Introduces the first public multi-source cybersecurity log dataset with per-entry ATT&CK technique labels across 12 tactics and 53 techniques and demonstrates learnability via LoRA fine-tuning of three SLMs on chunk classification and technique identification.
A comprehensive survey of small language mod- els in the era of large language models: Techniques, enhancements, applications, collaboration with llms, and trustworthiness
8 Pith papers cite this work, alongside 17 external citations. Polarity classification is still indexing.
8
Pith papers citing it
17
external citations · external index
citation-role summary
background 3
citation-polarity summary
roles
background 3representative citing papers
MAS-Bench introduces 139 tasks, 88 predefined shortcuts, and 9 metrics to evaluate hybrid GUI-shortcut mobile agents, reporting up to 68.3% success and 39% efficiency gains over GUI-only baselines.
On bandwidth-bound edge hardware, MoE inference cost tracks total parameters rather than active ones, so sparse activation fails to deliver the expected throughput or energy gains.
OrganicHAR discovers 4-8 activity categories per user from sensor signals, achieves 79% accuracy on coarse activities with ambient sensors alone and cuts VLM queries by 90% by triggering video analysis only at detected pattern moments.
Small language models are sufficiently capable, more suitable, and far more economical than large models for the repetitive tasks that dominate agentic AI systems.
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
Position paper claiming that distributed training across massive edge devices can overcome data depletion and centralized compute monopolies in LLM scaling.
citing papers explorer
-
Multi-Source Cybersecurity Logs: An ATT&CK-Labeled Dataset and SLM Evaluation
Introduces the first public multi-source cybersecurity log dataset with per-entry ATT&CK technique labels across 12 tactics and 53 techniques and demonstrates learnability via LoRA fine-tuning of three SLMs on chunk classification and technique identification.
-
MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents
MAS-Bench introduces 139 tasks, 88 predefined shortcuts, and 9 metrics to evaluate hybrid GUI-shortcut mobile agents, reporting up to 68.3% success and 39% efficiency gains over GUI-only baselines.
-
Does Mixture-of-Experts Actually Help Inference on Consumer and Edge Hardware? An Empirical Study
On bandwidth-bound edge hardware, MoE inference cost tracks total parameters rather than active ones, so sparse activation fails to deliver the expected throughput or energy gains.
-
OrganicHAR: Towards Activity Discovery in Organic Settings for Privacy Preserving Sensors Using Efficient Video Analysis
OrganicHAR discovers 4-8 activity categories per user from sensor signals, achieves 79% accuracy on coarse activities with ambient sensors alone and cuts VLM queries by 90% by triggering video analysis only at detected pattern moments.
-
Small Language Models are the Future of Agentic AI
Small language models are sufficiently capable, more suitable, and far more economical than large models for the repetitive tasks that dominate agentic AI systems.
-
Large Language Model-Brained GUI Agents: A Survey
A survey consolidating frameworks, data practices, large action models, benchmarks, applications, and research gaps in LLM-brained GUI agents.
-
Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices
Position paper claiming that distributed training across massive edge devices can overcome data depletion and centralized compute monopolies in LLM scaling.
- Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents