small language model

Full-Layer Memory Injection via Compile-Time Key-Value Caches: An External-Knowledge Mechanism for Small-Parameter Language Models

Knowledge of large language models (LLMs) is frozen in parameters after pretraining and hard to update at low cost. This paper proposes a full-layer memory injection method based on compile-time key-value (KV) caches. Experiments on Qwen3-0.6B show full-layer token-level KV injection raises private-specification QA sco...

Cell line screening of AI-generated drug repurposing predictions for NF2-related schwannomas

Non-NF2 schwannomatosis (SWN) is a rare syndrome that causes nerve sheath tumors with complex genetic variations and poorly understood modifiers. With no approved pharmacologic interventions, there is an urgent need for treatments that prevent or reduce tumor growth, or that ameliorate schwannoma-associated pain. Many...

Consumer Wearable Devices for Population-Level Infectious Disease Surveillance: A Scoping Review

Preprint, version 2. This manuscript has not been peer reviewed. It is under consideration at a peer-reviewed journal. This version supersedes version 1 (10.5281/zenodo.19411761, April 2026), which should no longer be cited for any numerical result. The review was rebuilt rather than amended, and the two versions do no...

ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

Cost-Efficient Large Language Model-Assisted Title and Abstract Screening for Systematic Reviews: Method Evaluation and Validation

DroneServer v2.0.2: an LLM-agnostic, MAVLink-based drone command-and-control MCP server with an untrusted-commander safety layer

Archived copy of the DroneServer code release v2.0.2 (git tag v2.0.2, commit 3281e6c3755814318d436556690c28e669f8c2e9), the version reported in the article An LLM-Agnostic, MAVLink-Based Drone Command and Control Interface and Agentic Harness Using the Model Context Protocol (Ramos Silva and Burke; preprint arXiv:2601....

Towards Behavior Tree-Guided Vulnerability Detection with Lightweight LLMs

Investigating Behavior Trees (BTs) as an alternative intermediate representation for LLM-based vulnerability detection suggests that BTs can provide a compact and useful structured representation for vulnerability detection with quantized, locally deployable LLMs.

MINERVA: How Small Can a Manipulation Policy Be and Still Solve LIBERO?

Vision-language-action (VLA) models with billions of parameters now dominate the LIBERO manipulation benchmark, but the model capacity actually required by the benchmark remains unclear. We introduce MINERVA (MINimal Efficient Robotic Vision-Action policy), a family of deliberately compact visuomotor policies designed...

A SoK for SoCs: Reading the TI Leaves on AI for Cyber Threat Intelligence Generation and Sharing

Three research directions for automating the production of shareable intelligence are derived from a literature survey of academic papers, organizing the CTI lifecycle into three stages: Threat Data Collection, CTI Generation and Sharing, and CTI Consumption.

Classic AI Scaffolding for LLM Social Agents

EpisodeSim is presented, a hybrid LLM-agent architecture that represents classic-AI structures as natural-language control state interpreted by LLM calls that supports a design claim that coherent social simulation benefits from persistent classic-AI-style scaffolding that organizes behavior over time.

frb-vlm-benchmark: a zero-shot Vision-Language Model benchmark for Fast Radio Burst detection

Code and evaluation artifacts supporting the article "Generalist Vision-Language Models for Fast Radio Burst detection: a zero-shot benchmark against a specialized detector" (Santos, Queiroz, Duarte, de Farias & Batista), submitted to The Astrophysical Journal Supplement Series (manuscript AAS80842; preprint arXiv:2607...

Vibe coding for ophthalmologists.

This review examines vibe coding through an ophthalmology-specific lens, identifying where it adds value and how it can be used responsibly, and how it can be used responsibly while preserving safety and accountability.