2 papers
cs.CV2026
Semantic Head Specialization Guides Hybrid ViT Attention for Multimodal LLMs
Chenhong He, Lei Li, Shicheng Li +5
Hybrid attention dominates frontier LLMs, yet Vision Transformers (ViTs) in multimodal LLMs lack a satisfactory hybrid design, with no consensus on why certain attention patterns w…
cs.CL2026
PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems
Hanglong Lv, Dawei Zhu, Lei Li +11
Large language models are increasingly used as agentic workflow executors, yet existing training data and benchmarks largely assume informationally complete, single-turn queries. O…