OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data Paper • 2603.15594 • Published Mar 16 • 150
VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation Paper • 2601.02256 • Published Jan 5 • 33
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation Paper • 2601.02204 • Published Jan 5 • 64
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders Paper • 2510.19779 • Published Oct 22, 2025 • 62
