FlexServe introduces recallable secure memory and NPU to enable cooperative secure LLM inference on mobile devices, reporting 10.05X TTFT speedup over a basic TrustZone strawman.
arXiv:2509.00531 [cs.MA] https://arxiv.org/abs/2509.00531
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
Page-granular Flex-Mem and switchable Flex-NPU cut TrustZone LLM TTFT by ~10× vs a CMA strawman and ~2.4× vs a pipelined secure-NPU strawman on RK3588.
DeltaBox achieves 14 ms checkpoint and 5 ms rollback for AI agent sandboxes via layered DeltaFS and incremental DeltaCR mechanisms that exploit similarity between consecutive states.
EdgeFlow reduces mobile LLM cold-start latency up to 4.07x versus llama.cpp, MNN, and llm.npu by NPU-aware adaptive quantization, SIMD-friendly packing, and synergistic granular CPU-NPU pipelining at comparable accuracy.
SE-GA combines Test-Time Memory Extension for dynamic context retrieval with Memory-Augmented Self-Evolution training to reach 89.0% on ScreenSpot and 75.8% on AndroidControl-High.
citing papers explorer
-
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
FlexServe introduces recallable secure memory and NPU to enable cooperative secure LLM inference on mobile devices, reporting 10.05X TTFT speedup over a basic TrustZone strawman.
-
FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation
Page-granular Flex-Mem and switchable Flex-NPU cut TrustZone LLM TTFT by ~10× vs a CMA strawman and ~2.4× vs a pipelined secure-NPU strawman on RK3588.
-
DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
DeltaBox achieves 14 ms checkpoint and 5 ms rollback for AI agent sandboxes via layered DeltaFS and incremental DeltaCR mechanisms that exploit similarity between consecutive states.
-
EdgeFlow: Fast Cold Starts for LLMs on Mobile Devices
EdgeFlow reduces mobile LLM cold-start latency up to 4.07x versus llama.cpp, MNN, and llm.npu by NPU-aware adaptive quantization, SIMD-friendly packing, and synergistic granular CPU-NPU pipelining at comparable accuracy.
-
SE-GA: Memory-Augmented Self-Evolution for GUI Agents
SE-GA combines Test-Time Memory Extension for dynamic context retrieval with Memory-Augmented Self-Evolution training to reach 89.0% on ScreenSpot and 75.8% on AndroidControl-High.