About
Research & Development
Recover-LoRA: Restoring Accuracy in Degraded Language Models Without Labeled Data
TLDR: Recover-LoRA is a novel, lightweight, and data-free method that restores the accuracy of degraded language models (SLMs) that have suffered performance drops due...
Research & Development
Unlocking User Intent: How Small Language Models Are Enhancing Recommendations with ‘Thought Space’
TLDR: The research paper introduces PULSE, a framework that uses Small Language Models (SLMs) to create a "Thought Space" for recommender systems. Unlike traditional...
Research & Development
Streamlining Android Development: How Specialized AI Tools Fix Build Errors
TLDR: This research introduces AndroidBuildBench, a benchmark of 1,019 real-world Android build failures, and GradleFixer, an LLM agent with domain-specific tools for automated build...
Research & Development
Guiding Language Models with Energy: Fewer False Refusals, More Helpful Responses
TLDR: A new research paper introduces Energy-Driven Steering (EDS), a fine-tuning-free framework that significantly reduces false refusals in large language models (LLMs) without compromising...
Research & Development
Unpacking Personal Narratives: A New Framework for Analyzing Linguistic Style
TLDR: This research introduces a framework to formalize style in personal narratives by analyzing patterns in linguistic choices like processes, participants, and circumstances, automatically...
Research & Development
DPCformer: A New Deep Learning Approach Enhances Crop Trait Prediction
TLDR: DPCformer is a novel deep learning model integrating CNNs and self-attention for genomic prediction in crops. It uses an 8-dimensional SNP encoding and...