Double: Breaking the Acceleration Limit via Double Retrieval Collection 0 items • Updated 15 days ago • 1
Double: Breaking the Acceleration Limit via Double Retrieval Collection 0 items • Updated 15 days ago • 1
Speculative Decoding via Hybrid Drafting and Rollback-Aware Collection 1 item • Updated 15 days ago • 1
Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning Paper • 2601.03872 • Published 19 days ago • 42
HyperVL: An Efficient and Dynamic Multimodal Large Language Model for Edge Devices Paper • 2512.14052 • Published Dec 16, 2025 • 42
Speculative Decoding via Hybrid Drafting and Rollback-Aware Branch Parallelism Paper • 2506.01979 • Published May 16, 2025 • 1