3 papers
cs.CV2026
Spheriverse: 3D Scene Understanding from Spherical Observations in the Wild
Fei Teng, Sheng Wu, Mengfei Duan +7
Spherical observations provide global visual context for 3D scene understanding. However, visual information is encoded in an angular domain, whereas the physical world is represen…
cs.CL2026
Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM Inference
Zheyuan Wang, Siyu Li, Peiqiao Song +3
Large language model (LLM) cascades answer easy requests with a small model and escalate selected requests to a larger model. Most routers prioritize examples on which the small mo…
cs.CL2026
CEDAR: Error-Bounded Residual Routing for Efficient Long-Context Attention
Siyu Li, Dong Wang, Jie Zhou +3
Post-hoc sparse attention accelerates long-context prefill by routing each query to a small set of token-level interactions. Hard selection, however, assigns zero probability to ev…