Tongliang Liu
- AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
- Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation
- Can Dependencies Induced by LLM-Agent Workflows Be Trusted?
- Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
- Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
- Epistemic Uncertainty for Generated Image Detection
- Generative Model Inversion Through the Lens of the Manifold Hypothesis
- MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation
- Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization
- RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels
- Revealing Multimodal Causality with Large Language Models
- Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes