Product Design, Manufacturing & Innovation Resources

Neueste Veröffentlichungen und Patente zu kleinen Sprachmodellen (SLMs)

Kleine Sprachmodelle

Tipp: Zusätzlich zu der unten stehenden Auswahl können Sie unsere 2 gesamten Datenbanken durchsuchen und filtern:

> Kostenloses Tool zur Suche nach Veröffentlichungen < nach Autor, Thema, Stichwörtern, Datum oder Zeitschrift.

> Kostenloses Tool zur Suche nach Patenten < für Patente in englischer Sprache vom Europäischen Patentamt.

Kleine Sprachmodelle
Kleine Sprachmodelle ermöglichen eine effiziente Verarbeitung natürlicher Sprache auf Endgeräten und eingebetteten Systemen.

Kleine Sprachmodelle bezeichnen auf Transformer basierende Systeme zur Verarbeitung natürlicher Sprache, die mit weniger als etwa 7 Milliarden Parametern arbeiten – eine Schwelle, die weniger durch eine formale Grenze als vielmehr durch die praktische Beschränkung der Einsatzfähigkeit auf Verbraucherhardware, mobilen Geräten und eingebetteten Systemen ohne Cloud-Inferenzinfrastruktur definiert ist.

Das Gebiet entstand als direkte Reaktion auf die Rechen- und Wirtschaftskosten von Modellen im Grenzbereich: Architekturen mit mehr als einer Milliarde Parametern weisen zwar eine breite allgemeine Leistungsfähigkeit auf, doch ihr Speicherbedarf, ihre Inferenzlatenz und ihr Energieverbrauch machen sie strukturell unvereinbar mit dem Einsatz auf Geräten, datenschutzsensiblen Anwendungen und dem Betrieb in Umgebungen mit geringer Bandbreite oder Offline-Umgebungen.

Das zentrale Forschungsprogramm schließt die Leistungslücke zwischen kompakten und Spitzenmodellen durch eine Kombination aus Wissensdestillation – dem Trainieren eines kleineren Schülermodells anhand der Ausgabeverteilungen eines größeren Lehrermodells – strukturiertem und unstrukturiertem Pruning, aggressiver Gewichtsquantisierung bis hin zu INT4- und INT8-Darstellungen sowie parametereffizienten Feinabstimmungsmethoden wie LoRA und QLoRA, die ein komprimiertes Basismodell mit minimalem zusätzlichem Rechenaufwand an domänenspezifische Aufgaben anpassen.

Die unten aufgeführten Veröffentlichungen und Patente behandeln Modellkomprimierungstechniken, Quantisierungsalgorithmen, Destillationsprotokolle, effiziente Transformerarchitekturen, On-Device-Inferenzoptimierung und domänenspezifische Feinabstimmungspipelines:

Dies ist unsere neueste Auswahl an weltweiten Veröffentlichungen und Patenten in englischer Sprache zu Small Language Models (SLMs), die in vielen wissenschaftlichen Online-Zeitschriften zu finden sind und sich auf Small Language Model, SLM, On-Device Language Model, Edge Language Model, Compact Transformer, Sub-7B Parameter Model, Language Model Compression, Knowledge Distillation NLP, Structured Pruning Language Model konzentrieren, unstrukturiertes Pruning-Sprachmodell, Gewichtsquantisierungs-Sprachmodell, INT4-Quantisierungs-NLP, INT8-Quantisierungs-NLP, parameter-effiziente Feinabstimmung, LoRA-Feinabstimmung, QLoRA-Feinabstimmung, Adapter-Tuning-Sprachmodell, On-Device-Inferenz, Edge-Inferenz-NLP, spekulative Dekodierung, Modell-Destillations-Transformator, GGUF-Quantisierungsformat und Mixture-of-Experts-Kompaktmodell.

Teaching small language models petro-technical knowledge through language reasoning and fine-tuning

Patent published on the 2026-10-15 in US under Ref US20260319121 by SCHLUMBERGER TECH CORPORATION [US] (Paydayesh Mehdi [gb], Shamsa Amir [ca])

Abstract: A method for automatically generating an answer to a petro-technical query in an oil and gas domain includes receiving input data including question-answer pairs related to the oil and gas domain. The method also includes training a small language model (SLM) based upon the input data to produce a trained model. The method also includes fine-tuning the trained model to produce a fine-tuned model. The method also includes receiving the petro-technical query in the oil and gas domain. The method a[...]


Our summary: This method trains a small language model using question-answer pairs from the oil and gas domain. It fine-tunes the model to improve its ability to generate answers to petro-technical queries. The process enables automatic response generation for specific queries in the oil and gas sector.

small language models, petro-technical knowledge, fine-tuning, query generation

Patent

Method of laser-based additive manufacturing with pulse scan patterns for magnesium and its alloys

Patent published on the 2026-10-08 in US under Ref US20260307150 by OSSEOLABS CO LTD [TH] (Promoppatum Patcharapit [th], Sukpasert Montian [th], Ahuja Vikram [th], Harrysson Ola [us])

Abstract: This invention introduces an advanced pulse scanning technique for Selective Laser Melting (SLM) of magnesium, addressing critical manufacturing challenges. The method employs iterative optimization to regulate heat input through precise pulse patterns, preventing overheating and material defects. By alternating between powered and unpowered laser phases, the technique reduces material evaporation, minimizes internal stresses, and enhances microstructural uniformity. This approach enables more s[...]


