A Situational Speech Synthesizer for Yoruba: System Design, Phonological Rule Architecture, and Orthographic Extensions for Contour
Research
Research News
New papers, breakthroughs and academic AI research
Masked Self-Distillation: Internalizing the Chain-of-Thought in Language Models
Research
Fixed-point neural samplers on discrete spaces
Research
Physics-Refined Spatiotemporal Forecasting on Open-Boundary Hydrologic Graphs
Research
SkillEvoLean: Mutation-enhanced skill evolution for Lean provers
Research
Vision-language models for chest radiography do not always need the image
Research
CARD: Cross-component Audio Representation Distillation for Encoder-Free Audio Captioning
Research
Accelerating Constrained Decoding with Token Space Compression
Research
Evidence-Gated Research: Statistically Controlled Model Adoption in Adaptive Search
Research
Leveraging Instruction Tuning and Merging for Reasoning Model Adaptation
Research
Function-Structured Reinforcement Learning with Executable Verifiers for Mathematical Reasoning
Research
SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples
Research