About
Research & Development
Unlocking Software Reliability: How Language Models Aid Proof Assistants in Verification
TLDR: A case study explored the effectiveness of Large Language Models (LLMs) in generating proofs for formal software verification using Rocq Prover. The study...
Research & Development
New Research Uncovers How Quantization Affects Different Types of Knowledge in Large Language Models
TLDR: A new research paper introduces task-stratified scaling laws for post-training quantized Large Language Models (LLMs). It disentangles LLM knowledge into memorization and utilization...
Research & Development
LaQual: A New Framework for Automated Quality Assessment of LLM Applications
TLDR: LaQual is an automated framework designed to evaluate the quality of LLM applications in app stores. It addresses the challenge of identifying high-quality...
Research & Development
Enhancing Ancient Chinese Inscription Detection with Feature Clustering
TLDR: This research introduces a novel clustering-based feature representation learning method to improve the automated detection of Oracle Bone Inscriptions (OBIs) from rubbing images....
Research & Development
Unveiling Market Uncertainty: How Executive Voices Predict Volatility, Not Returns
TLDR: A new research paper introduces a multimodal framework that combines textual sentiment with paralinguistic cues from executive voices in earnings calls to forecast...
Research & Development
AI Framework Addresses Fairness and Skill Alignment in Medical Collaboration
TLDR: Researchers developed FairSkillMARL, an AI framework that defines fairness in multi-agent systems by balancing workload and aligning tasks with agent skills, specifically for...