This is a PyTorch implementation of ConvTran
-
Updated
Mar 21, 2025 - Python
#
position-encoding
Here are 8 public repositories matching this topic...
[ICLR 2026] GRAPE: Group Representational Position Encoding (https://arxiv.org/abs/2512.07805)
deep-learning pretraining model-architectures foundation-models large-language-models llms position-encoding
-
Updated
Jun 15, 2026 - Python
Official Project Page for HLA: Higher-order Linear Attention (https://arxiv.org/abs/2510.27258)
deep-learning pretraining model-architectures foundation-models large-language-models llms position-encoding
-
Updated
Jun 15, 2026 - HTML
[ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"
-
Updated
Nov 25, 2024 - Python
PyTorch implementation of RoFormer's Rotary Position Embeddings (RoPE) with comprehensive tests, benchmarks, and documentation. Used in LLaMA, PaLM, GPT-NeoX.
nlp machine-learning deep-learning pytorch transformer llama attention-mechanism research-paper rope position-encoding
-
Updated
Jul 15, 2026 - Python
Position-Guided Transformer for Image Captioning. Image and Vision computing.
-
Updated
Oct 21, 2022 - Python
Trains a neural network to output the RGB color for a given XYZ coordinate on a vertex colored 3D mesh.
ply reconstruction color-encoding vertex-color vertex-coloring position-encoding vertexcolor neural-reconstruction
-
Updated
Oct 27, 2025 - Python
Benchmarking RoPE scaling methods on TinyLlama-1.1B to measure perplexity degradation when extending context from 2048 to 8192 tokens. NTK-aware scaling preserves quality almost perfectly while linear scaling collapses.
benchmarking yarn transformers pytorch rope perplexity long-context position-encoding llm-inference tinyllama context-extension ntk-scaling
-
Updated
Jul 19, 2026 - Python
Improve this page
Add a description, image, and links to the position-encoding topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the position-encoding topic, visit your repo's landing page and select "manage topics."