#knowledge-distillation

Knowledge Distillation

2 stories tagged Knowledge Distillation

researchApr 13, 2026

WAND: Efficient Autoregressive TTS with Windowed Attention and Knowledge Distillation

Researchers introduce WAND, a framework that reduces the computational and memory costs of autoregressive text-to-speech models by using windowed attention and knowledge distillation. This approach maintains high-fidelity speech output while making the models more scalable.

via ArXiv cs.CL#tts #attention #efficiency

researchApr 10, 2026

KD-MARL: Efficient Knowledge Distillation for Edge-Ready Multi-Agent Systems

Researchers propose a new method for resource-aware knowledge distillation in multi-agent reinforcement learning (MARL). The approach addresses the challenges of deploying expert policies on edge devices by focusing on coordination structure and heterogeneous agent capabilities.

via ArXiv cs.AI#marl #knowledge-distillation #edge-computing