About
Research & Development
Advancing Traffic Prediction in Sensor-Scarce Urban Areas
TLDR: GenCast is a novel traffic forecasting model designed to predict traffic in regions lacking sensors. It achieves superior performance by integrating physics-informed neural...
Research & Development
Enhancing Audio AI Evaluation Through Perceptual Ranking
TLDR: QAMRO (Quality-aware Adaptive Margin Ranking Optimization) is a new framework for evaluating AI-generated audio (music, speech, general audio) that better aligns with human...
Research & Development
Bridging the Audio Gap: A New Approach to Robust Speech Recognition Across Diverse Channels
TLDR: A new research paper argues that ASR performance degradation across different audio recording channels is primarily due to intrinsic signal differences, not just...
Research & Development
DPGNet: Advancing Deepfake Detection with Unlabeled Data
TLDR: DPGNet is a new AI framework designed to detect highly realistic deepfake faces without relying heavily on manually labeled data. It tackles the...
Research & Development
SPARC: Enhancing Recommendations with Dynamic User Interests
TLDR: SPARC is a new retrieval model for recommender systems that addresses limitations of existing multi-interest models. It uses a learnable, dynamic interest space...
Research & Development
ASPIRE: A New AI Model for Understanding Diverse Structured Data
TLDR: ASPIRE (Arbitrary Set-based Permutation-Invariant Reasoning Engine) is a novel Universal Neural Inference model designed to process and make predictions on heterogeneous structured data....