About
Research & Development
AI Unlocks Deeper Biomedical Insights for Faster Drug Repurposing
TLDR: LLaDR is a novel framework that significantly improves drug repurposing by integrating common-sense biomedical knowledge from large language models (LLMs) into knowledge graph...
Research & Development
CompoDistill: Enhancing Visual Perception in Compact Multimodal AI Models
TLDR: CompoDistill is a new knowledge distillation framework for Multimodal Large Language Models (MLLMs) that addresses "visual attention misalignment" between teacher and student models....
Research & Development
MoRA: Tailoring Large Language Models for Molecular Understanding
TLDR: MoRA is a novel AI framework that enables Large Language Models (LLMs) to dynamically adapt to individual molecular structures. It generates unique, molecule-specific...
Research & Development
Diffusion Models Reshape Reinforcement Learning: A New Era for AI Decision-Making
TLDR: This research paper provides a comprehensive survey on the integration of Diffusion Models (DMs) with Reinforcement Learning (RL). It highlights DMs' advantages like...
Research & Development
Unlocking Selective Listening: A New Brain-Controlled Approach to Speaker Extraction
TLDR: TFGA-Net is a novel deep learning model that uses electroencephalography (EEG) signals from a listener's brain to directly extract a target speaker's voice...
Research & Development
LLMs Grapple with Human Disagreement: A Look at Test-Time Scaling in Nuanced NLP Tasks
TLDR: A study on Large Language Models (LLMs) and "test-time scaling" methods found that while Model Averaging and Majority Voting improve performance on NLP...