Tongliang Liu

26

Papers

75

Total Citations

Papers (26)

LaVin-DiT: Large Vision Diffusion Transformer

Towards Effective Evaluations and Comparisons for LLM Unlearning Methods

Federated Causal Discovery from Heterogeneous Data

Neural Auto-designer for Enhanced Quantum Kernels

Robust Training of Federated Models with Extremely Label Deficiency

Learning Graph Invariance by Harnessing Spuriosity

Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions

Towards Out-of-Modal Generalization without Instance-level Modal Correspondence

Efficient and Trustworthy Causal Discovery with Latent Variables and Complex Relations

Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning

Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning

Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection

Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising

Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning

Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning

Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency

MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence

Optimal Kernel Choice for Score Function-based Causal Discovery

Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning

Mitigating Label Noise on Graphs via Topological Sample Selection

Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints

Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training

Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection

E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning

Towards Realistic Model Selection for Semi-supervised Learning

Exploring Channel-Aware Typical Features for Out-of-Distribution Detection