Gerard De Melo
95 publications
25 venues
H Index 34
Affiliation
University of Potsdam, GermanyHasso Plattner Institute, Potsdam, Germany
Rutgers, The State University of New Jersey, New Brunswick, USA
Tsinghua University
Links
DBLPGoogle Scholar
Twitter- http://gerard.demelo.org/
- http://iiis.tsinghua.edu.cn/demelo/
- https://dl.acm.org/profile/81447595290
- https://mathgenealogy.org/id.php?id=164997
- https://orcid.org/0000-0002-2930-2059
- https://www.wikidata.org/entity/Q21057281
- https://www.researcherid.com/rid/P-7886-2014
- https://d-nb.info/gnd/141159790
- https://d-nb.info/gnd/1261074017
- https://ieeexplore.ieee.org/author/37882471300
- https://zbmath.org/authors/?q=ai:de-melo.gerard
| Name | Venue | Year | citations |
|---|---|---|---|
MINGLE: VLMs for Semantically Complex Region Detection in Urban Scenes.
|
AAAI | 2026 | 0 |
| Hierarchical Divide-and-Conquer for Fine-Grained Alignment in LLM-Based Medical Evaluation.
|
AAAI | 2025 | 3 |
| AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation.
|
ACL | 2025 | 1 |
| SLlama: Parameter-Efficient Language Model Architecture for Enhanced Linguistic Competence Under Strict Data Constraints.
|
EMNLP | 2025 | 0 |
| NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning.
|
AAAI | 2025 | 0 |
| Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision.
|
ICML | 2025 | 0 |
| Mitigate the Gap: Improving Cross-Modal Alignment in CLIP.
|
ICLR | 2025 | 0 |
| ACE-M³: Automatic Capability Evaluator for Multimodal Medical Models.
|
COLING | 2025 | 0 |
| I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token.
|
NIPS/NeurIPS | 2024 | 0 |
| NextLevelBERT: Masked Language Modeling with Higher-Level Representations for Long Documents.
|
ACL | 2024 | 6 |
| CliMedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models in Clinical Scenarios.
|
EMNLP | 2024 | 12 |
| MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models.
|
AAAI | 2024 | 0 |
| Fifth Knowledge-aware and Conversational Recommender Systems Workshop (KaRS).
|
RecSys | 2023 | 3 |
| Disentangled CVAEs with Contrastive Learning for Explainable Recommendation.
|
AAAI | 2023 | 6 |
| Robust NLP for Finance (RobustFin).
|
KDD | 2023 | 1 |
| A Disentangled-Attention Based Framework with Persona-Aware Prompt Learning for Dialogue Generation.
|
AAAI | 2023 | 8 |
| Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning.
|
IJCAI | 2023 | 1 |
| FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models.
|
EMNLP | 2023 | 65 |
| Multi-Modal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision-Language Models.
|
EACL | 2023 | 0 |
| Frozen CLIP Models are Efficient Video Learners.
|
ECCV | 2022 | 267 |
| Fourth Knowledge-aware and Conversational Recommender Systems Workshop (KaRS).
|
RecSys | 2022 | 11 |
| Temporal Event Reasoning Using Multi-source Auxiliary Learning Objectives.
|
ECIR | 2022 | 1 |
| Path Language Modeling over Knowledge Graphsfor Explainable Recommendation.
|
WWW | 2022 | 89 |
| Curriculum Prompt Learning with Self-Training for Abstractive Dialogue Summarization.
|
EMNLP | 2022 | 9 |
| Improving Personalized Explanation Generation through Visualization.
|
ACL | 2022 | 38 |
| Art Creation with Multi-Conditional StyleGANs.
|
IJCAI | 2022 | 8 |
| Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation.
|
EMNLP | 2022 | 17 |
| D-HYPR: Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning.
|
CIKM | 2022 | 0 |
| Purely Attention Based Local Feature Integration for Video Classification.
|
TPAMI | 2022 | 0 |
| Context-Aware Interaction Network for Question Matching.
|
EMNLP | 2021 | 16 |
| Popcorn: Human-in-the-loop Popularity Debiasing in Conversational Recommender Systems.
|
CIKM | 2021 | 42 |
| EXACTA: Explainable Column Annotation.
|
KDD | 2021 | 10 |
| HOOPS: Human-in-the-Loop Graph Reasoning for Conversational Recommendation.
|
SIGIR | 2021 | 39 |
| Guilt by Association: Emotion Intensities in Lexical Representations.
|
EMNLP | 2021 | 2 |
| TIME: Text and Image Mutual-Translation Adversarial Networks.
|
AAAI | 2021 | 0 |
| Long Short-Term Sample Distillation.
|
AAAI | 2020 | 7 |
| Illustrate Your Story: Enriching Text with Images.
|
WSDM | 2020 | 7 |
| Explainable Link Prediction for Emerging Entities in Knowledge Graphs.
|
ISWC | 2020 | 39 |
| HID: Hierarchical Multiscale Representation Learning for Information Diffusion.
|
IJCAI | 2020 | 25 |
| CAFE: Coarse-to-Fine Neural Symbolic Reasoning for Explainable Recommendation.
|
CIKM | 2020 | 101 |
| Incorporating Pragmatic Reasoning Communication into Emergent Language.
|
NIPS/NeurIPS | 2020 | 25 |
| Cross-Lingual Emotion Lexicon Induction using Representation Alignment in Low-Resource Settings.
|
COLING | 2020 | 6 |
| ABSent: Cross-Lingual Sentence Representation Mapping with Bidirectional GANs.
|
AAAI | 2020 | 20 |
| Domain-Specific Sentiment Lexicons Induced from Labeled Documents.
