About
Research & Development
Improving How AI Understands Spoken Language Through GRPO
TLDR: A new research paper introduces a Group Relative Policy Optimization (GRPO)-based method to train Speech-Aware Large Language Models (SALLMs) for open-format speech understanding...
Research & Development
MIR: A New Benchmark for Training AI to Understand Complex Multi-Image Stories
TLDR: The paper introduces MIR, a novel benchmark and a stage-wise curriculum learning strategy for Multi-modal Large Language Models (MLLMs). MIR aims to improve...
Research & Development
Advancing Breast Ultrasound AI with a Comprehensive Reasoning Dataset
TLDR: Researchers have introduced BUS-CoT, a large-scale breast ultrasound dataset with 11,439 images covering all 99 histopathology types. It includes unique chain-of-thought reasoning annotations,...
Research & Development
DiffSyn: Advancing Materials Synthesis with AI-Powered Recipe Generation
TLDR: DiffSyn is a new generative diffusion model that predicts synthesis routes for crystalline materials like zeolites. Trained on over 23,000 recipes, it captures...
Research & Development
Enhancing Solar Power Forecasts with Deep Learning and Smart Data Reconstruction
TLDR: A new deep learning method, CEEDMA-Multi_nets-EQN, significantly improves ultra-short-term solar power forecasting. It achieves this by decomposing solar data into high and low-frequency...
Research & Development
Streamlining Prompt Management for LLM-Powered Software Development
TLDR: Prompt-with-Me is an IDE plugin that brings structured management to LLM prompts in software engineering. It automatically classifies prompts using a four-dimensional taxonomy,...