Ph.D. Candidate, AIR, Tsinghua University
I am a 4th year Ph.D. candidate at AIR, THU, working on on-device AI (Ph.D. work overview) and embodied AI. Currently I am exploring efficient deployment of embodied foundation models (VLAs and WAMs), as well as self-evolving physical intelligence.
ArXiv preprint, 2026
ACM MobiSys 2026Best Paper Award Runner-Up, Results Reproduced @AE
ArXiv preprint, 2024Survey & Position, “Efficiency” Section Lead
How quantization, sampler tuning, kernel work, and rollout topology accelerate NVIDIA's 16B Cosmos 3 robot policies on 24 GB GPUs — from single-request serving to full 1,200-episode evaluations.
Vec-LUT turns repetitive scalar table lookups into contiguous vector reads, accelerating parallel ternary LLM inference on x86 and ARM CPUs by up to 4.2×.
An analysis of GPTQv2 format limitations in vLLM and the CUDA kernel changes needed for low-bit asymmetric quantization inference.
