Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism Paper • 2601.05524 • Published Jan 9 • 1
Double: Breaking the Acceleration Limit via Double Retrieval Collection 1 item • Updated 5 days ago • 1
Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making Paper • 2602.06570 • Published 21 days ago • 59
OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions Paper • 2602.05843 • Published 21 days ago • 57
Atlas: Orchestrating Heterogeneous Models and Tools for Multi-Domain Complex Reasoning Paper • 2601.03872 • Published Jan 7 • 43
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