Zhiyuan Zhang

35 papers · 2019–2026 · 14 conferences · across top CS/AI conferences

Achievements

+9 more ↓

🏃 Academic Marathon (7) 🌍 Conference Polyglot (14) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (12)

🌈 Renaissance Researcher (7) 🗺️ Taxonomy Completionist (70) 🌉 Interdisciplinary Bridge 🤝 Dynamic Duo (15) ❓ The Questioner ⚡ Prolific Year (8) 🗃️ Keyword Collector (154) 🔥 Unstoppable (8) 💎 Century Club (34)

Conferences

EMNLP (8) ICCV (5) CVPR (4) AAAI (3) ICLR (3) NIPS (3) NAACL (2) ACL (1) COLING (1) CORL (1) ECCV (1) IJCAI (1) MICCAI (1) WACV (1)

Top co-authors

Xu Sun (15) Qi Su (4) Xuancheng Ren (4) Fandong Meng (3) Siyuan Huang (3) Jie Zhou (3) Tengyu Liu (3) Junyu Shi (3) Hao Zhou (3) Bin He (3)

Research topics

Privacy (1)

Keywords

backdoor attack (5) diffusion model (3) neural network optimization (3) federated learning (3) transfer learning (2) large language model (2) layer normalization (2) end-to-end learning (2) skip connection (2) zero-shot generalization (2) model aggregation (2) autoregressive model (2) pretrained language model (2) deep neural network (2) model compression (2) autonomous driving (2) sentiment analysis (1) change detection (1) contrastive learning (1) anomaly detection (1)

Papers

EmbryoDiff: A Conditional Diffusion Framework with Multi-Focal Feature Fusion for Fine-Grained Embryo Developmental Stage Recognition AAAI 2026 MoSCo: Real-time and Efficient Text-to-Motion Synthesis via Delta Training WACV 2026 ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models CORL 2025 Time-Lapse Video-Based Embryo Grading via Complementary Spatial-Temporal Pattern Mining MICCAI 2025 DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving ICLR 2025 Information-Bottleneck Driven Binary Neural Network for Change Detection ICCV 2025 GenM3: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation ICCV 2025 MPDrive: Improving Spatial Understanding with Marker-Based Prompt Learning for Autonomous Driving CVPR 2025 I2V3D: Controllable Image-to-video Generation with 3D Guidance ICCV 2025 BHViT: Binarized Hybrid Vision Transformer CVPR 2025 DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines ICLR 2024 Enhancing Byzantine-Resistant Aggregations with Client Embedding EMNLP 2024 Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving NIPS 2024 Scaling Up Dynamic Human-Scene Interaction Modeling CVPR 2024 RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentation ECCV 2024 Full-Body Articulated Human-Object Interaction ICCV 2023 Diffusion Theory as a Scalpel: Detecting and Purifying Poisonous Dimensions in Pre-trained Language Models Caused by Backdoor or Bias ACL 2023 Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense NIPS 2023 Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models EMNLP 2022 End-to-End Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration AAAI 2022 Context-Aware Video Reconstruction for Rolling Shutter Cameras CVPR 2022 GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization EMNLP 2022 Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation EMNLP 2022 Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks EMNLP 2022 No Stock is an Island: Learning Internal and Relational Attributes of Stocks with Contrastive Learning EMNLP 2022 How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data ICLR 2022 Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption AAAI 2021 Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models NAACL 2021 Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning EMNLP 2021 Neural Network Surgery: Injecting Data Patterns into Pre-trained Models with Minimal Instance-wise Side Effects NAACL 2021 Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models EMNLP 2020 Is the Skip Connection Provable to Reform the Neural Network Loss Landscape? IJCAI 2020 Rethinking Skip Connection with Layer Normalization COLING 2020 ShellNet: Efficient Point Cloud Convolutional Neural Networks Using Concentric Shells Statistics ICCV 2019 Understanding and Improving Layer Normalization NIPS 2019