Zhenyu Zhang

CPTCoder: A Reliable LLM System for Medical Procedure Code Prediction ACL 2026 Decoupling Template Bias in CLIP: Harnessing Empty Prompts for Enhanced Few-Shot Learning AAAI 2026 Uncertainty-Aware Routing for Principled Alignment with MoE Dynamics ACL 2026 Dual-Kernel Graph Community Contrastive Learning AAAI 2026 Mixture of Hidden-Dimensions: Not All Hidden-States’ Dimensions are Needed in Transformer ICML 2025 E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models COLING 2025 Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution IJCAI 2025 STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolution ICCV 2025 StrandHead: Text to Hair-Disentangled 3D Head Avatars Using Human-Centric Priors ICCV 2025 Exploiting Multimodal Spatial-temporal Patterns for Video Object Tracking AAAI 2025 Diffusion-based Decoupled Deterministic and Uncertain Framework for Probabilistic Multivariate Time Series Forecasting ICLR 2025 R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference ICLR 2025 Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation AAAI 2025 Mask-Enhanced Autoregressive Prediction: Pay Less Attention to Learn More ICML 2025 On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving ICML 2025 Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent ICCV 2025 Debiasing Multimodal Large Language Models via Noise-Aware Preference Optimization CVPR 2025 HFT: Half Fine-Tuning for Large Language Models ACL 2025 BeamLoRA: Beam-Constraint Low-Rank Adaptation ACL 2025 Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging ACL 2025 Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal Thinking ACL 2025 Accelerating Dense LLMs via L0-regularized Mixture-of-Experts ACL 2025 NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time ACL 2024 Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding NIPS 2024 Test-time Adaptation in Non-stationary Environments via Adaptive Representation Alignment NIPS 2024 Tri-Perspective View Decomposition for Geometry-Aware Depth Completion CVPR 2024 Learning to Decouple the Lights for 3D Face Texture Modeling NIPS 2024 AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization AAAI 2024 Sparsity-Guided Holistic Explanation for LLMs with Interpretable Inference-Time Intervention AAAI 2024 DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion NIPS 2024 LEMON: Reviving Stronger and Smaller LMs from Larger LMs with Linear Parameter Fusion ACL 2024 HintMiner: Automatic Question Hints Mining From Q&A Web Posts with Language Model via Self-Supervised Learning AISTATS 2024 GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection ICML 2024 CaM: Cache Merging for Memory-efficient LLMs Inference ICML 2024 Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity ICML 2024 Sparse Cocktail: Every Sparse Pattern Every Sparse Ratio All At Once ICML 2024 Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference ICML 2024 JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention ICLR 2024 Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy ICLR 2024 DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion AAAI 2023 Adapting to Continuous Covariate Shift via Online Density Ratio Estimation NIPS 2023 H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models NIPS 2023 Dialog-Post: Multi-Level Self-Supervised Objectives and Hierarchical Model for Dialogue Post-Training ACL 2023 Graph Transformer GANs for Graph-Constrained House Generation CVPR 2023 ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts CVPR 2023 Learning To Measure the Point Cloud Reconstruction Loss in a Representation Space CVPR 2023 Learning Neural Proto-Face Field for Disentangled 3D Face Modeling in the Wild CVPR 2023 Learning Versatile 3D Shape Generation with Improved Auto-regressive Models ICCV 2023 Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together! ICLR 2023 Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers ICLR 2023 Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights? ICML 2023 Are Large Kernels Better Teachers than Transformers for ConvNets? ICML 2023 ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding EMNLP 2022 Label Anchored Contrastive Learning for Language Understanding NAACL 2022 RigNet: Repetitive Image Guided Network for Depth Completion ECCV 2022 Multi-modal Masked Pre-training for Monocular Panoramic Depth Completion ECCV 2022 Sparsity Winning Twice: Better Robust Generalization from More Efficient Training ICLR 2022 Physically-Guided Disentangled Implicit Rendering for 3D Face Modeling CVPR 2022 The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy CVPR 2022 Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022 Learning To Restore 3D Face From In-the-Wild Degraded Images CVPR 2022 Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022 Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness ICML 2022 Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets NIPS 2022 Sparse Winning Tickets are Data-Efficient Image Recognizers NIPS 2022 Enhancing Chinese Pre-trained Language Model via Heterogeneous Linguistics Graph ACL 2022 Towards Generalized Open Information Extraction EMNLP 2022 Efficient Lottery Ticket Finding: Less Data is More ICML 2021 From What to Why: Improving Relation Extraction with Rationale Graph IJCNLP 2021 Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning EMNLP 2021 Learning To Aggregate and Personalize 3D Face From In-the-Wild Photo Collection CVPR 2021 Robust Overfitting may be mitigated by properly learned smoothening ICLR 2021 GANs Can Play Lottery Tickets Too ICLR 2021 Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning ICLR 2021 Regularizing Nighttime Weirdness: Efficient Self-Supervised Monocular Depth Estimation in the Dark ICCV 2021 From What to Why: Improving Relation Extraction with Rationale Graph ACL 2021 You are caught stealing my winning lottery ticket! Making a lottery ticket claim its ownership NIPS 2021 Pattern-Structure Diffusion for Multi-Task Learning CVPR 2020 Distilling Knowledge from Well-Informed Soft Labels for Neural Relation Extraction AAAI 2020 Cross-Modal Attention Network for Temporal Inconsistent Audio-Visual Event Localization AAAI 2020 Coarse-to-Fine Pre-training for Named Entity Recognition EMNLP 2020 Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation EMNLP 2020 Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction COLING 2020 Document-level Relation Extraction with Dual-tier Heterogeneous Graph COLING 2020 Online Depth Learning Against Forgetting in Monocular Videos CVPR 2020 Beyond Word Attention: Using Segment Attention in Neural Relation Extraction IJCAI 2019 Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation CVPR 2019 Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation ECCV 2018