Larry (Peilin) Zhong Larryzpl123
- Pittsburgh
-
08:49
(UTC -04:00) - https://linktr.ee/LarryZPL
- https://orcid.org/0009-0006-5542-8057
- in/larry-zhong
Lists (5)
Sort Name ascending (A-Z)
Stars
Repo that uses Propublica data to reveal schools beyond ads and rankings
A vibe coded repo that connects to the Propublica Nonprofit Database and gets information about schools, so that you learn about schools beyond their advertisement and black box rankings.
Rya1cc / yt-dlp
Forked from yt-dlp/yt-dlpA feature-rich command-line audio/video downloader
A tcg game website about Vocaloid (And of course SynthesizerV, UTAU songs)
G-a-m-e / ufo-attack
Forked from Larryzpl123/ufo-attackPlane Shooter: UFO Attack
G-a-m-e / ryuu-play
Forked from keeshii/ryuu-playSimulator for the Pokémon Trading Card Game
Simulator for the Pokémon Trading Card Game
sat-practice tools
Configurable BSM2 wastewater-plant simulation harness: clean baselines, compliance-risk scenarios (incl. sludge bulking), synthetic influent, realistic sensors, phosphorus engine, and plant power-u...
neurolibre / neurolibre-neo
Forked from openjournals/jossNeuroLibre Preprint Server
Synthetic-Ascension / ten-proofs
Forked from altyni86/ten-proofsLean certificates accompanying proofs in mathematics and theoretical computer science
Code and data for the preprint "Smooth Surrogate Models Approve Impossible Firing Patterns." A smooth surrogate of a Hodgkin-Huxley f-I curve silently certifies firing rates the real neuron cannot ...
Diagnosing motor-imagery BCI failure: separating methodological from neural decoding failure on BCI Competition IV Dataset 2a
An LLM that can only reason in English between layers: legible-by-construction residual stream, covert channel collapses to chance. Toy testbed + code.
Random-interconnected gradient routing for unlearning: a toy MNIST testbed comparing routing+prune vs gradient-ascent on capacity, absorption, composability, and tamper-resistance.
Reading the Router: plain-language, legible profiles of Mixture-of-Experts (OLMoE) expert specialization. Paper + code.
Certified reachability of NLA-defined concepts: proving when a model can(not) recognize it is being tested. Mashes Anthropic's Natural Language Autoencoder with Raghunathan certified defenses, on G...
Do an open NLA and an open SAE agree on the same Qwen2.5-7B activations? Pilot: a weak but genuine structure correlation (ρ≈0.21); the larger headline lift is mostly topical confound (corrected 202...
Personal site with hidden admin editor — for a friend
Diagnosing Motor-Imagery BCI Failure: A Three-Step Diagnostic Framework (analysis code and derived results)
跑步游戏强化学习训练框架