Running
Reproduction: No More, No Less: Least-Privilege Language Models
🎯
Eric PRO
erobinson
·
AI & ML interests
None yet
Recent Activity
updated a bucket 12 days ago
erobinson/raco-repro-artifacts published a bucket 12 days ago
erobinson/raco-repro-artifacts updated a Space 12 days ago
erobinson/repro-no-more-no-less-least-privilege-language-modelsOrganizations
Running
Reproduction: MM-DeepResearch: A Simple and Effective Multimodal Agentic Search Baseline
🎯
Explore project logs and collaborate with a coding agent
Running
Reproduction: On Uniform Error Bounds for Kernel Regression under Non-Gaussian Noise
🎯
Explore research logbooks with code, traces, and workspace
Running
Reproduction: On the Epistemic Uncertainty of Overparametrized Neural Networks
🎯
Explore code, traces, and workspace in an interactive logbook
Running
Reproduction: Incremental Transformer Neural Processes
🎯
Explore experiment logs, traces, and workspace via web UI
Running
Reproduction: LLM Priors for ERM over Programs
🎯
Explore program logs, traces, and workspace in a collaborative UI
Running
Reproduction: REALISTA
🎯
Explore code, traces and workspace in an interactive logbook
Running
Resting Neurons, Active Insights: Robustifying Activation Sparsity in LLMs via Spontaneity
🎯
Explore and manage experiment logs, code, and traces
Running
structmampose_repro
🎯
Explore project logs, traces, and workspace in a web UI
Running
Reproduction: The Information Geometry of Softmax: Probing and Steering
🎯
Explore project logs, code, and traces via a web interface
Running
Reproduction: UltraLIF: Fully Differentiable Spiking Neural Networks via Ultradiscretization and Max-Plus Algebra
🎯
Explore and manage project logs, traces, and workspace
Running
Reproduction: Learning Permutation from Structure Without Supervision
🎯
Explore project logs, code, and execution traces
Running
Reproduction: Toward Training Superintelligent Software Agents through Self-Play SWE-RL
🎯
Explore code, traces, and workspace in an interactive logbook
Running
Reproduction: Maximum Likelihood Reinforcement Learning
🎯
Explore and manage experiment logs, code, and traces
Running
Reproduction: Recursive Monte-Carlo Tree Search
🎯
Explore logs, traces, and workspace for MCTS experiments
Running
Reproduction: AOEB: Benchmarking Agent-Oriented Multimodal Embeddings
🎯
Browse and collaborate on multimodal embedding benchmark logs
Running
Reproduction: AOEB: Benchmarking Agent-Oriented Multimodal Embeddings
🎯
Explore experiment logs and collaborate with an AI agent
Running
Reproduction: RADAR: Defending RAG Dynamically against Retrieval Corruption
🎯
Explore logs, traces, and workspace with an interactive logbook
Running
Reproduction: Calibrated Test-Time Guidance for Bayesian Inference
🎯
Explore project logs, traces, and workspace in a web view
No application file
Agents
Fastai
🌍