Lune

Profiles2020-2026

Tongliang Liu

The University of Sydney

112Papers
55Last author
166Unique co-authors
0First author
0Solo

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

Recent papers112

  1. When Safety Collides: Resolving Multi-Category Harmful Conflicts in Text-to-Image Diffusion via Adaptive Safety GuidanceAuthor 6 of 6CVPR 2026 · 14 citations
  2. FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEctionAuthor 7 of 7CVPR 2026 · 13 citations
  3. Mobile-VTON: High-Fidelity On-Device Virtual Try-OnAuthor 7 of 8CVPR 2026 · 4 citations
  4. Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein DistanceAuthor 6 of 6CVPR 2026 · 2 citations
  5. MedDCR: Learning to Design Agentic Workflows for Medical CodingAuthor 6 of 8ACL Findings 2026 · 1 citation
  6. Beyond Optimal Transport: Model-Aligned Coupling for Flow MatchingAuthor 4 of 4CVPR Findings 2026
  7. Causal Effect Identifiability in the Presence of Latent Confounders Without Auxiliary VariablesAuthor 4 of 4ICML 2026
  8. Select Before Use: On the Importance of Reference Model Selection in Preference AlignmentAuthor 6 of 6ACL 2026
  9. RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between LabelsAuthor 9 of 10NeurIPS 2025 · 18 citations
  10. Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video GenerationAuthor 6 of 6NeurIPS 2025 · 6 citations
  11. Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM ReasoningAuthor 5 of 6NeurIPS 2025 · 5 citations
  12. Revealing Multimodal Causality with Large Language ModelsAuthor 5 of 8NeurIPS 2025 · 5 citations
  13. Can Dependencies Induced by LLM-Agent Workflows Be Trusted?Author 6 of 6NeurIPS 2025 · 4 citations
  14. Generative Model Inversion Through the Lens of the Manifold HypothesisAuthor 4 of 6NeurIPS 2025 · 3 citations
  15. A Lens into Interpretable Transformer Mistakes via Semantic DependencyAuthor 4 of 4ICML 2025
  16. A Robust Method to Discover Causal or Anticausal RelationAuthor 6 of 6ICLR 2025
  17. Chain-of-Focus Prompting: Leveraging Sequential Visual Cues to Prompt Large Autoregressive Vision ModelsAuthor 7 of 7ICLR 2025
  18. Efficient and Trustworthy Causal Discovery with Latent Variables and Complex RelationsAuthor 2 of 2ICLR 2025
  19. Flow: Modularized Agentic Workflow AutomationAuthor 7 of 7ICLR 2025
  20. Jailbreaking the Non-Transferable Barrier via Test-Time Data DisguisingAuthor 5 of 5CVPR 2025
  21. LaVin-DiT: Large Vision Diffusion TransformerAuthor 7 of 7CVPR 2025
  22. Learning Graph Invariance by Harnessing SpuriosityAuthor 4 of 6ICLR 2025
  23. Pruning Spurious Subgraphs for Graph Out-of-Distribution GeneralizationAuthor 4 of 7NeurIPS 2025
  24. Ranked from Within: Ranking Large Multimodal Models Without LabelsAuthor 7 of 7ICML 2025
  25. Recovery of Causal Graph Involving Latent Variables via Homologous SurrogatesAuthor 3 of 3ICLR 2025
  26. Towards Out-of-Modal Generalization without Instance-level Modal CorrespondenceAuthor 5 of 5ICLR 2025
  27. Understanding and Enhancing the Transferability of Jailbreaking AttacksAuthor 4 of 4ICLR 2025
  28. When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You NeedAuthor 6 of 6ICML 2025
  29. Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?Author 7 of 8NeurIPS 2024 · 124 citations
  30. Negative Label Guided OOD Detection with Pretrained Vision-Language ModelsAuthor 5 of 7ICLR 2024 · 73 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines