Li Liu

Venues

Frequent coauthors

Papers

1. Boosting ASR Robustness via Test-Time Reinforcement Learning with Audio-Text Semantic Rewards
   AAAI 2026 ·

   Linghan Fang

   DBLP profile ↗ORCID search ↗
2. Cueing Without Gapping: Cuer-Independent Cued Speech Recognition Powered by Cross-Cuer Invariant Modeling
   AAAI 2026 ·

   Fengji Ma

   DBLP profile ↗ORCID search ↗
3. TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability
   AAAI 2026 ·

   Fengji Ma

   DBLP profile ↗ORCID search ↗
4. UniCUE: Unified Recognition and Generation Framework for Chinese Cued Speech Video-to-Speech Generation
   AAAI 2026 ·

   Jinting Wang

   DBLP profile ↗ORCID search ↗
5. Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks
   ICLR 2025 ·

   Danni Yuan

   DBLP profile ↗ORCID search ↗
6. AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation
   ACM MM 2025 ·

   Yan Rong

   DBLP profile ↗ORCID search ↗
7. BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model
   NeurIPS 2025 ·

   Weilin Lin

   DBLP profile ↗ORCID search ↗
8. Cued-Agent: A Collaborative Multi-Agent System for Automatic Cued Speech Recognition
   ACM MM 2025 ·

   Guanjie Huang

   DBLP profile ↗ORCID search ↗
9. Failure Cases Are Better Learned but Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Training
   ICCV 2025 ·

   Yanyun Wang

   DBLP profile ↗ORCID search ↗
10. Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
    AAAI 2025 ·

    Weilin Lin

    DBLP profile ↗ORCID search ↗
11. Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey
    EMNLP 2025 ·

    Tianxin Xie

    DBLP profile ↗ORCID search ↗
12. Bridge to Non-Barrier Communication: Gloss-Prompted Fine-Grained Cued Speech Gesture Generation with Diffusion Model
    IJCAI 2024 ·

    Wentao Lei

    DBLP profile ↗ORCID search ↗
13. Prior-free Balanced Replay: Uncertainty-guided Reservoir Sampling for Long-Tailed Continual Learning
    ACM MM 2024 ·

    Lei Liu

    DBLP profile ↗ORCID search ↗
14. Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
    NeurIPS 2024 ·

    Weilin Lin

    DBLP profile ↗ORCID search ↗
15. WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark
    NeurIPS 2024 ·

    Chunhui Zhang

    DBLP profile ↗ORCID search ↗