Xiuyu Li

发表论文 9 篇 · 总被引 327 次 · h-index 5

代表论文

• RouterBench: A Benchmark for Multi-LLM Routing System (2024 · arXiv.org · 被引 215)
• S*: Test Time Scaling for Code Generation (2025 · Conference on Empirical Methods in Natural Language Processing · 被引 104)
• STORM: Token-Efficient Long Video Understanding for Multimodal LLMs (2025 · 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · 被引 47)
• Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning (2026 · arXiv.org · 被引 22)
• A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models (2024 · 被引 11)
• Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Services (2026 · arXiv.org · 被引 2)