Fromthesky Research Labs
@fromtheskyresearch.bsky.social
AI/ML Research
https://huggingface.co/fromthesky
https://huggingface.co/fromthesky
We are happy to announce PLDR-LLM support for Huggingface Transformers library! We also release three high performing fine-tuned small size PLDR-LLMs for sentiment analysis, token classification and question answering. It is now possible to check out PLDR-LLM with just a few lines of code!
September 22, 2025 at 3:59 AM
We are happy to announce PLDR-LLM support for Huggingface Transformers library! We also release three high performing fine-tuned small size PLDR-LLMs for sentiment analysis, token classification and question answering. It is now possible to check out PLDR-LLM with just a few lines of code!
PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference
Preprint: arxiv.org/abs/2502.13502
Preprint: arxiv.org/abs/2502.13502
PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference
We show that Large Language Model from Power Law Decoder Representations (PLDR-LLM) is a foundational model whose deductive outputs are invariant tensors up to a small perturbation. PLDR-LLM learns a ...
arxiv.org
May 5, 2025 at 9:12 AM
PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference
Preprint: arxiv.org/abs/2502.13502
Preprint: arxiv.org/abs/2502.13502
PLDR-LLM: Large Language Model from Power Law Decoder Representations
Preprint: arxiv.org/abs/2410.16703
Preprint: arxiv.org/abs/2410.16703
PLDR-LLM: Large Language Model from Power Law Decoder Representations
We present the Large Language Model from Power Law Decoder Representations (PLDR-LLM), a language model that leverages non-linear and linear transformations through Power Law Graph Attention mechanism...
arxiv.org
May 5, 2025 at 9:11 AM
PLDR-LLM: Large Language Model from Power Law Decoder Representations
Preprint: arxiv.org/abs/2410.16703
Preprint: arxiv.org/abs/2410.16703
Power Law Graph Transformer for Machine Translation and Representation Learning
Preprint: arxiv.org/abs/2107.02039
Preprint: arxiv.org/abs/2107.02039
Power Law Graph Transformer for Machine Translation and Representation Learning
We present the Power Law Graph Transformer, a transformer model with well defined deductive and inductive tasks for prediction and representation learning. The deductive task learns the dataset level ...
arxiv.org
May 5, 2025 at 9:10 AM
Power Law Graph Transformer for Machine Translation and Representation Learning
Preprint: arxiv.org/abs/2107.02039
Preprint: arxiv.org/abs/2107.02039
Coulgat: An Experiment on Interpretability of Graph Attention Networks
Preprint: arxiv.org/abs/1912.08409
Preprint: arxiv.org/abs/1912.08409
CoulGAT: An Experiment on Interpretability of Graph Attention Networks
We present an attention mechanism inspired from definition of screened Coulomb potential. This attention mechanism was used to interpret the Graph Attention (GAT) model layers and training dataset by ...
arxiv.org
May 5, 2025 at 9:08 AM
Coulgat: An Experiment on Interpretability of Graph Attention Networks
Preprint: arxiv.org/abs/1912.08409
Preprint: arxiv.org/abs/1912.08409