I publish as Yu Mao. I'm a Research Scientist at ByteDance working on AI infrastructure: LLM inference and reproducibility, compression and representation, model capability, and agent reliability. I received my Ph.D. in Computer Science from City University of Hong Kong and am based in San Jose.
Homepage · Publications · Google Scholar · LinkedIn
| Project | Status | Question | Start with |
|---|---|---|---|
| KVBytePack | Reproducible artifact | When do smaller KV records pay for their codec cost? | Public records, CPU cost and memory measurements |
| BitExact LLM | Research prototype | What stays identical when inference execution changes? | Reproduction guide · Scoped vLLM plugin evidence |
| AIBrix Hybrid KV Cache | Experimental | What state must a hybrid prefix cache preserve? | CPU storage/trace example · RFC · Open draft PR #3221 |
| Random-Reward RL Probe | Paper artifact | What can training reach without correctness feedback? | Paper result CSVs and GPU-free figure reproduction |
These projects expose their tradeoffs and evidence: byte-preserving codecs, explicit inference-identity contracts, independently testable storage behavior, and reported training outcomes. The open draft AIBrix PR proposes only the byte-store contract, excludes the hybrid serving connector and codecs, and has not been merged. The hybrid integration's model equivalence is still unresolved; BitExact's current H800 plugin runs are scoped to the recorded models, versions and configurations; its CPU checks and device reports do not certify every device.
Earlier compression work includes TRACE (WWW 2022), with follow-ups at ACM MM 2022 and DAC 2023.
I'm also building Hushword: speak in the app you're using, then return to writing. It combines local Whisper with Apple Speech and offers an optional Agent rewrite after dictation.
Build and try it on an Apple Silicon Mac · Where audio and text are processed
- AgentPProf: Semantic Profiler for AI Agents · AgenticOS @ SOSP 2026 · 🏆 Best Paper Award
- Probe with Participation Trophies: Random-Reward RL as a Probe of LLM Capability · Preprint 2026
- WISE: A Framework for Gigapixel Whole-Slide-Image Lossless Compression · CVPR 2025
- PMR: Fast Application Response via Parallel Memory Reclaim on Mobile Devices · USENIX ATC 2025
- When Compression Meets Model Compression: Memory-Efficient Double Compression for Large Language Models · EMNLP Findings 2024
- Faster and Stronger Lossless Compression with Optimized Autoregressive Framework · DAC 2023
- TRACE: A Fast Transformer-based General-purpose Lossless Compressor · WWW 2022
Full list on my homepage and Google Scholar.
Python · PyTorch · Triton · CUDA · vLLM · Go · eBPF


