Di Wu

Learning Dynamics as Feedback: An Adaptive Entropy Flow Dynamics Framework for Long-tailed Human Action Recognition AAAI 2026 SIAM: Towards Generalizable Articulated Object Modeling via Single Robot-Object Interaction AAAI 2026 Rethinking Crystal Symmetry Prediction: A Decoupled Perspective AAAI 2026 Rethinking Multimodal Point Cloud Completion: A Completion-by-Correction Perspective AAAI 2026 Cross-Modal Unlearning via Influential Neuron Path Editing in Multimodal Large Language Models AAAI 2026 Introducing Visual Scenes and Reasoning: A More Realistic Benchmark for Spoken Language Understanding AAAI 2026 Open-Domain Safety Policy Construction EACL 2026 What Does Infect Mean to Cardio? Investigating the Role of Clinical Specialty Data in Medical LLMs EACL 2026 VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval ACL 2026 On-policy Reinforcement Fine-tuning with Offline reward for Multi-step Embodied Planning ACL 2026 PAGPL: Privacy-Aware Graph Prompt Learning Scheme via Adaptive Perturbation-Estimated Topology Recovery AAAI 2026 Label Effects: Shared Heuristic Reliance in Trust Assessment by Humans and LLM-as-a-Judge ACL 2026 Cost-Aware Optimal Pairwise Pure Exploration AISTATS 2025 MXMap: A Multivariate Cross Mapping Framework for Causal Discovery in Dynamical Systems CLEAR 2025 ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling AAAI 2025 Sampling Innovation-Based Adaptive Compressive Sensing CVPR 2025 Fully-Scalable Massively Parallel Algorithm for k-center with Outliers AAAI 2025 RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation RSS 2025 How to Learn in a Noisy World? Self-Correcting the Real-World Data Noise in Machine Translation NAACL 2025 BRIEF: Bridging Retrieval and Inference for Multi-hop Reasoning via Compression NAACL 2025 Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review IJCAI 2025 DyMAS-Net: Dynamic Multi-Scale Adaptive Sampling Network for Efficient Medical Image Segmentation MICCAI 2025 A Novel Sparse Active Online Learning Framework for Fast and Accurate Streaming Anomaly Detection Over Data Streams IJCAI 2025 Towards Homogeneous Lexical Tone Decoding from Heterogeneous Intracranial Recordings ICLR 2025 LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory ICLR 2025 Can LLMs Really Learn to Translate a Low-Resource Language from One Grammar Book? ICLR 2025 Know-MRI: A Knowledge Mechanisms Revealer&Interpreter for Large Language Models ACL 2025 Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models ACL 2025 Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translation EMNLP 2025 KMatrix-2: A Comprehensive Heterogeneous Knowledge Collaborative Enhancement Toolkit for Large Language Model EMNLP 2025 UvA-MT’s Participation in the WMT25 General Translation Shared Task EMNLP 2025 UvA-MT at WMT25 Evaluation Task: LLM Uncertainty as a Proxy for Translation Quality EMNLP 2025 INT: Establishing Information Transfer for Multilingual Intent Detection and Slot Filling ACL 2025 VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling ICML 2024 Robot Policy Learning with Temporal Optimal Transport Reward NIPS 2024 MKG-FENN: A Multimodal Knowledge Graph Fused End-to-End Neural Network for Accurate Drug–Drug Interaction Prediction AAAI 2024 Neural Network Approximation for Pessimistic Offline Reinforcement Learning AAAI 2024 Meta-Task Prompting Elicits Embeddings from Large Language Models ACL 2024 KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation ACL 2024 How Far can 100 Samples Go? Unlocking Zero-Shot Translation with Tiny Multi-Parallel Data ACL 2024 On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation COLING 2024 Flow Matching for Conditional Text Generation in a Few Sampling Steps EACL 2024 Neuron Specialization: Leveraging Intrinsic Task Modularity for Multilingual Machine Translation EMNLP 2024 The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention EMNLP 2024 Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation EMNLP 2024 KMatrix: A Flexible Heterogeneous Knowledge Enhancement Toolkit for Large Language Model EMNLP 2024 MetaKP: On-Demand Keyphrase Generation EMNLP 2024 Representational Isomorphism and Alignment of Multilingual Large Language Models EMNLP 2024 UvA-MT’s Participation in the WMT24 General Translation Shared Task EMNLP 2024 Exploring Effective Stimulus Encoding via Vision System Modeling for Visual Prostheses ICLR 2024 FedInverse: Evaluating Privacy Leakage in Federated Learning ICLR 2024 MogaNet: Multi-order Gated Aggregation Network ICLR 2024 FuRL: Visual-Language Models as Fuzzy Rewards for Reinforcement Learning ICML 2024 FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees ICML 2024 Repoformer: Selective Retrieval for Repository-Level Code Completion ICML 2024 BADFSS: Backdoor Attacks on Federated Self-Supervised Learning IJCAI 2024 Unsupervised Anomaly Detection via Masked Diffusion Posterior Sampling IJCAI 2024 FedTAD: Topology-aware Data-free Knowledge Distillation for Subgraph Federated Learning IJCAI 2024 MMGNN: A Molecular Merged Graph Neural Network for Explainable Solvation Free Energy Prediction IJCAI 2024 An Uyghur Extension to the MASSIVE Multi-lingual Spoken Language Understanding Corpus with Comprehensive Evaluations INTERSPEECH 2024 Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation EMNLP 2023 Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN ICML 2023 BARA: Efficient Incentive Mechanism with Online Reward Budget Allocation in Cross-Silo Federated Learning IJCAI 2023 DPAUC: Differentially Private AUC Computation in Federated Learning AAAI 2023 Online Semi-supervised Learning with Mix-Typed Streaming Features AAAI 2023 Empathy Intent Drives Empathy Detection EMNLP 2023 Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks EMNLP 2023 ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs INTERSPEECH 2023 MSAF: A Multiple Self-Attention Field Method for Speech Enhancement INTERSPEECH 2023 Gap Minimization for Knowledge Sharing and Transfer JMLR 2023 Spatial Self-Distillation for Object Detection with Inaccurate Bounding Boxes ICCV 2023 ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling CVPR 2023 Relightable Neural Human Assets From Multi-View Gradient Illuminations CVPR 2023 UvA-MT’s Participation in the WMT 2023 General Translation Shared Task EMNLP 2023 Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Models EMNLP 2023 FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment IJCAI 2023 Object Localization Under Single Coarse Point Supervision CVPR 2022 Constrained Adaptive Projection with Pretrained Features for Anomaly Detection IJCAI 2022 AutoMix: Unveiling the Power of Mixup for Stronger Classifiers ECCV 2022 Reinforcement Learning Based Dynamic Model Combination for Time Series Forecasting AAAI 2022 MirrorAlign: A Super Lightweight Unsupervised Word Alignment Model via Cross-Lingual Contrastive Learning ACL 2022 Challenges to Open-Domain Constituency Parsing ACL 2022 DLME: Deep Local-Flatness Manifold Embedding ECCV 2022 Representation Learning for Resource-Constrained Keyphrase Generation EMNLP 2022 A Closer Look at Offline RL Agents NIPS 2022 WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit INTERSPEECH 2022 WeNet: Production Oriented Streaming and Non-Streaming End-to-End Speech Recognition Toolkit INTERSPEECH 2021 Improving Neural Machine Translation by Bidirectional Training EMNLP 2021 Residential Electric Load Forecasting via Attentive Transfer of Graph Neural Networks IJCAI 2021 Context-Aware Cross-Attention for Non-Autoregressive Translation COLING 2020 SlotRefine: A Fast Non-Autoregressive Model for Joint Intent Detection and Slot Filling EMNLP 2020 Online Learning from Capricious Data Streams: A Generative Approach IJCAI 2019 WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition EMNLP 2018 Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition CVPR 2014