Product Design, Manufacturing & Innovation Resources

Publicações recentes – Patentes sobre modelos de linguagem de pequeno porte (SLMs)

Modelos de idiomas pequenos

Dica: além da seleção abaixo, você pode pesquisar e filtrar nossos 2 bancos de dados completos:

> ferramenta de busca de publicações gratuitas < Por autor, tópico, palavras-chave, data ou periódico.

> ferramenta gratuita de busca de patentes < para patentes em inglês do Escritório Europeu de Patentes.

Small language models
Modelos de linguagem pequenos permitem eficiência processamento de linguagem natural em dispositivos de consumo e dispositivos embarcados.

Os modelos de linguagem pequenos designam sistemas de processamento de linguagem natural baseados em transformadores que operam com menos de aproximadamente 7 bilhões de parâmetros — um limite definido menos por uma fronteira formal do que pela restrição prática de implantação em hardware de consumo, dispositivos móveis e sistemas embarcados sem infraestrutura de inferência em nuvem.

O domínio surgiu como uma resposta direta aos custos computacionais e econômicos dos modelos de escala de fronteira: embora as arquiteturas com mais de um bilhão de parâmetros demonstrem ampla capacidade geral, sua pegada de memória, latência de inferência e consumo de energia as tornam estruturalmente incompatíveis com a implantação em dispositivos, aplicações sensíveis à privacidade e contextos operacionais de baixa largura de banda ou offline.

O programa central de pesquisa visa reduzir a lacuna de capacidade entre modelos compactos e de vanguarda por meio de uma combinação de destilação de conhecimento — treinando um modelo aluno menor com base nas distribuições de saída de um modelo professor maior — poda estruturada e não estruturada, quantização agressiva de pesos até representações INT4 e INT8, e métodos de ajuste fino com uso eficiente de parâmetros, como LoRA e QLoRA, que adaptam um modelo base comprimido a tarefas específicas do domínio com custo computacional adicional mínimo.

As publicações e patentes indexadas abaixo abordam técnicas de compressão de modelos, algoritmos de quantização, protocolos de destilação, arquiteturas de transformadores eficientes, otimização de inferência em dispositivos e pipelines de ajuste fino específicos de domínio:

Esta é a nossa mais recente seleção de publicações e patentes mundiais em inglês sobre Modelos de Linguagem Compactos (SLMs), provenientes de diversos periódicos científicos online, classificadas e focadas em modelos de linguagem compactos, SLMs, modelos de linguagem em dispositivos, modelos de linguagem de borda, Transformers compactos, modelos com menos de 7 bilhões de parâmetros, compressão de modelos de linguagem, destilação de conhecimento em PNL, modelos de linguagem com poda estruturada, modelos de linguagem com poda não estruturada, modelos de linguagem com quantização de pesos, quantização INT4 em PNL, quantização INT8 em PNL, ajuste fino com eficiência de parâmetros, ajuste fino LoRa, ajuste fino QLoRA, ajuste de adaptadores em modelos de linguagem, inferência em dispositivos, inferência de borda em PNL, decodificação especulativa, Transformers de destilação de modelos, formato de quantização GGUF e modelos compactos de mistura de especialistas.

Deformable high-strength aluminum alloy compositions and methods of making the same

Patent published on the 2026-06-04 in US under Ref US20260152827 by PURDUE RES FOUNDATION [US] (Zhang Xinghang [us], Wang Haiyan [us], Stegman Benjamin Thomas [us], Shang Anyu [us])

Abstract: [0000] An alloy comprising 92 at % aluminum, 2 at % titanium, 2 at % iron, 2 at % cobalt, and 2 at % nickel. A method of making an alloy is disclosed. The method contains the steps of providing particles of desired composition, utilizing a selective leaser melting (SLM) apparatus producing a first layer of the particles on a substrate and melting and solidifying a first group selected areas of the layer of particles, wherein the melting and the solidification results in an alloy of desired compo[...]


