About
Research & Development
Smart Security for Robotic Systems: Detecting Anomalies in ROS2 Cyber-Physical Systems
TLDR: This research introduces a new method for detecting attacks in Cyber-Physical Systems (CPS) that use ROS2. It addresses the challenge of limited labeled...
Research & Development
A Collaborative AI Approach to Multimodal Entity Linking
TLDR: DeepMEL is a new framework that uses a team of specialized AI agents to improve Multimodal Entity Linking (MEL). It addresses challenges in...
Research & Development
Annif System Leads GermEval-2025 LLMs4Subjects Task with Hybrid AI for Subject Indexing
TLDR: The paper details the Annif system's winning approach at GermEval-2025's LLMs4Subjects task, focusing on automated subject indexing. It combines traditional extreme multi-label text...
Research & Development
New Benchmarks Reveal LLM Struggles in Formal Mathematical Proofs
TLDR: A new research paper introduces a scalable method to create challenging formal theorem proving benchmarks for large language models (LLMs) using theoretical computer...
Research & Development
Enhancing LLM Efficiency: A New Approach to Tensor-Parallel Latent Attention
TLDR: TPLA (Tensor-Parallel Latent Attention) is a new method that improves the efficiency of large language models during inference by combining KV cache compression...
Research & Development
Text-to-Table Generation: When Does Structured Decoding Help or Hinder?
TLDR: A new study evaluates the effectiveness of structured decoding versus one-shot prompting for text-to-table generation using large language models across three datasets: E2E,...