{"total":46,"rows":[{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650,"area":null},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"area":null},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203,"area":null},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115,"area":null},{"id":"2312.16051","title":"Inter-X: Towards Versatile Human-Human Interaction Analysis","created":"2023-12-26","cited_by_count":98,"area":null},{"id":"2303.10876","title":"EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning","created":"2023-03-20","cited_by_count":97,"area":null},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78,"area":null},{"id":"2304.10628","title":"HM-ViT: Hetero-modal Vehicle-to-Vehicle Cooperative perception with vision transformer","created":"2023-04-20","cited_by_count":70,"area":null},{"id":"2303.10437","title":"Grounding 3D Object Affordance from 2D Interactions in Images","created":"2023-03-18","cited_by_count":62,"area":null},{"id":"2403.11882","title":"ReGenNet: Towards Human Action-Reaction Synthesis","created":"2024-03-18","cited_by_count":53,"area":null},{"id":"2209.01589","title":"Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection","created":"2022-09-04","cited_by_count":43,"area":null},{"id":"2212.05946","title":"Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks","created":"2022-12-12","cited_by_count":37,"area":null},{"id":"2306.08107","title":"AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks","created":"2023-06-13","cited_by_count":35,"area":null},{"id":"2308.12216","title":"SG-Former: Self-guided Transformer with Evolving Token Reallocation","created":"2023-08-23","cited_by_count":32,"area":null},{"id":"2403.01753","title":"Training-Free Pretrained Model Merging","created":"2024-03-04","cited_by_count":32,"area":null},{"id":"2308.08643","title":"Towards Personalized Federated Learning via Heterogeneous Model Reassembly","created":"2023-08-16","cited_by_count":31,"area":null},{"id":"2207.08224","title":"Learning with Recoverable Forgetting","created":"2022-07-17","cited_by_count":30,"area":null},{"id":"2210.04206","title":"Attention Diversification for Domain Generalization","created":"2022-10-09","cited_by_count":29,"area":null},{"id":"2301.01296","title":"TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models","created":"2023-01-03","cited_by_count":24,"area":null},{"id":"2306.08328","title":"Distribution Shift Inversion for Out-of-Distribution Prediction","created":"2023-06-14","cited_by_count":23,"area":null},{"id":"2304.14593","title":"Deep Graph Reprogramming","created":"2023-04-28","cited_by_count":22,"area":null},{"id":"2211.12712","title":"Contrastive Identity-Aware Learning for Multi-Agent Value Decomposition","created":"2022-11-23","cited_by_count":19,"area":null},{"id":"2304.11595","title":"Segment Anything in Non-Euclidean Domains: Challenges and Opportunities","created":"2023-04-23","cited_by_count":16,"area":null},{"id":"2305.19903","title":"Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization","created":"2023-05-31","cited_by_count":12,"area":null},{"id":"2412.05186","title":"One-shot Federated Learning via Synthetic Distiller-Distillate Communication","created":"2024-12-06","cited_by_count":12,"area":null},{"id":"2502.12706","title":"Scalable Model Merging with Progressive Layer-wise Distillation","created":"2025-02-18","cited_by_count":10,"area":null},{"id":"2304.11818","title":"Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2406.11129","title":"Neural Lineage","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2303.10597","title":"Partial Network Cloning","created":"2023-03-19","cited_by_count":6,"area":null},{"id":"2307.14382","title":"When Multi-Task Learning Meets Partial Supervision: A Computer Vision Review","created":"2023-07-25","cited_by_count":6,"area":null},{"id":"2404.17184","title":"Low-Rank Knowledge Decomposition for Medical Foundation Models","created":"2024-04-26","cited_by_count":5,"area":null},{"id":"2406.00275","title":"StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization","created":"2024-06-01","cited_by_count":5,"area":null},{"id":"2409.05780","title":"Breaking Neural Network Scaling Laws with Modularity","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2306.17005","title":"High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2312.02470","title":"Generator Born from Classifier","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2409.19540","title":"LoRKD: Low-Rank Knowledge Decomposition for Medical Foundation Models","created":"2024-09-29","cited_by_count":4,"area":null},{"id":"2410.11878","title":"Neural Metamorphosis","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2308.00759","title":"Decomposition Ascribed Synergistic Learning for Unified Image Restoration","created":"2023-08-01","cited_by_count":3,"area":null},{"id":"2407.11902","title":"Encapsulating Knowledge in One Prompt","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2412.07802","title":"Language Model as Visual Explainer","created":"2024-12-08","cited_by_count":3,"area":null},{"id":"2303.06635","title":"Schema Inference for Interpretable Image Classification","created":"2023-03-12","cited_by_count":1,"area":null},{"id":"2310.06124","title":"Parameter-efficient Multi-Task and Multi-Domain Learning using Factorized Tensor Networks","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2504.10141","title":"The Impact of Model Zoo Size and Composition on Weight Space Learning","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2304.04135","title":"Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning","created":"2023-04-09","cited_by_count":0,"area":null},{"id":"2310.09278","title":"Disentangled Latent Spaces Facilitate Data-Driven Auxiliary Learning","created":"2023-10-13","cited_by_count":0,"area":null},{"id":"2512.10522","title":"Disentangled and Distilled Encoder for Out-of-Distribution Reasoning with Rademacher Guarantees","created":"2025-12-11","cited_by_count":0,"area":null}],"next_cursor":null}