1 citations · 1 across the 12 of their papers we have counts for
14 papers
Repair Changes Which Layers to Remove: Exact Optima for Depth Pruning of Language Models
Jianchang Su, Dawei Xiang, Yifan Zhang +1
Depth pruning removes entire transformer layers to make large language models faster, and recent methods recover quality by replacing the removed layers with a training-free linear…
Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM Evaluation
Jianchang Su, Dawei Xiang, Yifan Zhang +1
LLM-agent evaluation reports behavioral scores but leaves the identity of the deployed runtime stack unreported. A tampered deployment that preserves evaluated outputs passes every…
HBFSim: Fast and Faithful Simulation of High-Bandwidth Flash Under Real GPU Execution
Yanpeng Hu, Yiwei Yang, Yuanwu Zhu +3
High-Bandwidth Flash (HBF) places high-capacity NAND beside HBM to relieve the memory-capacity bottleneck of LLM inference, yet its system-level behavior cannot be evaluated before…
When Can Agents Safely Checkpoint, Fork, Restore, and Merge? Exact Checking for Execution Edits
Yusheng Zheng, Xiaoyu Song, Yanpeng Hu +3
Agent runtimes can Checkpoint an execution, Fork it, Restore a checkpoint, or Merge branches without restarting a task. We call these operations execution edits, with Checkpoint re…
Characterizing and Bridging the Diagnostic Gap in eBPF Verifier Rejections
Yusheng Zheng, Zhengjie Ji, Weichen Tao +5
eBPF lets developers run custom programs inside the Linux kernel, where a verifier proves each program safe. However, when the verifier rejects a program, the unclear error makes r…
MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
Kexin Chu, Yang Zhou, Wei Zhang
Temperature-zero BF16 LLM inference is often treated as reproducible, yet the same request can emit different tokens when decoded alone or inside a larger batch. Existing fixes use…
ACRFence: Preventing Semantic Rollback Attacks in Agent Checkpoint-Restore
Yusheng Zheng, Yiwei Yang, Wei Zhang +1
LLM agent frameworks increasingly offer checkpoint-restore for error recovery and exploration, advising developers to make external tool calls safe to retry. This advice assumes th…
Dynamic Expert Quantization for Scalable Mixture-of-Experts Inference
Kexin Chu, Dawei Xiang, Zixu Shen +3
Mixture-of-Experts (MoE) has become a practical architecture for scaling LLM capacity while keeping per-token compute modest, but deploying MoE models on a single, memory-limited G…
ExpertFlow: Adaptive Expert Scheduling and Memory Coordination for Efficient MoE Inference
Zixu Shen, Kexin Chu, Yifan Zhang +3
The expansion of large language models is increasingly limited by the constrained memory capacity of modern GPUs. To mitigate this, Mixture-of-Experts (MoE) architectures activate…
Towards Agentic OS: An LLM Agent Framework for Linux Schedulers
Yusheng Zheng, Yanpeng Hu, Wei Zhang +1
Operating system schedulers suffer from a fundamental semantic gap, where kernel policies fail to understand application-specific needs, leading to suboptimal performance. We intro…
PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization
Dawei Xiang, Wenyan Xu, Kexin Chu +5
The rapid advancement of generative AI has democratized access to powerful tools such as Text-to-Image models. However, to generate high-quality images, users must still craft deta…
CXLAimPod: CXL Memory is all you need in AI era
Yiwei Yang, Yusheng Zheng, Yiqi Chen +5
The proliferation of data-intensive applications, ranging from large language models to key-value stores, increasingly stresses memory systems with mixed read-write access patterns…
Selective KV-Cache Sharing to Mitigate Timing Side-Channels in LLM Inference
Kexin Chu, Zecheng Lin, Dawei Xiang +7
Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversari…
MVVM: Deploy Your AI Agents-Securely, Efficiently, Everywhere
Yiwei Yang, Aibo Hu, Yusheng Zheng +6
The rise of AI agents powered by Large Language Models (LLMs) presents critical challenges: how to securely execute and migrate these agents across heterogeneous environments while…