Program
The ACM MobiSys 2026 conference will take place from Sunday, June 21st to Thursday, June 25th, 2026.
Program Overview
| Sunday June 21Ray Dolby Centre | Monday June 22Ray Dolby Centre | Tuesday June 23Ray Dolby Centre | Wednesday June 24William Gates Building | Thursday June 25William Gates Building |
|---|---|---|---|---|
08:30 – 09:15 Registration | 08:00 – 08:45 Registration 08:45 – 09:00 Opening | 08:00 – 09:00 Registration | 08:00 – 09:30 Registration | 08:00 – 09:00 Registration |
09:15 – 17:30 Pre-Conference Events Coffee Breaks: 10:30 – 11:00 & 15:00 – 15:30 · Lunch: 12:30 – 14:00 | 09:00 – 10:30 | 09:00 – 10:30 | 09:30 – 10:30 | 09:00 – 17:00 Workshops
Coffee Breaks & Lunch · Schedule TBA — see Accepted Workshops |
10:30 – 11:00 Coffee Break | 10:30 – 11:00 Coffee Break | 10:30 – 11:00 Coffee Break | ||
11:00 – 12:00 | 11:00 – 12:00 | |||
12:00 – 13:00 Lunch | 12:00 – 13:00 Lunch | 12:00 – 13:00 Lunch | ||
13:00 – 14:00 | 13:00 – 14:00 | 13:00 – 13:30 13:30 – 14:30 | ||
14:00 – 15:30 Coffee Break with Posters & Demos (1) | 14:00 – 15:30 Coffee Break with Posters & Demos (2) | 14:30 – 15:30 Coffee Break | ||
15:30 – 16:45 | 15:30 – 16:30 | |||
16:45 – 17:45 SIGMOBILE Townhall Meeting | 16:30 – 16:45 Conference Closing Session | |||
18:00 – 20:00 | Starts 19:00 · 19:00 – 22:00 |
Detailed Program
Day 1: Monday, June 22
11:00 AM - 12:00 PM
Ray Dolby Centre
Session 1: Paper Preview + Material and Environmental Sensing
Session Chair: Zerina Kapetanovic
TIPS: Thermal Image based Plastics Sorting
Featured Paper
WheatScout: A Handheld Analyzer for Pre-Harvest Wheat Protein and Moisture Monitoring
Reliable Metal Foreign Object Detection for Mobile Wireless Charging via Harmonic Fingerprinting
1:00 PM - 2:00 PM
Ray Dolby Centre
Session 2: Mobile Agents and Personal AI Systems
Session Chair: Qiang Yang
TimelyLLM: Time-sensitive LLM Serving System for Physical-I/O Limited Agents
Featured Paper
Agent-X: Full Pipeline Acceleration of On-device AI Agents
SAIL: Redesigning Collaborative Language Inference with a Single Server-to-Mobile Handoff
MemoLens: Empowering Augmented Reality Glasses with Super Memory
[Emerging Ideas] Artificial Tripartite Intelligence: A Bio-Inspired, Sensor-First Architecture for Physical AI
AgentProg: Empowering Long-Horizon GUI Agents with Program-guided Context Management
Mobile GUI Agents under Real-world Threats: Are We There Yet?
3:30 PM - 4:45 PM
Ray Dolby Centre
Session 3: RF Perception and Large-Scale Signal Sensing
Session Chair: Dong Li
Towards Seeing Bones at Radio Frequency
Featured Paper
MulDar: Unleashing the Potential of Distributed COTS mmWave Radar by Exploiting Cross-Device Channels
TwinFocus: Autofocus for Handheld mmWave SAR Imaging via Physical and Digital Twin References
MuPose: Breaking the Scalability Barrier of mmWave Multi-User Pose Estimation in the Wild
ZA-SLAM: Leveraging Vision-Language Model for Zero-Shot Acoustic SLAM
Needle in a Haystack: Tracking UAVs from Massive Noise in Real-World 5G-A Base Station Data
Pinpointing Transmitting LEO Satellites from a Single Passive Array
Surface Characterization with mmWave Signals
Day 2: Tuesday, June 23
11:00 AM - 12:00 PM
Ray Dolby Centre
Session 4: Health, Human, and Bio-Sensing Systems
Session Chair: Akshay Garde
[Emerging Ideas] Phonotonos: Through-Skin Ultrasonic Blood Flow Sensing Using Smartphones
Featured Paper
BladderSense: A Wearable Ultrasound System for Continuous Bladder Monitoring in Real-World Use
Fine-grained Soundscape Control for Augmented Hearing
[Emerging Ideas] Towards Practical Metabolic Sensing with Wearable TEGs
GlucOS: Security, correctness, and simplicity for automated insulin delivery
Rapid Plant Health Monitoring for Leafy Greens through Carbon Dioxide Sensing
AquaCode: Turning Transaction Platforms into Non-Invasive Liquid Quality Checker
1:00 PM - 2:00 PM
Ray Dolby Centre
Session 5: Spatial AI and XR
