🏗️ Building on HF

Lukas Lozada

neonforestmist

2

·

AI & ML interests

None yet

Recent Activity

new activity 4 days ago

huggingface/InferenceSupport:MiniMaxAI/MiniMax-H3

updated a collection 4 days ago

Image LoRA Library

updated a collection 4 days ago

Image LoRA Library

View all activity

Organizations

neonforestmist 's Spaces 241

The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks

Browse verified claims and evidence for a research paper

Context-free Recognition with Transformers

Explore verified research claims and evidence

Explaining Concept Shift with Interpretable Feature Attribution

Explore verified claims and evidence for research papers

Geometric Entropy and Retrieval Phase Transitions in Continuous Thermal Dense Associative Memory

Browse verified research claims with linked evidence artifacts

Harmful Overfitting in Sobolev Spaces

Show verified paper claims with linked evidence artifacts

Parsimonious Learning-Augmented Online Metric Matching

Explore verified claims and evidence for a research paper

Efficient Preference Poisoning Attack on Offline RLHF

View experiment results and metrics for RLHF attack study

Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO

Run LLM alignment benchmarks and view performance metrics

SURGE: Approximation and Training Free Particle Filter for Diffusion Surrogate

Run a training‑free particle filter to forecast diffusion processes

Causal Representation Learning with Optimal Compression and Complex Treatments

View reproducibility metrics for a research paper

Bilevel Optimization over Saddle Points of Zero-Sum Markov Games

View replication metrics for a zero-sum Markov game paper

TRACE: Trajectory Recovery for Continuous Mechanism Evolution in Causal Representation Learning

Run TRACE reproducibility experiment and see results

Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation

Run amortized simulation inference and see performance metrics

Twice Sequential Monte Carlo for Tree Search

View performance metrics for Twice Sequential Monte Carlo

Adaptive Policy Backbone via Shared Network

Run and view reproducibility metrics for Adaptive Policy Backbone

RoCA: Robust Cross-Domain End-to-End Autonomous Driving

View reproducibility metrics for RoCA autonomous driving paper

Leaderboard Incentives: Model Rankings under Strategic Post-Training

View model ranking leaderboard with performance metrics

Benchmarking World-Model Learning with Environment-Level Queries

View world-model benchmarking results

VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning

Run offline RL benchmarks with value‑function consistency checks

On the Role of Computation in Reinforcement Learning

View reproducibility results for a research paper

Personalized Policy Learning through Discrete Experimentation

View personalized policy learning experiment results

On the Difficulty of Learning a Meta-network for Training Data Selection

View reproducibility metrics for a research paper

Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning

Explore detailed results of tail‑aware flow model fine‑tuning

Desirable Effort Fairness and Optimality Trade-offs in Strategic Learning

View reproducibility status and metrics for research experiments