Wei Hu

ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders AAAI 2026 Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models AAAI 2026 Bootstrapping Code Translation with Weighted Multilanguage Exploration ACL 2026 Do We Truly Need So Many Samples? Multi-LLM Repeated Sampling Efficiently Scales Test-Time Compute AAAI 2026 Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation ACL 2026 Spatial-Spectral Homogeneous Attacks on Physical-World Large Vision-Language Models AAAI 2026 Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering ACL 2025 Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination JMLR 2025 Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition EMNLP 2025 Mixture of LoRA Experts for Continual Information Extraction with LLMs EMNLP 2025 Knowledge Graph-Guided Retrieval Augmented Generation NAACL 2025 Large Scene Generation with Cube-Absorb Discrete Diffusion ICCV 2025 ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents ACL 2025 Controllable Protein Sequence Generation with LLM Preference Optimization AAAI 2025 Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks CVPR 2025 Swing-by Dynamics in Concept Learning and Compositional Generalization ICLR 2025 HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration ICCV 2025 Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model ICLR 2025 Timeline-based Sentence Decomposition with In Context Learning for Temporal Fact Extraction ACL 2024 How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations ICLR 2024 Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking ICLR 2024 Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data ICLR 2024 A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning NIPS 2024 Abrupt Learning in Transformers: A Case Study on Matrix Completion NIPS 2024 KnowLA: Enhancing Parameter-efficient Finetuning with Knowledgeable Adaptation NAACL 2024 Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack AAAI 2024 Knowledge Graph Error Detection with Contrastive Confidence Adaption AAAI 2024 DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning AAAI 2024 Understanding Surprising Generalization Phenomena in Deep Learning AAAI 2024 Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion ACL 2024 Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation ACL 2024 Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization AISTATS 2024 Improving Multilingual Text-to-Speech with Mixture-of-Language-Experts and Accent Disentanglement INTERSPEECH 2024 E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition INTERSPEECH 2024 DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation ICML 2024 Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing CVPR 2024 LTGC: Long-tail Recognition via Leveraging LLMs-driven Generated Content CVPR 2024 RangeLDM: Fast Realistic LiDAR Point Cloud Generation ECCV 2024 Echoes of the Past: Boosting Long-tail Recognition via Reflective Learning ECCV 2024 MDCS: More Diverse Experts with Consistency Self-distillation for Long-tailed Recognition ICCV 2023 Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data ICLR 2023 MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer ICLR 2023 What Makes Entities Similar? A Similarity Flooding Perspective for Multi-sourced Knowledge Graph Embeddings ICML 2023 Continual Event Extraction with Semantic Confusion Rectification EMNLP 2023 Lifelong Embedding Learning and Transfer for Growing Knowledge Graphs AAAI 2023 Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity NIPS 2023 Enabling Abductive Learning to Exploit Knowledge Graph IJCAI 2023 3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack ICCV 2023 Serial Contrastive Knowledge Distillation for Continual Few-shot Relation Extraction ACL 2023 Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection CVPR 2023 Improving Continual Relation Extraction by Distinguishing Analogous Semantics ACL 2023 Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations ICML 2023 Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation NIPS 2022 Implicit Relation Linking for Question Answering over Knowledge Graph ACL 2022 CMCC: A Comprehensive and Large-Scale Human-Human Dataset for Dialogue Systems EMNLP 2022 Exploring the Devil in Graph Spectral Domain for 3D Point Cloud Attacks ECCV 2022 Neural Capture of Animatable 3D Human from Monocular Video ECCV 2022 State-Aware Adversarial Training for Utterance-Level Dialogue Generation EMNLP 2022 Ensemble Semi-supervised Entity Alignment via Cycle-Teaching AAAI 2022 Learning to Focus on the Foreground for Temporal Sentence Grounding COLING 2022 More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize ICML 2022 Understanding and Improving Knowledge Graph Embedding for Entity Alignment ICML 2022 Knowing the No-match: Entity Alignment with Dangling Cases IJCNLP 2021 Knowing the No-match: Entity Alignment with Dangling Cases ACL 2021 Diffusion Probabilistic Models for 3D Point Cloud Generation CVPR 2021 AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations From Self-Trained Negative Adversaries CVPR 2021 Knowing False Negatives: An Adversarial Training Method for Distantly Supervised Relation Extraction EMNLP 2021 Score-Based Point Cloud Denoising ICCV 2021 Few-Shot Learning via Learning the Representation, Provably ICLR 2021 Impact of Representation Learning in Linear Bandits ICLR 2021 Near-Optimal Linear Regression under Distribution Shift ICML 2021 A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning ICML 2021 When is particle filtering efficient for planning in partially observed linear dynamical systems? UAI 2021 Edge-aware Graph Representation Learning and Reasoning for Face Parsing ECCV 2020 GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-Wise Transformations CVPR 2020 The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks NIPS 2020 Simple and Effective Regularization Methods for Training on Noisily Labeled Data with Generalization Guarantee ICLR 2020 Knowledge Association with Hyperbolic Knowledge Graph Embeddings EMNLP 2020 Global-to-Local Neural Networks for Document-Level Relation Extraction EMNLP 2020 Knowledge Graph Alignment Network with Gated Multi-Hop Neighborhood Aggregation AAAI 2020 Provable Benefit of Orthogonal Initialization in Optimizing Deep Linear Networks ICLR 2020 A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks ICLR 2019 Width Provably Matters in Optimization for Deep Linear Neural Networks ICML 2019 Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs ICML 2019 Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering EMNLP 2019 Multi-view Knowledge Graph Embedding for Entity Alignment IJCAI 2019 Noise-Tolerant Paradigm for Training Face Recognition CNNs CVPR 2019 Leveraging Frequent Query Substructures to Generate Formal Queries for Complex Question Answering IJCNLP 2019 Linear Convergence of the Primal-Dual Gradient Method for Convex-Concave Saddle Point Problems without Strong Convexity AISTATS 2019 On Exact Computation with an Infinitely Wide Neural Net NIPS 2019 Implicit Regularization in Deep Matrix Factorization NIPS 2019 Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets NIPS 2019 Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks ICML 2019 Bootstrapping Entity Alignment with Knowledge Graph Embedding IJCAI 2018 Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced NIPS 2018 An Analysis of the t-SNE Algorithm for Data Visualization COLT 2018 Online Improper Learning with an Approximation Oracle NIPS 2018 Linear Convergence of a Frank-Wolfe Type Algorithm over Trace-Norm Balls NIPS 2017 Combinatorial Multi-Armed Bandit with General Reward Functions NIPS 2016 Modeling Chinese Documents with Topical Word-Character Models COLING 2008