3 papers
cs.LG2026
Depth Exploration for LLM Decoding
Weisi Yang, Zipeng Sun, Stephen Xia
Autoregressive LLM decoding evaluates every generated token through the full layer stack, even though many tokens become predictable at intermediate depths. Existing lossless depth…
cs.LG2025
MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs
Hongjun Xu, Junxi Xia, Weisi Yang +2
Deploying Mamba models on microcontrollers (MCUs) remains challenging due to limited memory, the lack of native operator support, and the absence of embedded-friendly toolchains. W…
cs.CR2025
Towards Scalable Defenses against Intimate Partner Infiltrations
Weisi Yang, Shinan Liu, Feng Xiao +2
Intimate Partner Infiltration (IPI)--a type of Intimate Partner Violence (IPV) that typically requires physical access to a victim's device--is a pervasive concern around the world…