Lune

Profiles2023-2026ORCID 0000-0001-9158-9401

Haizhou Li

Shenzhen Loop Area Institute

13Papers
10Last author
23Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers13

  1. EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language ModelsAuthor 9 of 9ICLR 2026 · 13 citations
  2. AdapAction: Adaptive Target Action Backdoor Attack against GUI AgentsAuthor 3 of 4CVPR 2026
  3. Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMsAuthor 12 of 13ACL 2026
  4. UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-ExpertsAuthor 14 of 15ACL 2026
  5. Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement MeasurementAuthor 5 of 5WWW 2025 · 20 citations
  6. Multi-modal and Multi-scale Spatial Environment Understanding for Immersive Visual Text-to-SpeechAuthor 4 of 4AAAI 2025 · 8 citations
  7. UniTalker: Conversational Speech-Visual SynthesisAuthor 3 of 3ACM MM 2025 · 2 citations
  8. Chain-Talker: Chain Understanding and Rendering for Empathetic Conversational Speech SynthesisAuthor 5 of 5ACL Findings 2025 · 1 citation
  9. Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context ModelingAuthor 5 of 5AAAI 2024 · 31 citations
  10. Generative Expressive Conversational Speech SynthesisAuthor 3 of 3ACM MM 2024 · 15 citations
  11. Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language ModelsAuthor 7 of 7EMNLP Findings 2024 · 2 citations
  12. Unveiling the Achilles' Heel of NLG Evaluators: A Unified Adversarial Framework Driven by Large Language ModelsAuthor 6 of 6ACL Findings 2024
  13. Disentangling Voice and Content with Self-Supervision for Speaker RecognitionAuthor 4 of 4NeurIPS 2023 · 53 citations
Dusk over the sea between two cliffs drawn in fine vertical lines