sync with your coding agent
Running
Repro - Optimal Rates for Feasible Payoff Set Estimation in Games
🎯
Explore and collaborate on research logs with an AI agent
Running
Repro - Scalable Bayesian Inference for Nonlinear Conservation Laws (GP-FVM)
🌊
Explore project logbook and sync with your coding agent
Running
Repro - Online Social Welfare Function-based Resource Allocation
🎯
Explore and share experiment logs with an AI coding assistant
Running
Repro — Dynamic Programming for Epistemic Uncertainty in MDPs
🎯
Browse and sync experiment logs with your coding agent
Running
Repro - MEMO
🎯
Browse and sync your project logbook with an AI agent
Running
Repro - Optimal Fair Aggregation of Crowdsourced Noisy Labels using Demographic Parity Constraints
🎯
Aggregate crowdsourced labels fairly with demographic parity
Running
Repro — Covariance estimation using Markov chain Monte Carlo
🎲
Explore and share your MCMC covariance experiment logbook