Our summary: The content describes a high-strength aluminum alloy with specific composition percentages. It outlines a method for creating the alloy using selective laser melting to achieve desired thickness and shape. The process involves layering particles, melting, and solidifying selected areas to form intermetallic structures.

aluminum alloy, selective laser melting, intermetallic lamellae, high-strength

Patent

Quantization-aware lora fine-tuning for llm

Patent published on the 2026-06-04 in US under Ref US20260154540 by MEDIATEK SINGAPORE PTE LTD [SG] (Lim Jia Yao Christopher [sg], Huang Ya-lin [tw], Li Huai-ting [tw], Wong Wai Mun [sg], Liang Jen-wei [tw], Lee Timothy Jun Jie [sg])

Abstract: [0000] In an aspect of the disclosure, a method of using a LoRA for inference with a FC layer of a LLM is provided. The method includes: dequantizing an INT input to an FP output; processing the FP output from the DQ and a first FP input from first weights of a down projection module of the LoRA, to output a first FP output; processing the first FP output from the first BMM and a second FP input from second weights of an up projection module of the LoRA, to output a second FP output; quantizing [...]


Our summary: The method describes using LoRA for inference in a fully connected layer of a large language model. It involves dequantizing inputs, processing them through down and up projection modules, and quantizing outputs. The final output is an INT inference result derived from the LoRA adjustments.

Quantization, LoRA, fine-tuning, LLM

Patent

Systems and methods for assisting operation and maintenance of marine machine equipment

Patent published on the 2026-06-03 in EP under Ref EP4752805 by ALFA LAVAL CORP AB [SE] (Karlsson Jimmie [se], Boman Jesper [se])

Abstract: [0001] The present invention relates to a method of operating and maintaining a piece of marine machine equipment. The piece of marine machine equipment is connected to a local processor. The method comprising the steps of obtaining a set of training data specific to the piece of marine machine equipment and training a Small Language Model (SLM) with the set of training data specific to the piece of marine machine equipment. The method further comprising the step of executing the trained SLM on [...]


Our summary: The invention describes a method for operating and maintaining marine machine equipment using a local processor. It involves training a Small Language Model (SLM) with specific training data for the equipment. The trained SLM provides offline operational advice utilizing real-time data from the equipment.

marine machine equipment, operational advice, Small Language Model, real-time data

Patent

Parameter-free method for efficient and accurate llm inference acceleration via speculative decoding

Patent published on the 2026-05-07 in WO under Ref WO2026092843 by MARZOLLO MICHELE [DE] (Marzollo Michele [de], Mueller Lorenz [de], Zhuang Jiawei [de], Roemer Niklas [de], Cavigelli Lukas [de])

Abstract: In some examples, apparatus and methods are provided for selecting a draft token sequence for verification by using a large language model, LLM. Different sources of statistics on text data (prompt, generated output, large dataset of text data) can be utilized in order to choose candidates to use for speculative decoding via look-ups.[...]


Our summary: This method accelerates LLM inference without parameters by using speculative decoding. It selects draft token sequences for verification through statistical analysis of text data. The approach utilizes various sources of statistics to optimize candidate selection for decoding.

speculative decoding, LLM inference, token sequence selection, text data statistics

Patent

Automated synthesis of planar linkage mechanisms with diverse joint types via spring-connected link models and contrastive graph learning

Published on 2026-03-28 by @OXFORD

Abstract: AbstractThe automated synthesis of planar linkage mechanisms has long been a challenge in mechanism design, requiring both geometric feasibility and motion accuracy. Recent advances in data-driven and neural network–based methods have shown promise in automating linkage synthesis, improving efficiency and scalability compared to traditional analytical or optimization-based techniques. Nevertheless, existing data-driven approaches remain limited in handling diverse joint configurations and ofte[...]


Our summary: This study presents a framework for automating the synthesis of planar linkage mechanisms using deep learning and physics-based modeling. It employs a spring-connected link model for diverse joint configurations and utilizes contrastive graph learning for efficient linkage retrieval. The method demonstrates improved accuracy and optimization stability compared to traditional approaches.

mechanism synthesis, deep learning, contrastive graph learning, optimization stability

Publication

Enhancing Whisper Fine-Tuning with Discrete Wavelet Transform-Based LoRA Initialization

Published on 2026-01-29 by Liang Lan, Molin Fang, Yuxuan Chen, Daliang Wang, Wenyong Wang @MDPI

Abstract: In low-resource automatic speech recognition (ASR) scenarios, parameter-efficient fine-tuning (PEFT) has become a crucial approach for adapting large pre-trained speech models. Although low-rank adaptation (LoRA) offers clear advantages in efficiency, stability, and deployment friendliness, its performance remains constrained because random initialization fails to capture the time&amp;ndash;frequency structural characteristics of speech signals. To address this limitation, this work proposes[...]


