2 papers
cs.LG2026
EdgeRock: Strong Reasoning at Constant Memory
Huishan Ji, Hua Xu, Weiming Zhang +3
We present EdgeRock, a family of multimodal models that deliver strong reasoning at constant memory. Most models keep reasoning history in a key-value (KV) cache that grows with ev…
cs.CL2026
Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality
Xunlei Chen, Qirui Ye, Yuang Li +5
Large language models (LLMs) require effective unlearning to address privacy regulations and safety concerns. However, achieving precise forgetting without compromising general uti…