Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks281 from public data
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning582
This paper proposes a novel method called reasoning on graphs (RoG) that synergizes LLMs with KGs to enable faithful and interpretable reasoning and presents a planning-retrieval-reasoning framework, where RoG first generates relation paths grounded by KGs as faithful plans.
- XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages570
This work presents XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics, and is the largest abstractive summarization dataset in terms of the number of samples collected from a single source and thenumber of languages covered.
- VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks231
VLABench is an open-source benchmark for evaluating universal LCM task learning and provides high-quality training data collected via an automated framework incorporating heuristic skills and prior information to support the downstream finetuning.
- Multivariate Time Series Forecasting With Dynamic Graph Neural ODEs206
A continuous model to forecast multivariate time series forecasting is proposed, designed and solved to complement missing graph topologies and unify both spatial and temporal message passing, allowing deeper graph propagation and fine-grained temporal information aggregation to characterize stable and precise latent spatial-temporal dynamics.
- ANEMONE200
A novel graph anomaly detection framework, namely ANEMONE, to simultaneously identify the anomalies in multiple graph scales and employs a statistical anomaly estimator to evaluate the abnormality of each node according to the degree of agreement from multiple perspectives.
- Continual Learning for Large Language Models: A Survey198
This paper surveys recent works on continual learning for LLMs and catalogs continue learning techniques in a novel multi-staged categorization scheme, involving continual pretraining, instruction tuning, and alignment.
- Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning194
A novel self-supervised approach to learn node representations by enhancing Siamese self-distillation with multi-scale contrastive learning that not only achieves new state-of-the-art results but also surpasses some semi- supervised counterparts by large margins.
- Measuring design complexity of semantic web ontologies134
This paper proposes a suite of ontology metrics, at both the ontology-level and class-level, to measure the design complexity of ontologies, and points out possible applications of the proposed metrics to ontology quality control.
- Verifying feature models using OWL133
A general OWL debugger has been developed to tackle the disadvantage of lacking debugging aids for the current OWL reasoner and to complement the verification approach to modeling and verifying feature diagrams using Semantic Web OWL ontologies.
- Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs131
A new approach, Neural Temporal Walks ( NeurTWs), for representation learning on continuous-time dynamic graphs by considering not only time constraints but also structural and tree traversal properties, demonstrates overwhelming superiority under both transductive and inductive settings on six real-world datasets.
- Two decades of Web application testing—A survey of recent advances90
A broad survey of recent Web testing advances is presented and it is discussed their goals, targets, techniques employed, inputs/outputs and stopping criteria.
- Curriculum-Meta Learning for Order-Robust Continual Relation Extraction89
A novel curriculum-meta learning method is proposed to quickly adapt model parameters to a new task and to reduce interference of previously seen tasks on the current task to tackle catastrophic forgetting and order-sensitivity in continual relation extraction.
- Difficulty-Controllable Multi-hop Question Generation from Knowledge Graphs86
This work presents an end-to-end neural network-based method for automatic generation of complex multi-hop questions over knowledge graphs, and incorporates difficulty estimation based on named entity popularity, and makes use of this estimation to generate difficulty-controllable questions.
- An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models76
A novel VQA dataset is constructed, Spatial-MM, to comprehensively study large Multimodal Models’ spatial understanding and reasoning capabilities and reveals that LMMs are much stronger at basic object detection than complex spatial reasoning.
- Predicting Reasoning Performance Using Ontology Metrics74
A systematic study to tackle hardness of reasoning about individual ontologies using machine learning techniques, covering over 350 real-world ontologies and four state-of-the-art, widely-used OWL 2 reasoners and identifying a number of metrics that can be used to effectively predict reasoning performance.
- A semantic web approach to feature modeling and verification74
A Semantic Web environment for modeling and verifying feature diagrams using ontologies using OWL DL (a decidable dialect of OWL) to precisely capture the relationships among features in feature diagrams and configurations.
- Structured Two-Stream Attention Network for Video Question Answering73
This paper proposes a Structured Two-stream Attention network, namely STA, to answer a free-form or open-ended natural language question about the content of a given video to infer rich longrange temporal structures in videos using the authors' structured segment component and encode text features.
- Multimodal feature-wise co-attention method for visual question answering66
By introducing MulFA modules, this paper constructs an effective union feature-wise and spatial co-attention network (UFSCAN) model for VQA, and evaluation on two large-scale V QA datasets shows that UFSCAN achieves performance competitive with state-of-the-art models.
- Generating question titles for Stack Overflow from mined code snippets66
An approach to assist developers in writing high-quality questions by automatically generating question titles for a code snippet using a deep sequence-to-sequence learning approach that significantly outperforms several state-of-the-art baselines in both automatic and human evaluation.
- MMGRec: Multimodal Generative Recommendation with Transformer Model63
A relation-aware self-attention mechanism is devised for the Transformer to handle non-sequential interaction sequences, which explores the element pairwise relation to replace absolute positional encoding.
- CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs62
A multistage data sampling algorithm is proposed to effectively train a cross-lingual summarization model capable of summarizing an article in any target language and LaSE, an embedding-based metric for automatically evaluating model-generated summaries is introduced.
- Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion60
A normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC), which unify normalizing flows and neural processes to model a complex distribution of KG completion functions and introduces an attentive relation path-based graph neural network to capture path information in KGs.
- Combining cross-modal knowledge transfer and semi-supervised learning for speech emotion recognition53
This work proposes a new architecture that combines cross-modal knowledge transfer from visual to audio modality into the authors' semi-supervised learning method with consistency regularization, and proposes two fusion algorithms, i.e. weighted fusion and consistent & random.
- Automating Reading Comprehension by Generating Question and Answer Pairs50
A novel two-stage process to generate question-answer pairs from the text using sequence to sequence models and global attention and answer encoding for generating the question most relevant to the answer is presented.
- A framework for automatic question generation from text using deep reinforcement learning.48
This paper presents a novel deep reinforcement learning based framework for automatic question generation that significantly outperforms state-of-the-art systems on the widely-used SQuAD benchmark in both automatic and human evaluation.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.