Xintong Sun — accepted AI-conference papers

2025

Earley-Driven Dynamic Pruning for Efficient Structured Decoding

Xintong Sun, Chi Wei, Minghao Tian, Shiwen Ni

ICML 2025poster

Large Language Models (LLMs) have shown remarkable capabilities, yet ensuring their outputs conform to strict structural or grammatical constraints remains challenging, which is critical in function calls and domain-specific language (DSL) generation. Constrained decoding with context-free grammar i…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem

Hongyi Liu, Shaochen Zhong, Xintong Sun, Minghao Tian, Mohsen Hariri, Zirui Liu +9

EMNLP 2025

Backdoor attacks are powerful and effective, but distributing LLMs without a proven track record like ‘meta-llama‘ or ‘qwen‘ rarely gains community traction. We identify LoRA sharing as a unique scenario where users are more willing to try unendorsed assets, since such shared LoRAs allow them to enj

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