Resource:Paper Carnival 2025

  Paper carnival 2025, Time: 2025-8-27 ~ 2024-8-28, Location: A518; Reading list can be found here.

Day 1

System Track

1. LLM Cache Optimization - Qinyong Li "9:20-10:00"

• [Eurosys'25] CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
• [MobiCom'24] CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving

2. Video Analytics - Xinyan Wang "10:00-10:40"

• [ISCA'24] DACAPO: Accelerating Continuous Learning in Autonomous Systems for Video Analytics
• [NSDI'23] RECL: Responsive Resource-Efficient Continuous Learning for Video Analytics
• [MM'23] Edge-Assisted On-Device Model Update for Video Analytics in Adverse Environments

3. Disaggregated OS - Haifeng Huang "10:40-11:20"

• [NSDI'25] Beehive: A Scalable Disaggregated Memory Runtime Exploiting Asynchrony of Multithreaded Programs

4. Code Generation - Youwei Ran "11:40-12:10"

• [Mobicom'25] AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation

Network Track 14:00-17:00

1. ML in LoRa Reception - Kai Chen"14:00-14:40"

• [ICNP'23] Hi2LoRa: Exploring Highly Dimensional and Highly Accurate Features to Push LoRaWAN Concurrency Limits with Low Implementation Cost
• [SenSys'24] Enhancing LoRa Reception with Generative Models: Channel-Aware Denoising of LoRaPHY Signals
• [ICNP'24] Deepdetangle: Deep Learning-Based Fusion of Chirp-Level and Packet-Level Features for Lora Parallel Decoding

2. Quantum network - Yaliang "14:40-15:20"

• [INFOCOM'22] E2E Fidelity Aware Routing and Purification for Throughput Maximization in Quantum Networks
• [JSAC'24] On Optimum Entanglement Purification Scheduling in Quantum Networks
• [INFOCOM'25] Link Configuration for Fidelity-Constrained Entanglement Routing in Quantum Networks

3. V2V Networks - Zhenguo Bi "14:30-15:10"

• [INFOCOM'25] RoCooper: Robust Cooperative Perception under Vehicle-to-Vehicle Communication Impairments

4. Lora - Mengyu "15:10-16:00"

• [ToN'24] RALoRa: Rateless-Enabled Link Adaptation for LoRa Networking
• [TMC'25] Enhancing Link Performance for Mobile LoRa Networks

5. Offloading - Yi Zhou "16:00-16:30"

• [MobiSys 2024]LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices

6.UAV - Jiahao He "16:30-17:00"

• [T-RO'25]FAPP: Fast and Adaptive Perception and Planning for UAVs in Dynamic Cluttered Environments

Day 2

Edge Track 9:00-11:50

1.Volume Video- Mengfan Wang "9:00-9:30"

• [Mobicom'24] An End-to-End, Low-Cost, and High-Fidelity 3D Video Pipeline for Mobile Devices

2.Volume Video- Jiyi Wu "9:30-10:10"

• [TOG'23] 3D Gaussian Splatting for Real-Time Radiance Field Rendering
• [TOG'24] V^3: Viewing Volumetric Videos on Mobiles via Streamable 2D Dynamic Gaussians

3. LLM-driven applications - Bairong Liu "10:10-10:50"

• [ICSE'25] InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translation
• [Arxiv] AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications

4. Inference Optimization - Ruizheng Zhang "10:50-11:20"

• [INFOCOM'25] DUNE: Distributed Inference in the User Plane

5. Edge LLM - Junzhe Guan "11:20-11:50"

• [INFOCOM'25] TensAllo: Adaptive Deployment of LLMs on Resource-Constrained Heterogeneous Edge Devices