2026.05
MEDUSA repo is here!
MEDUSA repository is available on GitHub.
Ph.D. in Computer Sciences
Yilong Li
University of Wisconsin-Madison, advised by Prof. Suman Banerjee
I am a systems researcher who builds both hardware and software for intelligent edge systems. My work focuses on on-device AI, reinforcement-learning post-training for efficient edge intelligence, and wireless sensing systems.
I build the full stack: custom wearable and embedded hardware, accelerator-aware runtimes, sensing platforms, model adaptation pipelines, and post-training methods that make AI run under real-world compute, memory, energy, and privacy constraints. My work has appeared in MobiCom, ICLR, NSDI, and SenSys.
Recent Momentum
News / Updates
2026.03
CRANE was open-sourced for direct Apple Neural Engine inference
CRANE is now open-sourced for direct Apple Neural Engine inference without Core ML.
2026.01
NanoMind was accepted to ICLR 2026
Our work on efficient multimodal inference for battery-powered small devices was accepted to ICLR 2026.
2025.06
Distributed MIMO Radars was accepted to MobiCom 2025
Our work on scalable biometric sensing in the wild through distributed MIMO radars was accepted to MobiCom 2025.
2025.01
PalmBench was accepted to ICLR 2025
PalmBench, our benchmark of compressed large language models on mobile platforms, was accepted to ICLR 2025.
Research Systems
Research Projects
I build systems across sensing hardware, on-device AI, ML systems, and reinforcement-learning fine-tuning for efficient LLMs.
Theme 01
Hardware + Software
Building physical sensing and AI systems from RF hardware and embedded platforms through runtime software and model deployment.
Theme 02
Efficient Edge AI
Designing inference pipelines, accelerator mappings, and memory policies for devices with tight compute, energy, and context budgets.
Theme 03
Learning Under Constraints
Using model adaptation and reinforcement-learning fine-tuning to improve reasoning, retrieval, and memory under practical deployment limits.
Wireless Sensing
Medusa Wireless Sensing
Distributed UWB MIMO radar systems for robust biometric and vital-sign sensing in real-world indoor environments.
View project contextOn-Device AI
On-Device AI
Battery-powered multimodal assistant systems that combine custom hardware, embedded software, and local vision-language inference.
View project contextML Systems
ML Sys / EdgeFlow
Edge ML systems for efficient inference across constrained devices and heterogeneous accelerators, including direct ANE runtime support.
View project contextLLM Post-Training
LLM RL Fine-Tuning
Reinforcement-learning fine-tuning and agentic-memory methods for efficient long-horizon reasoning under compute and context budgets.
View project contextSelected Output
Selected Publications
Recent work on efficient multimodal inference, mobile AI benchmarking, and wireless sensing systems.
Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning
Repeated sampling with a verifier is a standard way to allocate test-time compute for code generation, but drawing K independent samples from one answer distribution often wastes the pass@K budget on near-duplicate re...
EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents
EMBER studies Budgeted Pre-Query Retention for long-horizon agents: an agent ingests a stream before future queries are known, keeps only a fixed budget of source evidence, and later answers from that retained memory ...
Tiny but Mighty: A Software-Hardware Co-Design Approach for Efficient Multimodal Inference on Battery-Powered Small Devices
Large Multimodal Models (LMMs) are inherently modular, consisting of vision and audio encoders, projectors, and large language models. Yet, they are almost always executed monolithically, which underutilizes the heter...
Scalable Biometric Sensing in the Wild through Distributed MIMO Radars
Radar-based techniques for detecting vital signs have shown promise for continuous contactless vital sign sensing and healthcare applications. However, real-world indoor environments face significant challenges for ex...
PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy concerns or impractical due to network...
Gemini: Integrating Full-fledged Sensing upon Millimeter Wave Communications
Integrating millimeter wave (mmWave)technology in both communication and sensing is promising as it enables the reuse of existing spectrum and infrastructure without draining resources. Most existing systems piggyback...
LiveTag: Sensing Human-Object Interaction through Passive Chipless WiFi Tags
Many types of human activities involve interaction with passive objects. Thus, by wirelessly sensing human interaction with them, one can infer activities at a fine resolution, enabling a new wave of ubiquitous comp...