PPaperPicks

Tongliang Liu

85 papers at tracked venues · 81 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. GUIC: Certified Graph Unlearning with Individual Fairness Guarantees
  2. La La LiDAR: Large-Scale Layout Generation from LiDAR Data
  3. MedDCR: Learning to Design Agentic Workflows for Medical Coding
  4. Robust Learning from Noisily Labeled Long-Tailed Data via Fairness Regularizer
  5. Select Before Use: On the Importance of Reference Model Selection in Preference Alignment
  6. A Lens into Interpretable Transformer Mistakes via Semantic Dependency
  7. A Robust Method to Discover Causal or Anticausal Relation
  8. A Sample Efficient Conditional Independence Test in the Presence of Discretization
  9. AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
  10. Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation
  11. Can Dependencies Induced by LLM-Agent Workflows Be Trusted?
  12. Chain-of-Focus Prompting: Leveraging Sequential Visual Cues to Prompt Large Autoregressive Vision Models
  13. Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning
  14. DEEM: Diffusion models serve as the eyes of large language models for image perception
  15. Efficient and Trustworthy Causal Discovery with Latent Variables and Complex Relations
  16. Enhancing Sample Selection Against Label Noise by Cutting Mislabeled Easy Examples
  17. Epistemic Uncertainty for Generated Image Detection
  18. Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
  19. Flow: Modularized Agentic Workflow Automation
  20. From Debate to Equilibrium: Belief‑Driven Multi‑Agent LLM Reasoning via Bayesian Nash Equilibrium
  21. Generative Model Inversion Through the Lens of the Manifold Hypothesis
  22. Instance-dependent Early Stopping
  23. Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising
  24. LaVin-DiT: Large Vision Diffusion Transformer
  25. Label Distribution Learning with Biased Annotations Assisted by Multi-Label Learning
  26. Learning Graph Invariance by Harnessing Spuriosity
  27. MFT-VITON: High-Fidelity Virtual Try-On with Minimal Input via a Mask-Free Transformer-Diffusion Model
  28. MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation
  29. Noisy Test-Time Adaptation in Vision-Language Models
  30. OpenInsGaussian: Open-Vocabulary Instance Gaussian Segmentation with Context-Aware Cross-View Fusion
  31. Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection
  32. Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization
  33. RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Rank Correlation between Labels
  34. Ranked from Within: Ranking Large Multimodal Models Without Labels
  35. Recovery of Causal Graph Involving Latent Variables via Homologous Surrogates
  36. Revealing Multimodal Causality with Large Language Models
  37. Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
  38. Surrogate Prompt Learning: Towards Efficient and Diverse Prompt Learning for Vision-Language Models
  39. Toward Robust Non-Transferable Learning: A Survey and Benchmark
  40. Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
  41. Towards Out-of-Modal Generalization without Instance-level Modal Correspondence
  42. Understanding and Enhancing the Transferability of Jailbreaking Attacks
  43. When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need
  44. Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions
  45. Decomposed Prompt Decision Transformer for Efficient Unseen Task Generalization
  46. Discovery of the Hidden World with Large Language Models
  47. E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning
  48. ERASE: Error-Resilient Representation Learning on Graphs for Label Noise Tolerance
  49. Early Stopping Against Label Noise Without Validation Data
  50. Enhanced Motion-Text Alignment for Image-to-Video Transfer Learning
  51. Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data Augmentation
  52. Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
  53. Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection
  54. Exploring Channel-Aware Typical Features for Out-of-Distribution Detection
  55. FedImpro: Measuring and Improving Client Update in Federated Learning
  56. Federated Causal Discovery from Heterogeneous Data
  57. Few-Shot Adversarial Prompt Learning on Vision-Language Models
  58. IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
  59. Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Training
  60. Improving Non-Transferable Representation Learning by Harnessing Content and Style
  61. In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
  62. Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependency
  63. Learning the Latent Causal Structure for Modeling Label Noise
  64. MOKD: Cross-domain Finetuning for Few-shot Classification via Maximizing Optimized Kernel Dependence
  65. Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning
  66. Mind the Gap Between Prototypes and Images in Cross-domain Finetuning
  67. Mitigating Label Noise on Graphs via Topological Sample Selection
  68. Negative Label Guided OOD Detection with Pretrained Vision-Language Models
  69. Neural Auto-designer for Enhanced Quantum Kernels
  70. NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation
  71. NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
  72. On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
  73. One-Shot Learning as Instruction Data Prospector for Large Language Models
  74. Optimal Kernel Choice for Score Function-based Causal Discovery
  75. Out-of-Distribution Detection with Negative Prompts
  76. Pseudo-Private Data Guided Model Inversion Attacks
  77. Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints
  78. Robust Training of Federated Models with Extremely Label Deficiency
  79. Task-aware Orthogonal Sparse Network for Exploring Shared Knowledge in Continual Learning
  80. Towards Realistic Model Selection for Semi-supervised Learning
  81. Training A Secure Model Against Data-Free Model Extraction
  82. Unraveling the Impact of Heterophilic Structures on Graph Positive-Unlabeled Learning
  83. Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
  84. What If the Input is Expanded in OOD Detection?
  85. Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning