FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution Paper • 2608.16157 • Published Aug 17 • 113
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation Paper • 2605.13724 • Published May 13 • 104
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization Paper • 2602.02958 • Published Feb 3 • 35