-
OIST
- Okinawa, Japan
-
09:56
(UTC +09:00) - https://www.kaggle.com/ppyy22
- in/eiji-miyamoto-290a01225
- https://yypy22.github.io/
Stars
Bad Characters: Imperceptible NLP Attacks
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models [ACL 2025 Main]
Resources for the "SummEval: Re-evaluating Summarization Evaluation" paper
Code for automated main concept generation for narrative discourse assessment in aphasia
Granite Time Series Cookbook
Retrieval-Augmented Theorem Provers for Lean
Aphasia Recovery Cohort (ARC) Demonstration of Processing and Inference
[PNAS'21] The neural architecture of language: Integrative modeling converges on predictive processing
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A framework for few-shot evaluation of language models.
A collection of benchmarks and datasets for evaluating LLM.
Repository for "The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units" Paper
MrGGLS / BlockPruner
Forked from arcee-ai/BlockPrunerA block pruning framework for LLMs.
Evaluate computational models on their alignment to behavioral and neural measurements in the domain of language
TopoLM: brain-like spatio-functional organization in a topographic language model
Code for the ICLR 2025 Spotlight paper "Wasserstein Distances, Neuronal Entanglement, and Sparsity."
Induce brain-like topographic structure in your neural networks
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.
Structured Neuron Level Pruning to compress Transformer-based models [ECCV'24]
Code for the paper: Putting An End to End-to-End: Gradient-Isolated Learning of Representations
Very deep CNN for text classification
Machine learning lessons and teaching projects designed for engineers
Public code for Illing, Ventura, Bellec & Gerstner 2021: Local plasticity rules can learn deep representations using self-supervised contrastive predictions
Biologically Plausible Training Mechanisms for Self-Supervised Learning in Deep Networks
Repository containing code for blockwise SSL training