研究的交汇处

2024 / ACM MobiCom 2024

FlexNN: Efficient and Adaptive DNN Inference on Memory-Constrained Edge Devices

第一作者 (1/5)

在内存受限的端侧设备上实现高效、自适应的 DNN 推理。

• Memory Management
• Scheduling
• Adaptive Inference

Edge AI

2026 / ACM MobiSys 2026

Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices

共同第一作者 (1/6)

通过向量查表加速端侧 CPU 上的并行超低比特 LLM 推理。

• Low-bit Inference
• Kernel Optimization
• Matrix Multiplication

Large Language Models (LLMs) · Edge AI

2026 / IEEE Transactions on Mobile Computing (TMC)

DWI: Efficient On-Device LLM Decoding Through Dynamic Width Selection on Nested Models

合作作者 (3/6)

通过嵌套模型的动态宽度选择提升端侧 LLM 解码效率。

• Adaptive Inference

Large Language Models (LLMs) · Edge AI

2025 / IEEE Transactions on Mobile Computing (TMC)

Squeezer: Efficient Multi-DNN Inference for Edge Video Analytics via Cross-Model Scheduling

合作作者 (5/8)

通过跨模型调度优化端侧视频分析中的多 DNN 推理。

• Scheduling

Edge AI · Video Analytics

2022 / ISCA 2022

DIMMining: Pruning-Efficient and Parallel Graph Mining on Near-Memory-Computing

合作作者 (6/9)

面向近存计算的高效剪枝与并行图挖掘。

• Graph Mining
• Near-memory Computing

2026 / ACM MobiSys Companion 2026

Building Efficient Inference Systems for Resource-Constrained Edge AI Deployment

独立作者 · 博士工作概述 (1/1)

总结面向资源受限端侧智能部署的高效推理系统研究。

• Efficient Inference
• Adaptive Inference
• Inference Runtimes

Edge AI

2026 / ArXiv preprint

OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism

第一作者 (1/6)

统一 KV 缓存管理，协调 VLA 中动作与语言的并发生成。

• KV Cache Management
• Scheduling
• Continuous Batching
• Inference Runtimes

Vision-Language-Action Models (VLAs) · Edge AI

2026 / ArXiv preprint

Embodied.cpp: A Portable Inference Runtime of Embodied AI Models on Heterogeneous Robots

合作作者 (5/11)

面向异构机器人的可移植具身模型推理运行时。

• Inference Runtimes
• Heterogeneous Computing
• Kernel Optimization
• Closed-loop Control

Vision-Language-Action Models (VLAs) · World-Action Models (WAMs) · Edge AI

2026 / ArXiv preprint

ActProbe: Action-Space Probe for Early Failure Detection of Generative Robot Policies

共同第一作者 (2/11)

利用动作空间探针提前检测生成式机器人策略的失败。

• Failure Detection

Vision-Language-Action Models (VLAs)

2026 / ArXiv preprint

Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation

合作作者 (5/11)

通过上下文因果学习提升具身操作的泛化能力。

• In-context Adaptation
• Interaction Memory
• Causal Representation Learning
• Policy Adaptation
• Test-time Scaling

Vision-Language-Action Models (VLAs) · World-Action Models (WAMs)

2026 / ArXiv preprint

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

合作作者 (7/15)

面向自进化物理智能的闭环具身框架。

• Self-improvement
• Failure Recovery
• Closed-loop Control
• Failure Detection
• Robot Simulation
• Scheduling
• Heterogeneous Computing
• Quantization

Embodied Agents

2026 / ArXiv preprint

EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents

合作作者 (9/15)

通过技能感知反思推动具身智能体自进化。

• Reflection
• Self-improvement

Embodied Agents

2024 / ArXiv preprint

Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security

效率章节负责人 (4/25)

综述个人 LLM 智能体的能力、效率与安全，负责效率章节。

• Personal Agents
• Efficient Inference
• Security and Privacy

Personal Agents · Large Language Models (LLMs)

2024 / ArXiv preprint

ChainStream: An LLM-based Framework for Unified Synthetic Sensing

合作作者 (6/9)

基于 LLM 的统一合成感知框架。

• Context Sensing
• Program Synthesis
• Stream Processing

Large Language Models (LLMs)

2025 / EMNLP 2025

An Empirical Study of LLM Reasoning Ability Under Strict Output Length Constraint

合作作者 (6/11)

研究严格输出长度约束下 LLM 的推理能力。

• LLM Reasoning
• Test-time Scaling

Large Language Models (LLMs) · Edge AI

2026 / 开源项目

Cosmos Lite: Efficient inference for Cosmos 3 robot policies

项目维护 (project)

结合量化、内核优化与并行 rollout，在 24 GB GPU 上部署世界动作模型。

• Low-bit Inference
• Kernel Optimization
• Inference Runtimes
• Robot Simulation
• Scheduling

World-Action Models (WAMs)

2025 / 已合入上游的开源贡献

GPTQv2 format support in vLLM

开源贡献者 (contribution)

修正 vLLM 中低比特与非对称 GPTQv2 推理的零点处理。

• Low-bit Inference
• Kernel Optimization

Large Language Models (LLMs)