How Robust Are Neural Audio Codecs for African Speech? A Multi-Task Benchmark and the Limits of Perceptual Quality
Research
Research News
New papers, breakthroughs and academic AI research
On-Device Commercial Intent Retrieval Under Size, Latency, and Privacy Constraints: A 3 MiB Retrieval System with Typed Egress Boundaries
Research
Oneira: From Open-Ended Generation to Open-World Interaction in Video World Models
Research
System Attribution in LLM Brand Recommendations: Single Responses Identify the System, Aggregated Brand Profiles Do Not Transfer
Research
Fusing Visual and Textual Representations via Multi-layer Fusing Transformers for Vietnamese Visual Question Answering
Research
DiVid: Diagnosing Dimension-Specific Diversity Collapse in Video Generation Models
Research
TrueMuse: A Benchmark for Data Attribution in Text-to-Music Models
Research
Authorization for Self-Modifying AI Agent Populations: Conserving Authority across Replacement, Forking, and Rollback
Research
SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning
Research
Fixing a Model That Learned Worse Cancer Means Lower Risk: Monotonic Constraints in Bladder Cancer Recurrence Prediction
Research
Diffusion Editing with Soft Mask: Pixel Level Redo of Image and Video with Adjustable Strength
Research
A Shared Taste for Model-Written Text: The Generator-by-Selector Matrices of "AI-AI Bias" Show No Detectable Own-Model Premium
Research