Tag
The paper introduces TopoSIGN, a topology-guided graph pre-training and prompt learning framework for signed graphs, which combines structural encoding and persistent homology to improve transfer learning in tasks like link prediction and node classification.
The paper introduces CoSPOT, an LLM-based framework for online time series forecasting that uses compositional spectral prompts to efficiently adapt to non-stationary data and unseen patterns.
The paper introduces TPGC, a dual-prior prompt initialization method for multi-task graph pre-training that combines task and structural priors to improve alignment and transferability, achieving superior performance in few-shot scenarios.
This study proposes an integrated framework using domain-specific LLMs for intelligent identification and repair of design defects in BIM, achieving 85% accuracy and 94% reasonable repair suggestions with effective hallucination control.
This paper investigates the interpretability of DAPF-based models for dementia detection, revealing that while DAPF achieves strong performance, its token-level explanations lack faithfulness.
The paper proposes a multimodal prompt-learning framework to handle missing modalities in electronic health records for robust clinical prediction in intensive care units, introducing four prompt types to capture dependencies and interactions.
The paper addresses Incomplete Multimodal Sentiment Analysis with Unseen Modality Combinations and proposes the ContrastiveMixedPromptLearning (CMPL) model, which uses label-guided contrastive learning and modality-combination prompts to enhance generalization, achieving over 5% accuracy improvement on benchmark datasets.
This paper presents a comprehensive survey of federated prompt learning (FPL), reviewing advances in integrating federated learning with large language models, discussing motivations, trade-offs, and future research directions.
Proposes a novel multilevel graph prompt learning framework for crystal property prediction that captures local chemical semantics and global structural symmetry via node-level and graph-level soft prompts, improving state-of-the-art GNN performance by 3%-15% and enabling cross-property knowledge transfer.
This paper presents Semantic Action RL, which uses reinforcement learning over Vision-Language-Action (VLA) prompts to enable robots to learn new tasks quickly in the real world.
This paper introduces Manana, a non-parametric prompt-learning framework that teaches LLMs to recommend anti-seizure medications and defer uncertain cases in underrepresented epilepsy care settings, improving accuracy on Ugandan cohorts and enabling selective prediction with high precision.
Tsinghua University NLP Lab open-sourced 269 projects on GitHub, covering large model training, knowledge graphs, Prompt learning, parameter fine-tuning, and more, including well-known projects such as OpenPrompt, OpenNRE, OpenKE, UltraChat, and OpenDelta. Suitable for AI researchers and application developers.
TTL introduces a test-time textual learning framework for OOD detection using pretrained vision-language models like CLIP, which dynamically learns OOD semantics from unlabeled test streams without external OOD labels. The method uses pseudo-labeled samples and an OOD knowledge purification strategy to improve detection robustness across diverse and evolving OOD distributions.