SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue Paper • 2605.30993 • Published 18 days ago • 58
FastKernels: Benchmarking GPU Kernel Generation in Production Paper • 2605.23215 • Published 25 days ago • 8
KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving Paper • 2605.13734 • Published May 13 • 12
HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents Paper • 2604.07430 • Published Apr 8 • 189