arxiv:2401.15071
Kexin Huang
CaasiHUANG
AI & ML interests
SpeechLLM, LLM/AI Safety
Recent Activity
upvoted a paper 26 days ago
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs upvoted a paper 29 days ago
EmoNet-Voice: A Fine-Grained, Expert-Verified Benchmark for Speech
Emotion Detection upvoted a paper about 2 months ago
Measuring Audio's Impact on Correctness: Audio-Contribution-Aware
Post-Training of Large Audio Language ModelsOrganizations
None yet