Product Design, Manufacturing & Innovation Resources

Ultime pubblicazioni e brevetti sui modelli linguistici di piccole dimensioni (SLM)

Modelli linguistici di piccole dimensioni

Suggerimento: oltre alla selezione sottostante, è possibile cercare e filtrare i nostri 2 interi database:

> strumento di ricerca di pubblicazioni gratuite < per autore, argomento, parole chiave, data o rivista.

> strumento di ricerca brevetti gratuito < per brevetti in inglese dall'Ufficio europeo dei brevetti.

Modelli linguistici di piccole dimensioni
I modelli linguistici di piccole dimensioni consentono un'elaborazione efficiente del linguaggio naturale su dispositivi di consumo e embedded.

I modelli linguistici di piccole dimensioni designano i sistemi di elaborazione del linguaggio naturale basati su transformer che operano al di sotto di circa 7 miliardi di parametri: una soglia definita meno da un confine formale che dal vincolo pratico di implementabilità su hardware di consumo, dispositivi mobili e sistemi embedded senza infrastruttura di inferenza cloud.

Questo ambito di ricerca è emerso come risposta diretta ai costi computazionali ed economici dei modelli di frontiera: sebbene le architetture con oltre un miliardo di parametri dimostrino un'ampia capacità generale, il loro ingombro di memoria, la latenza di inferenza e il consumo energetico le rendono strutturalmente incompatibili con l'implementazione su dispositivo, le applicazioni sensibili alla privacy e i contesti operativi a bassa larghezza di banda o offline.

Il programma di ricerca centrale mira a colmare il divario di capacità tra modelli compatti e modelli di frontiera attraverso una combinazione di distillazione della conoscenza (addestramento di un modello studente più piccolo rispetto alle distribuzioni di output di un modello insegnante più grande), potatura strutturata e non strutturata, quantizzazione aggressiva dei pesi fino alle rappresentazioni INT4 e INT8 e metodi di fine-tuning efficienti in termini di parametri come LoRA e QLoRA, che adattano un modello base compresso a compiti specifici del dominio con un costo computazionale aggiuntivo minimo.

Le pubblicazioni e i brevetti elencati di seguito trattano tecniche di compressione dei modelli, algoritmi di quantizzazione, protocolli di distillazione, architetture di trasformatori efficienti, ottimizzazione dell'inferenza su dispositivo e pipeline di fine-tuning specifiche per dominio:

Questa è la nostra ultima selezione di pubblicazioni e brevetti in inglese su Small Language Models (SLM), tra numerose riviste scientifiche online, classificate e focalizzate su 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, modello linguistico di potatura non strutturato, modello linguistico di quantizzazione del peso, NLP di quantizzazione INT4, NLP di quantizzazione INT8, fine-tuning efficiente dei parametri, fine-tuning LoRA, fine-tuning QLoRA, modello linguistico di sintonizzazione dell'adattatore, inferenza su dispositivo, NLP di inferenza sul bordo, decodifica speculativa, trasformatore di distillazione del modello, formato di quantizzazione GGUF e modello compatto misto di esperti.

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

Argomenti trattati: Modelli linguistici di piccole dimensioni, elaborazione del linguaggio naturale, sistemi basati su trasformatori, efficienza dei parametri, distillazione della conoscenza, compressione dei modelli, potatura strutturata, potatura non strutturata, quantizzazione dei pesi, INT4, INT8, metodi di regolazione fine, distribuzione sul dispositivo, latenza dell'inferenza, consumo energetico, applicazioni sensibili alla privacy, operazioni a bassa larghezza di banda, contesti operativi non in linea, IEEE 80211, ISO/IEC 30170, ISO/IEC 27001, ISO/IEC 25010 e NIST SP 800-53.

Glossario dei termini utilizzati

Natural Language Processing (NLP): Un campo dell'intelligenza artificiale incentrato sull'interazione tra computer e linguaggio umano, che consente alle macchine di comprendere, interpretare e generare testo o discorso in linguaggio naturale. Comprende attività come la traduzione linguistica, l'analisi del sentiment e il riconoscimento vocale.

Small Language Models (SLM): Reti neurali compatte progettate per attività di elaborazione del linguaggio naturale, tipicamente caratterizzate da un numero inferiore di parametri e requisiti computazionali ridotti rispetto a modelli più grandi, pur essendo in grado di generare testo coerente e comprendere il contesto entro ambiti limitati.

Contesto storico

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

(se la data è sconosciuta o non rilevante, ad esempio "meccanica dei fluidi", viene fornita una stima approssimativa della sua notevole comparsa)

decimo anno anniversario

Le immagini a grandezza naturale e i download sono disponibili, gratuitamente al 100%, solo per gli utenti registrati.

> Login <