Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks78 from public data
- TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Bases118
A new KBQA model, TIARA, is presented, which addresses issues by applying multi-grained retrieval to help the PLM focus on the most relevant KB context, viz., entities, exemplary logical forms, and schema items.
- GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition101
A simple but effective CNN-based network for NER, i.e., gated relation network (GRN), which is more capable than common CNNs in capturing long-term context and can achieve state-of-the-art performance with or without external knowledge.
- Caiipa100
Caiipa is a cloud service for testing apps over an expanded mobile context space in a scalable way that incorporates key techniques to make app testing more tractable, including a context test space prioritizer to quickly discover failure scenarios for each app.
- INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge92
This work constructs an evaluation suite of 197,243 QA pairs from local exam sources to measure the capabilities of multilingual LLMs in a variety of regional contexts and develops a comprehensive knowledge- and reasoning-centric benchmark that evaluates multilingual LLMs for performance in the actual language environments where they would be deployed.
- SIFT87
This work presents SIFT, a safety-centric programming platform for connected devices in IoT environments, and demonstrates the power of SIFT and how it leads to more robust and reliable IoT apps.
- Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language77
A teacher-student learning method, where NER models in the source languages are used as teachers to train a student model on unlabeled data in the target language, which outperforms existing state-of-the-art methods for both single-source and multi-source cross-lingual NER.
- Enhanced Meta-Learning for Cross-Lingual Named Entity Recognition with Minimal Resources73
This paper presents a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and proposes to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities.
- 68
- Systematically Debugging IoT Control System Correctness for Building Automation61
This paper presents the experience in running a building automation service based on the Salus framework, and demonstrates the usefulness of Salus in systematically debugging the correctness of IoT control systems for building automation.
- UniTrans : Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data53
This paper proposes a novel approach termed UniTrans to Unify both model and data Transfer for cross-lingual NER, and furthermore, leverage the available information from unlabeled target-language data via enhanced knowledge distillation.
- 45
- Cradle: Empowering Foundation Agents Towards General Computer Control43
This work proposes the General Computer Control (GCC) setting: building foundation agents that can master any computer task by taking only screen images of the computer as input, and producing keyboard and mouse operations as output, similar to human-computer interaction.
- AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER42
An adversarial learning framework in which an encoder learns entity domain knowledge from labeled source-language data and better shared features are captured via adversarial training - where a discriminator selects less language-dependent target- language data via similarity to the source language.
- 34
- A Survey on Game Playing Agents and Large Models: Methods, Applications, and Challenges33
This paper seeks to systematically review the existing architectures of LM-based Agents (LMAs) for games and summarize their commonalities, challenges, and any other insights, to assist researchers in gaining a clear understanding of the field and to generate more interest in this highly impactful research direction.
- 29
- LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection21
A unified model to detect anomalies from objects belonging to multiple classes when only normal data is accessible is developed, and the proposed LafitE, \ie, Latent Diffusion Model with Feature Editing, outperforms state-of-art methods by a significant margin in terms of average AUROC.
- GenDec: A robust generative Question-decomposition method for Multi-hop reasoning19
A GenDec method (GenDec) is proposed from the perspective of explainable QA by generating independent and complete sub-questions based on incorporating additional extracted evidence for enhancing LLMs' reasoning ability in RAG.
- 18
- Exploring Word Representations on Time Expression Recognition15
Simple neural architectures built on top of pre-trained word representations perform competitively and efficiently on time expression recognition and several design choices focusing on the need of contextualization and the training resource requirements are explored.
- 14
- MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents13
A novel method, MLLM As ReTriever (MART), is proposed, which enhances the performance of embodied agents by utilizing interaction data to fine-tune an MLLM retriever based on preference learning, such that the retriever fully considers the effectiveness of trajectories and prioritizes them for unseen tasks.
- 13
- Contextual Fuzzing: Automated Mobile App Testing Under Dynamic Device and Environment Conditions12
Context Virtualizer (ConVirt), a cloud-based testing service that provides a large set of realistic mobile contextual parameters to developers with emulators and enables scalable mobile context exploration with app similarity networks, is proposed.
- ContextPlayer: learning contextual music preferences for situational recommendations12
This case study presents a system for collecting context and usage data from mobile devices, but targeted at recommending music via unsupervised learning of user profiles and relevant situations, based on an international user trial.
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 2026-10-12. 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.