🏗️ Building on HF

Lukas Lozada

neonforestmist

·

AI & ML interests

None yet

Recent Activity

updated a model 3 days ago

neonforestmist/smolgpt-fables

updated a model 3 days ago

neonforestmist/Clover-Image-Tiny

updated a model 6 days ago

neonforestmist/Clover-Image-Tiny-Inpaint

View all activity

Organizations

neonforestmist 's Spaces 241

Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problems

Sample complex distributions using zeroth‑order variance‑reduced method

Trajectory-Level Data Augmentation for Offline Reinforcement Learning

Evaluate trajectory-level data augmentation for offline RL

Multivariate Distributional Reinforcement Learning Using Sliced Divergences

View reproducibility results for a reinforcement learning study

Causal-EPIG: Causally Aligned Active CATE Estimation

Estimate causal effects with active CATE algorithm

SciAgentGym: Benchmarking Multi-Step Scientific Tool-Use in LLM Agents

Run scientific tool-use benchmarks for LLM agents

Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning

Browse reproducibility metrics for a multi‑agent RL study

The Geometry of Updates: Fisher Alignment at Vocabulary Scale

Track and display ML experiment results and metrics

Sparse Bayesian Deep Functional Learning with Structured Region Selection

Run sparse Bayesian deep learning forecasts on your data

Moving Out: Physically-grounded Human-AI Collaboration

View benchmark results for the Moving Out experiment

Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients

Explore reproducibility results for ML research papers

The Theory and Practice of MAP Inference over Non-Convex Constraints

Explore reproducibility results for a research paper

Squeezing More from the Stream : Learning Representation Online for Streaming Reinforcement Learning

View streaming RL experiment results and metrics online

CyberGym-E2E: Scalable Real-World Benchmark for AI Agents' End-to-End Cybersecurity Capabilities

Benchmark AI agents' end-to-end cybersecurity performance

NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search

Run interaction‑guided multi‑agent MCTS for better decisions

Efficient Stochastic Optimisation via Sequential Monte Carlo

Show reproducibility metrics for stochastic optimization study

Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking

View reproducibility metrics for a two‑stage ranking paper

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

View detailed reproducibility results for OGPO experiments

$ ext{DT}^ ext{2}$: Decision-Targeted Digital Twins

View results of the DT² Decision-Targeted Digital Twins experiment

Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling

Reproduce and view RLHF reward‑modeling experiment results

StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learni

Generate optimized CUDA code using an automated multi‑agent system

MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification

View detailed reproducibility results for a research experiment

Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance

View reproducibility results for a research paper

Meta-Black-Box Optimization Can Do Search Guidance for Expensive Constrained Multi-Objective Optimization

Show experiment results for a research paper

Variational inference via Gaussian interacting particles in the Bures-Wasserstein geometry

View reproducibility results for a variational inference paper