| Jul 27, 2026 | Our paper AMBER: A Unified Accelerator for Multi-Precision LLM Inference Exploiting Bit-Level Redundancy and Reconfigurability presented at DAC 2026 in Long Beach, CA. |
| Jul 01, 2026 | Joined ByteDance as an AI chip engineer. |
| Jun 27, 2026 | Graduated with a Ph.D. from Tsinghua University. |
| Apr 15, 2026 | Our paper AMBER, a multi-precision LLM accelerator exploiting bit-level redundancy, accepted at DAC 2026. |
| Jan 22, 2026 | Our work MoBiLE, efficient MoE inference on consumer GPUs, presented at ASP-DAC 2026 in Hong Kong. |
| Nov 02, 2025 | Our work on Computing-in-Network for LLM processors presented at A-SSCC 2025 in Daejeon, Korea. |
| Oct 21, 2025 | Our work on efficient speculative LLM decoding uploaded to arXiv. |
| Feb 16, 2025 | Our work on energy-efficient edge LLM acceleration presented at ISSCC 2025 in San Francisco. |