Our summary: This invention presents a pulse scanning technique for Selective Laser Melting of magnesium. It optimizes heat input to prevent overheating and defects by alternating laser phases. This method improves fabrication stability and microstructural uniformity for magnesium components.

laser-based manufacturing, pulse scanning, magnesium alloys, Selective Laser Melting

Patent

Memory-efficient neural dialog artificial intelligence

Patent published on the 2026-10-08 in US under Ref US20260310927 by HSU JOSEPH BERNARD [US] (Hsu Joseph Bernard [us])

Abstract: [0000] A hybrid generative AI artificial intelligence system addresses cloud-centric AI inefficiencies through dynamic hierarchical memory indexing and selective cloud escalation. The system implements a three-object architecture comprising user profile management, thread index management, and dialog process control that enables client-side processing with precision-targeted cloud resource utilization. A small language model functions as a local decision engine, performing heuristic inference an[...]


Our summary: A hybrid generative AI system enhances cloud-centric AI efficiency through dynamic memory indexing. It features a three-object architecture for user profile, thread index, and dialog control. The system reduces response time by 84% and cloud dependency by 80% while ensuring cognitive coherence.

neural networks, cloud computing, memory indexing, dialog systems

Patent

Template guided speculative decoding

Patent published on the 2026-10-06 in US under Ref US12754958 by INTUIT INC [US] (Ben Shoham Ofir [il], Bar Eliyahu Natalie [il], Mendelson Shon [il], Antebi Sagiv [il], Ardazi Shai [il])

Abstract: Aspects of the present disclosure involve accelerated machine learning based sequence generation. Aspects include generating a first portion of a sequence based on an input query using a speculative decoding process involving a draft machine learning model and a target machine learning model with a larger number of parameters than the draft model. Aspects include determining, based on the input query and the first portion, that a next portion of the sequence is predicted to correspond to a templ[...]


Our summary: This disclosure involves a method for accelerated sequence generation using speculative decoding with two machine learning models. It includes generating a sequence portion based on an input query and determining if the next portion corresponds to a template. The next portion is generated through a template-based process and verified using a larger target model before appending to the sequence.

speculative decoding, sequence generation, machine learning models, template-based process

Patent

Secure explanation generation by large language models for sensitive search targets

Patent published on the 2026-10-06 in US under Ref US12755173 by INTUIT INC [US] (Eliyahu Natalie Bar [il], Mendelson Shon [il], Hazan Itay [il], Bechler Sigalit [il], Haas Noa [il], Bitton Ron [il])

Abstract: [0000] A method includes generating, by a large language model (LLM), a multitude of match explanations for a multitude of search targets. The multitude of match explanations is clustered to obtain a multitude of explanation clusters. An explanation template is generated for an explanation cluster. The explanation template includes a static portion and a dynamic portion. A multitude of explanation templates is obtained in this manner. A target match for a search target received from a user appli[...]


Our summary: The method generates match explanations for search targets using a large language model. These explanations are clustered to create templates with static and dynamic portions. A small language model populates match explanations based on user search targets and encoded templates.

explanation generation, large language model, sensitive search targets, clustering

Patent

Speculative decoding using expanded token matching

Patent published on the 2026-09-03 in US under Ref US20260260065 by MICROSOFT TECH LICENSING LLC [US] (Pathak Sayan Dev [us], Kesavamoorthy Harini [us], Basoglu Christopher Hakan [us], Vikram Ayush [us], Shah Amy Parag [us], Kelkar Rakesh [us])

Abstract: [0000] A speculative decoding technique generates tokens of a response using a verifying model and drafting model. In operation, the verifying model receives a set of draft tokens produced by the drafting model. The verifying model then verifies whether the draft tokens are correct by comparing probability information generated by the verifying model with probability information generated by the drafting model. The verifying model then determines whether any draft token that is rejected by the v[...]


Our summary: Speculative decoding generates response tokens using a verifying and drafting model. The verifying model checks draft tokens against probability information from both models. This iterative process expands accepted tokens, reducing resource use and latency.

speculative decoding, token matching, verifying model, drafting model

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

Behandelte Themen: Kleine Sprachmodelle, Verarbeitung natürlicher Sprache, transformatorbasierte Systeme, Parametereffizienz, Wissensdestillation, Modellkomprimierung, strukturiertes Pruning, unstrukturiertes Pruning, Gewichtsquantisierung, INT4, INT8, Feinabstimmungsmethoden, geräteinterne Bereitstellung, Inferenzlatenz, Energieverbrauch, datenschutzsensible Anwendungen, Operationen mit geringer Bandbreite, Offline-Betriebskontexte, IEEE 80211, ISO/IEC 30170, ISO/IEC 27001, ISO/IEC 25010 und NIST SP 800-53.

Glossar der verwendeten Begriffe

Natural Language Processing (NLP): Ein Bereich der künstlichen Intelligenz, der sich auf die Interaktion zwischen Computern und menschlicher Sprache konzentriert und es Maschinen ermöglicht, natürliche Texte oder Sprache zu verstehen, zu interpretieren und zu generieren. Es umfasst Aufgaben wie Sprachübersetzung, Stimmungsanalyse und Spracherkennung.

Small Language Models (SLM): Kompakte neuronale Netze, die für Aufgaben der natürlichen Sprachverarbeitung entwickelt wurden, zeichnen sich typischerweise durch weniger Parameter und einen geringeren Rechenaufwand im Vergleich zu größeren Modellen aus, sind aber dennoch in der Lage, kohärente Texte zu generieren und den Kontext innerhalb begrenzter Bereiche zu verstehen.

Historischer Kontext

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

(wenn das Datum unbekannt oder nicht relevant ist, z. B. „Strömungsmechanik“, wird eine gerundete Schätzung seines bemerkenswerten Auftretens bereitgestellt)

10. Jahr Jubiläum

Bilder in voller Größe und Downloads sind nur für registrierte Mitglieder 100% kostenlos verfügbar.

> Login <