🏗️ Building on HF

Lukas Lozada

neonforestmist

1

·

AI & ML interests

None yet

Recent Activity

updated a model 1 day ago

neonforestmist/Clover-Image-Tiny-CoreML

updated a model 2 days ago

neonforestmist/krea-2-watercolor-anime-lora

published a model 2 days ago

neonforestmist/krea-2-watercolor-anime-lora

View all activity

Organizations

neonforestmist 's Spaces 241

Reusing Trajectories in Policy Gradients Enables Fast Convergence

Browse claim verification status for research papers

Online Packet Scheduling with Deadlines and Learning

Explore verified claims and evidence for a research paper

Questioning the Coverage-Length Metric in Conformal Prediction: When Shorter Intervals Are Not Better

Explore verified research claims with linked evidence

Solving Imperfect-Recall Games via Sum-of-Squares Optimization

Explore verified claims and evidence for a research paper

Linear Regression with Unknown Truncation Beyond Gaussian Features

Explore verified research claims with linked evidence

An Odd Estimator for Shapley Values

Explore verified claims and evidence for a research paper

Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learning

Explore verified paper claims with linked evidence artifacts

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation B

Explore verified research claims with linked evidence

Steady-State Behavior of Constant-Stepsize Stochastic Approximation: Gaussian Approximation and Tail Bounds

Explore verified paper claims with linked evidence

Sinkhorn Normalization of Diffusion Kernels

Explore verified paper claims and evidence artifacts

Model-Free Robust Average-Reward Reinforcement Learning with Sample Complexity Analysis

Explore verified claims and evidence for a research paper

Adaptively Robust Resettable Streaming

Explore verified research claims with linked evidence

Understanding Behavior Cloning with Action Quantization

Explore verified research claims and view supporting evidence

Pseudo-Mallows for Efficient Probabilistic Preference Learning

Explore verified research claims with linked evidence artifacts

Provably Data-driven Multiple Hyper-parameter Tuning with Structured Loss Function

Explore verified claims and evidence for a research paper

Improved Bounds for Private and Robust Alignment

View verified research claims with linked evidence

Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness, and Safety

Explore verified claims and evidence for a research paper

Efficient and Minimax Optimal In-context Nonparametric Regression with Transformers

Browse and verify research paper claims with linked evidence

Two-Layer Linear Auto-Regressive Models Estimate Latent States

Browse verified claims and evidence for a research paper

The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity

Explore verified paper claims with linked evidence artifacts

Innovation: An Almost Characterization of Hallucination

Explore verified claims and evidence for research papers

Decentralized Online Convex Optimization with Efficient Communication: Improved Algorithm and Lower Bounds

Explore verified claims and evidence for a research paper

Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models

Browse verified paper claims with linked evidence artifacts

HiPPO Zoo: Explicit Memory Mechanisms for Interpretable State Space Models

Explore verified claims and evidence for a research paper