About
Research & Development
AI Agents Streamline Root Cause Localization in Microservice Systems
TLDR: RCLAgent is a new AI method for finding the root cause of failures in complex microservice systems. It mimics how human experts diagnose...
Research & Development
Graph-R1: Enhancing LLM Reasoning Through NP-Hard Graph Problems
TLDR: Graph-R1 is a new Large Language Model (LLM) post-training framework that uses NP-hard graph problems as a synthetic training corpus to develop advanced...
Research & Development
Unpacking LLM Reasoning: How Uncertainty Guides Correct Answers
TLDR: A new study introduces conditional entropy reduction as a metric to assess the utility of reasoning steps in Large Language Models (LLMs). It...
Research & Development
EAGLE-PC: A New Approach to Prevent Over-Forgetting in Large Language Model Unlearning
TLDR: EAGLE-PC is a novel framework for machine unlearning in Large Language Models (LLMs) that addresses the problem of 'excessive forgetting' (over-forgetting). It uses...
Research & Development
Connecting Joint Movements to Ball Flight: The CaddieSet Approach
TLDR: CaddieSet is a novel golf swing dataset that pairs detailed human joint features extracted from swing videos with corresponding ball trajectory information. It...
Research & Development
BioASQ 2025 Unveils New Tasks in Biomedical Semantic Indexing and Question Answering
TLDR: BioASQ 2025, the thirteenth challenge, advanced large-scale biomedical semantic indexing and question answering. It featured updated versions of Task b and Synergy, plus...