|
COLING | 2020 | 13 |
| Leveraging Adversarial Training in Self-Learning for Cross-Lingual Text Classification.
|
SIGIR | 2020 | 33 |
| Fairness-Aware Explainable Recommendation over Knowledge Graphs.
|
SIGIR | 2020 | 234 |
| Sentence Analogies: Linguistic Regularities in Sentence Embeddings.
|
COLING | 2020 | 35 |
| What Sparks Joy: The AffectVec Emotion Database.
|
WWW | 2020 | 19 |
| Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation.
|
AAAI | 2020 | 0 |
| OOGAN: Disentangling GAN with One-Hot Sampling and Orthogonal Regularization.
|
AAAI | 2020 | 0 |
| SCALOR: Generative World Models with Scalable Object Representations.
|
ICLR | 2020 | 0 |
| Data Augmentation for Multiclass Utterance Classification - A Systematic Study.
|
COLING | 2020 | 0 |
| EmoTag1200: Understanding the Association between Emojis and Emotions.
|
EMNLP | 2020 | 0 |
| Reinforcement Knowledge Graph Reasoning for Explainable Recommendation.
|
SIGIR | 2019 | 537 |
| Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation.
|
ACL | 2019 | 32 |
| Be Concise and Precise: Synthesizing Open-Domain Entity Descriptions from Facts.
|
WWW | 2019 | 4 |
| Paralinguistic recommendations for affective word clouds.
|
IUI | 2019 | 11 |
| Cross-Lingual Propagation for Deep Sentiment Analysis.
|
AAAI | 2018 | 39 |
| Visualizing Multi-document Semantics via Open Domain Information Extraction.
|
ECML/PKDD | 2018 | 6 |
| Generating Fine-Grained Open Vocabulary Entity Type Descriptions.
|
ACL | 2018 | 16 |
| A Helping Hand: Transfer Learning for Deep Sentiment Analysis.
|
ACL | 2018 | 47 |
| Multimodal Keyless Attention Fusion for Video Classification.
|
AAAI | 2018 | 139 |
| Link Prediction via Subgraph Embedding-Based Convex Matrix Completion.
|
AAAI | 2018 | 35 |
| Exploring Semantic Properties of Sentence Embeddings.
|
ACL | 2018 | 61 |
| Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval.
|
WSDM | 2018 | 0 |
| Attention Clusters: Purely Attention Based Local Feature Integration for Video Classification.
|
CVPR | 2018 | 0 |
| Link prediction by exploiting network formation games in exchangeable graphs.
|
IJCNN | 2017 | 8 |
| PACRR: A Position-Aware Neural IR Model for Relevance Matching.
|
EMNLP | 2017 | 162 |
| Multiple-Weight Recurrent Neural Networks.
|
IJCAI | 2017 | 5 |
| Should Algorithms for Random SAT and Max-SAT Be Different?
|
AAAI | 2017 | 0 |
| WebBrain: Joint Neural Learning of Large-Scale Commonsense Knowledge.
|
ISWC | 2016 | 10 |
| Morphological Segmentation with Window LSTM Neural Networks.
|
AAAI | 2016 | 52 |
| Concepts Not Alone: Exploring Pairwise Relationships for Zero-Shot Video Activity Recognition.
|
AAAI | 2016 | 86 |
| Heuristics for Connecting Heterogeneous Knowledge via FrameBase.
|
ESWC | 2016 | 9 |
| Klint: Assisting Integration of Heterogeneous Knowledge.
|
IJCAI | 2016 | 2 |
| Relation Classification via Multi-Level Attention CNNs.
|
ACL | 2016 | 510 |
| ShapeLearner: Towards Shape-Based Visual Knowledge Harvesting.
|
ECAI | 2016 | 2 |
| PEAK: Pyramid Evaluation via Automated Knowledge Extraction.
|
AAAI | 2016 | 49 |
| Perceptually Grounded Selectional Preferences.
|
ACL | 2015 | 13 |
| DynaDiffuse: A Dynamic Diffusion Model for Continuous Time Constrained Influence Maximization.
|
AAAI | 2015 | 32 |
| Sentiment-Aspect Extraction based on Restricted Boltzmann Machines.
|
ACL | 2015 | 62 |
| FrameBase: Representing N-Ary Relations Using Semantic Frames.
|
ESWC | 2015 | 61 |
| Knowlywood: Mining Activity Knowledge From Hollywood Narratives.
|
CIKM | 2015 | 54 |
| Structured Learning for Taxonomy Induction with Belief Propagation.
|
ACL | 2014 | 69 |
| Acquiring Comparative Commonsense Knowledge from the Web.
|
AAAI | 2014 | 61 |
| WebChild: harvesting and organizing commonsense knowledge from the web.
|
WSDM | 2014 | 167 |
| PIKM 2014: The 7th ACM Workshop for Ph.D. Students in Information and Knowledge Management.
|
CIKM | 2014 | 0 |
| Searching the Web of Data.
|
ECIR | 2013 | 9 |
| Not Quite the Same: Identity Constraints for the Web of Linked Data.
|
AAAI | 2013 | 54 |
| LINDA: distributed web-of-data-scale entity matching.
|
CIKM | 2012 | 98 |
| Deriving a Web-Scale Common Sense Fact Database.
|
AAAI | 2011 | 41 |
| MENTA: inducing multilingual taxonomies from wikipedia.
|
CIKM | 2010 | 108 |
| Untangling the Cross-Lingual Link Structure of Wikipedia.
|
ACL | 2010 | 51 |
| Towards a universal wordnet by learning from combined evidence.
|
CIKM | 2009 | 153 |
| Multilingual Text Classification Using Ontologies.
|
ECIR | 2007 | 35 |