No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping Paper • 2509.21880 • Published Sep 26, 2025 • 52
Evaluation of Deep Audio Representations for Hearables Paper • 2502.06664 • Published Feb 10, 2025 • 3
With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You Paper • 2506.16895 • Published Jun 20, 2025 • 1