News
Since starting the Ph.D. in January 2025. Papers in full are on the publications page.
2026
- Our paper SIM-D2NN (on onboard terrain classification straight from raw SAR data, using a stacked metasurface as the classifier) was accepted to IEEE Transactions on Signal Processing.
- Two of our papers were accepted to the NeurIPS 2026 Evaluations and Datasets Track: WirelessMathBench-XL, a wireless-math benchmark shipped with a rerunnable contamination audit, and DebateLedger, a protocol separating harmful collapse from useful correction in multi-agent LLM debate.
- Two of our papers were accepted to EMNLP 2026: TLVC, on picking the right verifier for best-of-K reasoning selection (Findings), and GraphReduce, on coverage-preserving LLM aggregation of e-commerce reviews (Industry Track).
- Our paper RobustMAD (a robustness benchmark for multimodal small language models in anomaly detection) was accepted to TMLR.
- Our paper Re:Form (on cutting human priors from RL-trained formal software verification) was accepted to TMLR.
- Our paper LiveCANNBench (a benchmark for AI coding on Ascend CANN) was accepted to Findings of ACL 2026.
- Received a Google Gemini Academic Program Award (US$10,000).
- Our paper DafnyComp (on benchmarking LLMs for compositional formal verification) was accepted to ICLR 2026.
2025
- Received the Rohde & Schwarz Award at the IEEE 6G Summit Singapore.
- Our paper LACP (a communication protocol for LLM agents) was accepted to AI4NextG @ NeurIPS 2025.
- Our paper WirelessMathBench (a benchmark for mathematical reasoning in wireless communications) was accepted to Findings of ACL 2025.
- Our workshop on Advancements for Intelligent Robotics in 4D Scenes at IROS 2025 was accepted.
- Our paper SIM-D2NN (on onboard terrain classification for remote sensing) was accepted to the ML4RS @ ICLR 2025.
- Our paper TransPathNet (on indoor pathloss prediction) was accepted to ICASSP 2025, ranked 4th in the Indoor Pathloss Challenge.
- Started my Ph.D. at NTU, supported by the NTU Research Scholarship.