small language model
PulseAugur coverage of small language model — every cluster mentioning small language model across labs, papers, and developer communities, ranked by signal.
7 天有情绪数据
-
PACE framework enables small language models to self-evolve
Researchers have developed PACE, a novel framework for enabling small language model (SLM) agents to self-evolve without requiring model weight updates or access to frontier models. This two-timescale approach separates…
-
Small language models poised to lead in healthcare applications
Small language models (SLMs) may offer significant advantages in healthcare due to their efficiency and accessibility. These compact models, potentially under 400MB, can achieve reasoning capabilities comparable to much…
-
HARNESS-LM trains compact models for faster sponsored search retrieval
Researchers have developed HARNESS-LM (HLM), a novel three-phase training framework designed to transfer the capabilities of large language models into compact, efficient models for sponsored search retrieval. This meth…
-
Small LLMs use positional copying shortcut for arithmetic, bypassing CoT logic
A new research paper reveals a significant shortcut in how small language models perform arithmetic tasks using chain-of-thought (CoT) prompting. Instead of relying on logical sequencing, these models tend to copy the n…
-
8-Bit Computer Project Trains Neural Networks from Assembly Code
A project called VirtualPC is demonstrating the feasibility of training neural networks on an 8-bit computer simulated from basic logic gates. This open-source initiative allows for direct training of models using assem…
-
Small Language Models show promise in educational assessment design
Researchers have compared the effectiveness of Large Language Models (LLMs) and Small Language Models (SLMs) for designing educational assessment questions. The study found that SLMs can perform comparably to LLMs on va…
-
SLMs emerge as enterprise alternative to LLMs for specific tasks
In 2026, Small Language Models (SLMs) are emerging as a viable alternative to Large Language Models (LLMs) for enterprise workloads. SLMs are suitable for narrow, well-defined tasks, data privacy concerns, edge device d…
-
On-device PII substitution pipeline uses locale-prompting to fix regurgitation
Researchers have developed an on-device pipeline for substituting Personally Identifiable Information (PII) with consistent, type-preserving fake values, aiming to maintain downstream text utility. The system uses a sma…
-
LIFT pipeline improves table extraction with fine-tuned small models
Researchers have introduced LIFT, a novel pipeline for improving table extraction from unstructured text. This method first uses a large language model to generate an initial table, followed by a smaller, fine-tuned mod…
-
Dataset preparation is key to successful model fine-tuning
This article emphasizes the critical importance of dataset preparation before engaging in model fine-tuning. It details how a well-structured and relevant dataset is foundational for successful fine-tuning, regardless o…
-
Fine-tuning small language models for security applications detailed
This article explores the practice of fine-tuning smaller language models, distinguishing them from larger counterparts. It details how this process can adapt general-purpose models for specific applications, particular…
-
TextPro-SLM reduces speech LLM modality gap by enhancing input processing
Researchers have developed TextPro-SLM, a novel speech large language model (SLM) designed to minimize the modality gap between spoken and text-based inputs. Unlike previous approaches focusing on output generation, Tex…
-
GRAIL framework slashes agent discovery latency by 79x with SLM-enhanced indexing
Researchers have developed GRAIL, a new framework designed to significantly speed up the discovery of AI agents for multi-agent collaboration. GRAIL utilizes a specialized Small Language Model (SLM) for faster capabilit…
-
Free Pascal and BLAS offer deterministic HPC for SLM projects
A user on Mastodon is exploring the use of BLAS, a set of Fortran-based matrix routines, for their Small Language Model (SLM) project. They express a preference for Free Pascal over languages like C, Python, Rust, and C…
-
Free Pascal and BLAS offer faster matrix multiplication for AI development
A user explored the performance of Python for AI tasks, noting its slowness but acknowledging the extensive AI ecosystem as its primary advantage. They conducted a test comparing Free Pascal and BLAS for matrix multipli…
-
RadLite fine-tunes small LLMs for CPU-deployable radiology AI
Researchers have developed RadLite, a method for fine-tuning small language models (SLMs) with 3-4 billion parameters for radiology tasks. This approach, utilizing LoRA fine-tuning on models like Qwen2.5-3B-Instruct and…
-
New 'Select to Think' method boosts small language models' reasoning
Researchers have developed a new method called Select to Think (S2T) to improve the reasoning capabilities of small language models (SLMs). S2T addresses the limitations of SLMs by reframing the role of larger language …
-
SwarmDrive uses local SLMs for cooperative autonomous driving
Researchers have developed SwarmDrive, a new framework for cooperative autonomous driving that utilizes local Small Language Models (SLMs) on vehicles. This system shares condensed intent information only when uncertain…
-
Small LMs achieve better reasoning with budget-aware guidance and prompt disambiguation
Researchers are exploring methods to enhance the reasoning capabilities of smaller language models (SLMs) without increasing their size or computational cost. One approach focuses on pre-inference prompt disambiguation,…