Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Paper • 2604.10098 • Published 5 days ago • 66
AgentSwing: Adaptive Parallel Context Management Routing for Long-Horizon Web Agents Paper • 2603.27490 • Published 18 days ago • 16
ELT: Elastic Looped Transformers for Visual Generation Paper • 2604.09168 • Published 6 days ago • 18
SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning Paper • 2602.08234 • Published Feb 9 • 74