Our summary: This work introduces a structured initialization mechanism combining LoRA with discrete wavelet transform for fine-tuning in low-resource ASR. The proposed DWTLoRA method enhances convergence speed, stability, and accuracy by aligning with speech signal characteristics. Experimental results show DWTLoRA outperforms standard LoRA and other PEFT methods in character error rate and training efficiency.

Fine-Tuning, Discrete Wavelet Transform, Low-Rank Adaptation, Automatic Speech Recognition

Publication

Influence and Optimization of Process Parameters on Surface Roughness of Selective Laser Melting of 316L Stainless Steel

Published on 2026-01-20 by Pin Dong, Kamonpong Jamkamon, Suppawat Chuvaree @MDPI

Abstract: To achieve better surface quality in selective laser melting (SLM), this study used 316L stainless steel powder and conducted a systematic design experiment to investigate the influence mechanism of process parameters on the surface roughness of the top and vertical surfaces. Response surface methodology (RSM) was then used for parameter optimization. The results showed that scanning speed has the greatest impact on surface roughness, followed by laser power, while scanning spacing has the least[...]


Our summary: This study investigates the impact of process parameters on the surface roughness of 316L stainless steel in selective laser melting. Scanning speed significantly affects surface quality, with optimal conditions identified for minimal roughness. The findings validate the effectiveness of the response surface methodology used for parameter optimization.

Selective Laser Melting, Surface Roughness, Process Parameters, Response Surface Methodology

Publication

A Lightweight LLM-Based Semantic&ndash;Spatial Inference Framework for Fine-Grained Urban POI Analysis

Published on 2026-01-16 by Zhuo Huang, Yixing Guo, Shuo Huang, Miaoxi Zhao @MDPI

Abstract: Unstructured POI name texts are widely used in fine-grained urban analysis, yet missing labels and semantic ambiguity often limit their value for spatial inference. This study proposes a large language model-based semantic&amp;ndash;spatial inference framework (LLM-SSIF), a lightweight semantic&amp;ndash;spatial pipeline that translates POI texts into interpretable, fine-grained spatial evidence through an end-to-end workflow that couples scalable label expansion with scale-controlled sp[...]


Our summary: This study introduces LLM-SSIF, a lightweight framework for translating unstructured POI texts into spatial evidence. It employs LoRA-based fine-tuning for efficient adaptation and enhances label coverage. The model demonstrates strong performance in urban analysis, revealing cultural differences between cities.

LLM, semantic inference, spatial analysis, fine-grained POI

Publication

Tópicos abordados: Modelos de linguagem pequenos, Processamento de linguagem natural, Sistemas baseados em Transformers, Eficiência de parâmetros, Destilação de conhecimento, Compressão de modelos, Poda estruturada, Poda não estruturada, Quantização de pesos, INT4, INT8, Métodos de ajuste fino, Implantação em dispositivos, Latência de inferência, Consumo de energia, Aplicações sensíveis à privacidade, Operações de baixa largura de banda, Contextos operacionais offline, IEEE 80211, ISO/IEC 30170, ISO/IEC 27001, ISO/IEC 25010 e NIST SP 800-53.

Glossário de termos utilizados

Natural Language Processing (NLP): Um campo da inteligência artificial focado na interação entre computadores e linguagem humana, permitindo que máquinas compreendam, interpretem e gerem texto ou fala em linguagem natural. Abrange tarefas como tradução de idiomas, análise de sentimentos e reconhecimento de fala.

Small Language Models (SLM): Redes neurais compactas, projetadas para tarefas de processamento de linguagem natural, geralmente caracterizadas por menos parâmetros e requisitos computacionais reduzidos em comparação com modelos maiores, mas ainda capazes de gerar texto coerente e compreender o contexto dentro de escopos limitados.

Contexto histórico

1965
1970
1970
1974-11-15
1980
1980
1980
1964
1968
1970
1970
1975
1980
1980
1980

(Caso a data seja desconhecida ou irrelevante, por exemplo, "mecânica dos fluidos", é fornecida uma estimativa aproximada de seu surgimento notável)

Imagens em tamanho real e downloads estão disponíveis apenas, 100% gratuitos, para membros registrados.