#large language models

DDPT: Enhancing complex reasoning in large language models via distillation and dynamic prompt tuning

Ge Teng Chen Shen Wenxiao Wang Sinan Fan Liang Xie Xiang Tian Peng Chen Xuesong Liu Yaowu Chen Jieping Ye

Oct 2026 · Neurocomputing · Vol 698, pp. 134297 · 0 citations · 38 references

Computer Science

DOI Semantic Scholar

View source

Related blog posts

Google Research Blog · research.google Aug 21, 2026

How mobility gives language models a deeper understanding of place

Algorithms & Theory

MIT News · Artificial Intelligence · news.mit.edu Aug 18, 2026

When AI art has no author: Study finds generated images often can’t be traced to training data

A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.

Hugging Face Blog · huggingface.co Aug 18, 2026

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Hugging Face Blog · huggingface.co Aug 14, 2026

State of Open Models: Summer 2026 Observations

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

DDPT: Enhancing complex reasoning in large language models via distillation and dynamic prompt tuning

Similar papers

A semi-supervised multi-stage pipeline for low-resource industrial condition monitoring by injecting domain knowledge via cross-modal multimodal large language model fine-tuning

A comprehensive survey of prompt engineering and context engineering techniques in large language models

PathSymphony: Harmonizing symbolic planning and Large Language Models for curriculum-guided mathematical reasoning

Large language models in mechanical design of mechatronic systems: A review

Large language model-driven information extraction and causal chain reasoning from chemical accident investigation reports for process safety intelligence

Risk carrier identification and heterogeneity analysis for underground space development beneath existing buildings: A multi-source data and large-language-model-driven retrieval model

Related blog posts

How mobility gives language models a deeper understanding of place

When AI art has no author: Study finds generated images often can’t be traced to training data

Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers

State of Open Models: Summer 2026 Observations