Session Chair: Robert Likamwa
Towards Fast and Fully Automatic Drone Mapping
Featured Paper
BlenDR: Bandwidth-efficient RGB-D Representation and Delivery for Live 3D Video Streaming
AdaSprite: Resource-efficient Online Co-Adaptation for V2I Systems Under Large-scale Data Drifts
Ouroboros: Instilling Motion Awareness in ViTs for Efficient Video Analytics on the Edge
HoloMobile: Photorealistic Avatar on Mobile via Compact Dynamic Gaussians from a Monocular Video
[Emerging Ideas] ConCord: Human-in-the-Loop, Cooperative Robot Exploration
Building Audio-Visual Digital Twins with Smartphones
3:30 PM - 4:45 PM
Ray Dolby Centre
Session 6: Communication Systems and Spectrum
Session Chair: Ruichun Ma
BeamFormer: Transformer-based Beam Management for 6G Networks
Featured Paper
Wideband Low-complexity High-speed 5G NR Backscatter
Listen Over the Air: Towards Long-Range Low-Power Backscatter Downlink
BeamMix: 3D Gaussian Mixture-of-Experts for Element-Space Wireless Channel Modeling
RF Super Resolution: A Deep Learning Approach to Spatial Enhancement for LoRa
SpecSentry: Micro-power Wideband Spectrum Surveillance for Ephemeral Transmissions
AquaScope: Reliable Underwater Image Transmission on Mobile Devices
[Emerging Ideas] OrbitTransit: Traffic Delivery and Diffusion for Earth Observation via Satellite Mobility
Day 3: Wednesday, June 24
9:30 AM - 10:30 AM
William Gates Building
Session 7: On-Device AI
Session Chair: Dongqi Cai
Vec-LUT: Vector Table Lookup for Parallel Ultra-Low-Bit LLM Inference on Edge Devices
Featured Paper
SpMAP: Transparent Sparsity for LLMs
ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference
Act Before It's Too Late: Power-Efficient LLM Inference on Mobile Device
FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs
KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference
VLMCache: Efficient On-Device Vision-Language Model Inference
11:00 AM - 12:00 PM
William Gates Building
Session 8: Learning for Sensing Systems
Session Chair: Rui Xiao
Physical Self-Supervised Learning: IMU Sensing without Manual Labels
Featured Paper
A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning
Solving Scarce Wireless Signal Dilemma in Model Training using Cross-Modal Learning Leveraging Limited Video Data
ADL-CLIP: Text-Aligned RF Representation for Continuous ADL Detection in Home Environments
DeformRF: Data-driven Beamforming and Direction Finding with Deformable Antenna Arrays
StreamSplit: Continuous Audio Representation Learning via Uncertainty-Guided Adaptive Splitting
Diversified Neural Networks: Defeating Adversarial Attacks via Numerous Orthogonal Variants
1:30 PM - 2:30 PM
William Gates Building
Session 9: Systems and Security
Session Chair: Tao Ni
Insecurity of Lost/Stolen Phone Reporting Services: Vulnerabilities, Attacks, and Countermeasures
Featured Paper
GeoTwins: Uncovering Hidden Geographic Disparities in Android Apps
Fragile Deliveries: Inconsistencies in Android Parcel and Their Security Consequences
Analysis of Always-Listening Services on Android
Hide-and-Sweep: Detecting Concealed Cameras via LED Illumination Sweeps
Ringmaster: How to juggle high-throughput host OS system calls from TrustZone TEEs
Bringing Confidential Computing to Android
3:30 PM - 4:30 PM
William Gates Building
Session 10: Novel Hardware and Edge Design
Session Chair: Zehua Sun
Microwatt Microwave (M²) Oscillator: Going Beyond the Delegation Architecture of Low-power Wireless Communication
Featured Paper
AutoRF: Towards an Agentic Framework for Automated RF Hardware Design
[Emerging Ideas] IoTGen: Towards LLM-driven IoT Hardware Generation
BIONIC: A Co-Designed Hardware and Runtime for Time-Sensitive Battery-Free IoT
[Emerging Ideas] A Greener Edge: A Framework on Carbon-aware Edge ML System Design
WiMirror: Towards 802.11-Compliant RIS Control Using Compressed Beamforming Reports
Armstrong: A Full-Duplex Backscatter Architecture for the mmWave IoT
