English is Not All You Need: Systematically Exploring the Role of Multilinguality in LLM Post-Training
Research
Research News
New papers, breakthroughs and academic AI research
Confident in a Confidence Score: Investigating the Sensitivity of Confidence Scores to Supervised Fine-Tuning
Research
Closing the Speech-Text Gap with Limited Audio for Effective Domain Adaptation in LLM-Based ASR
Research
Beyond the Raw Waveform: Fusing Visual Representations of EDA for Stress Detection
Research
Comparative Analysis of State-of-the-Art Foundation Models for Sleep Analysis Under Channel Reduction
Research
Graph Learning for Cross-Subject, Cross-Population EEG Emotion Decoding and Model-Derived Spatial-Spectral Neural Signatures
Research
What Makes Good Multilingual Reasoning? Disentangling Traces with Measurable Features
Research
Leakage-Safe Empirical Benchmarking of EEG-Based Machine Learning Pipelines for Dementia Classification
Research
MedGPT-oss: Training a General-Purpose Vision-Language Model for Biomedicine
Research
Learning Dynamic Neural Evidence Representations for Time-Adaptive Brain-Computer Interfaces
Research
When Is Availability-Aware Training Worth It? A Benchmark and Empirical Study of Interruption-Resilient Optimization Under Predictable Compute Schedules
Research
Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models
Research