Zihao Li

Venues

Frequent coauthors

Papers

1. Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching
   ACL 2026 ·

   Bo Lv

   DBLP profile ↗ORCID search ↗
2. CAST: Achieving Stable LLM-based Text Analysis for Data Analytics
   ACL 2026 ·

   Jinxiang Xie

   DBLP profile ↗ORCID search ↗
3. CyPortQA: Benchmarking Multimodal Large Language Models for Cyclone Preparedness in Port Operation
   AAAI 2026 ·

   Chenchen Kuai

   DBLP profile ↗ORCID search ↗
4. Data-Centric Continual Pre-training for 500+ Languages: A New Bilingual Translation Corpus and Multilingual Models
   ACL 2026 ·

   Shaoxiong Ji

   DBLP profile ↗ORCID search ↗
5. Test-Time Scaling of Reasoning Models for Machine Translation
   EACL 2026 · Zihao Li
6. AIM 2025 Challenge on High FPS Motion Deblurring: Methods and Results
   ICCV 2025 ·

   George Ciubotariu

   DBLP profile ↗ORCID search ↗
7. AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Results
   ICCV 2025 ·

   Chao Wang

   DBLP profile ↗ORCID search ↗
8. Boosting Inverse Tone Mapping via Diffusion Regularization
   ICCV 2025 ·

   Xin Lu

   DBLP profile ↗ORCID search ↗
9. Contrastive Reinforcement Learning for Robust Anomaly Detection with Limited Labels
   ICDM 2025 · Zihao Li
10. Efficient High FPS Non-Uniform Motion Deblurring via Progressive Learning
    ICCV 2025 ·

    Xin Lu

    DBLP profile ↗ORCID search ↗
11. Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models
    EMNLP 2025 · Zihao Li
12. GlotEval: A Test Suite for Massively Multilingual Evaluation of Large Language Models
    EMNLP 2025 ·

    Hengyu Luo

    DBLP profile ↗ORCID search ↗
13. Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages
    AAAI 2025 · Zihao Li
14. Lip Geometry-Constrained Smooth Sliding Path Planning for Robotic Negative Pressure Therapy on Extremities
    IROS 2025 · Zihao Li
15. MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
    ICML 2025 ·

    Kaixuan Huang

    DBLP profile ↗ORCID search ↗
16. Model Unlearning via Sparse Autoencoder Subspace Guided Projections
    EMNLP 2025 ·

    Xu Wang

    DBLP profile ↗ORCID search ↗
17. Scaling Low-Resource MT via Synthetic Data Generation with LLMs
    EMNLP 2025 ·

    Ona de Gibert

    DBLP profile ↗ORCID search ↗
18. A Comparison of Language Modeling and Translation as Multilingual Pretraining Objectives
    EMNLP 2024 · Zihao Li
19. Efficient Path Planning for Modular Reconfigurable Robots
    IROS 2024 ·

    Matthias Mayer

    DBLP profile ↗ORCID search ↗
20. Global Convergence in Training Large-Scale Transformers
    NeurIPS 2024 ·

    Cheng Gao

    DBLP profile ↗ORCID search ↗
21. Meta-Reinforcement Learning Robust to Distributional Shift Via Performing Lifelong In-Context Learning
    ICML 2024 ·

    Tengye Xu

    DBLP profile ↗ORCID search ↗
22. One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
    NeurIPS 2024 · Zihao Li
23. Policy Evaluation for Reinforcement Learning from Human Feedback: A Sample Complexity Analysis
    AISTATS 2024 · Zihao Li
24. ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation
    CVPR 2024 ·

    Yipin Guo

    DBLP profile ↗ORCID search ↗
25. Theoretical insights for diffusion guidance: A case study for Gaussian mixture models
    ICML 2024 ·

    Yuchen Wu

    DBLP profile ↗ORCID search ↗