SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks Paper • 2602.12670 • Published Feb 13 • 56
End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions Paper • 2601.17640 • Published Jan 25 • 5
End-to-End Joint ASR and Speaker Role Diarization with Child-Adult Interactions Paper • 2601.17640 • Published Jan 25 • 5
Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis Paper • 2601.14417 • Published Jan 20 • 5
VoxCog: Towards End-to-End Multilingual Cognitive Impairment Classification through Dialectal Knowledge Paper • 2601.07999 • Published Jan 12 • 1
Quantifying Speaker Embedding Phonological Rule Interactions in Accented Speech Synthesis Paper • 2601.14417 • Published Jan 20 • 5
LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning Paper • 2512.05325 • Published Dec 5, 2025 • 4
LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning Paper • 2512.05325 • Published Dec 5, 2025 • 4
Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe Paper • 2508.01691 • Published Aug 3, 2025 • 10
Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models Paper • 2505.14071 • Published May 20, 2025 • 1
Sample Efficient Preference Alignment in LLMs via Active Exploration Paper • 2312.00267 • Published Dec 1, 2023