SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? Paper • 2605.30329 • Published 8 days ago • 8
SwanVoice: Expressive Long-Form Zero-Shot Speech Synthesis for Both Monologue and Dialogue Paper • 2605.30993 • Published 7 days ago • 56
Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents Paper • 2605.28775 • Published 9 days ago • 38
FastKernels: Benchmarking GPU Kernel Generation in Production Paper • 2605.23215 • Published 14 days ago • 8
An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU Paper • 2603.16428 • Published Mar 17 • 51