small language model

Understanding Pose-Based Sign Language Translation: Ablation Studies

Corpus-level behavioral intensity in human–AI conversations

This study proposes a transparent rule-based framework for estimating persistence, delegation-related lexical patterns, and refinement-related lexical markers without inferring psychological dependence in conversational generative models.

Integrating Geogebra and Liveworksheets in Developing PMRI-Based Interactive Worksheets: a 4D Model Study on Linear Equations

To address persistent shortcomings in students’ conceptual understanding, this development study designed and validated interactive digital worksheets grounded in the Indonesian Realistic Mathematics Education approach (PMRI) and integrating GeoGebra and Liveworksheets for eighth‑grade instruction on linear equation. E...

Can Large Language Models Evaluate Grant Proposal Quality? Revisiting the Wennerås and Wold Peer Review Data

Abstract Purpose Despite the importance of peer review for grant funding decisions, academics are often reluctant to conduct it. This can lead to long delays between submission and the final decision as well as the risk of substandard reviews from busy or non-specialist scholars. At least one funder now uses Large Lang...

What is the Role of Small Models in the LLM Era: A Survey

Abstract Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning tasks, which leads to the development of increasingly large models. However, scaling up model sizes results in significantly higher computational costs and energy consumption, which makes these models impractical for ac...

Dynamic medical knowledge graph updating method based on LLM decision control

A Dynamic Medical Knowledge Graph updating framework based on Large Language Model (LLM) decision control is proposed, modeling the knowledge updating process as a sequential decision problem driven by multi-source feedback and stability constraints, thereby achieving a safe and controllable updating mechanism at the m...

SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulation

SkipVLA is a hybrid policy that combines a pretrained VLA with a classical motion planner, using the planner for free-space motion and querying the VLA only for contact-rich skills such as grasping and placing, demonstrating up to 2.5x faster task completion and significantly lower energy consumption.

HEROIC: Heterogeneous Evidential Reasoning for Open-Vocabulary Identification and Cross-Robot Collaboration

HEROIC is a decentralized heterogeneous multi-agent open-vocabulary search coordination framework that requires agents to communicate in natural language only and reaches the target 84% of the time across all 6 scenes, compares to 35-54% for vision-language frontier baselines, frontier-based search, lawnmower, and rand...

Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models

The Depth Control Protocol (DCP) is proposed, a diagnostic suite that disentangles three quantities of depth: truncating depth at inference time, plotting quality against retained depth fraction, and reading off the slope.

Molecular Geometry Understanding Has Unintendedly Emerged in Frontier Large Language Models

This work tests a model's ability to rank conformers by stability, suggesting that it emerged unintendedly from models training on linked but conceptually different tasks, and suggests that current frontier models offer a realistic starting point for AI-driven molecular design.

The pitfalls of AI detection in academic writing: bias, false positives, and the need for inclusive assessment

The paper distinguishes genuine false positives from definitional boundary cases involving AI-assisted translation and polishing, engages the counter-argument that AI-polished prose may itself flatten linguistic diversity in academic English, and proposes a concrete process-oriented assessment model based on declared s...

EviRCA: Decoupling Evidence Extraction from Reasoning for Microservice Root-Cause Analysis

EviRCA is presented, a framework for LLM-based RCA that decouples deterministic evidence extraction from LLM reasoning and substantially outperforms prior OpenRCA baselines that achieve up to 15.2%, while reducing token consumption by 15-26x and execution time by 3-20x.