About
Research & Development
Advancing Mitosis Detection and Classification with a Teacher-Student AI Model
TLDR: Researchers developed a teacher-student AI model for the MIDOG 2025 Challenge to detect and classify mitosis in pathology images. The model uses a...
Research & Development
Unmasking AI in Academic Peer Review: A Content-Centric Approach
TLDR: The paper introduces CoCoNUTS, a new benchmark dataset, and CoCoDet, a novel AI detector, designed to identify AI involvement in academic peer reviews...
Research & Development
GPT-5 Sets New Benchmarks in Biomedical Question Answering, Challenges Remain in Other NLP Tasks
TLDR: A new benchmark study evaluated GPT-5 and GPT-4o on 12 biomedical natural language processing (BioNLP) tasks. GPT-5 achieved the highest overall performance, notably...
Research & Development
The Clues in Contradictions: Pinpointing LLM Uncertainty Sources
TLDR: A new research paper introduces a framework to diagnose the specific sources of uncertainty in large language models (LLMs). Instead of just quantifying...
Research & Development
Streamlining Large Language Models for Faster Inference
TLDR: This research introduces a novel pruning method to enhance the efficiency of Large Language Models (LLMs), particularly in prefill-decode disaggregated inference. The approach...
Research & Development
COCORELI: A Hybrid AI Framework for Precise Language Instruction Execution
TLDR: COCORELI is a novel hybrid AI framework that uses medium-sized LLM agents, abstraction mechanisms, and a discourse module to accurately follow complex language...