{"total":89,"rows":[{"id":"2201.12204","title":"From data to functa: Your data point is a function and you can treat it like one","created":"2022-01-28","cited_by_count":187,"area":null},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107,"area":null},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87,"area":null},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70,"area":null},{"id":"2209.14733","title":"Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weights","created":"2022-09-29","cited_by_count":64,"area":"distill"},{"id":"2302.05438","title":"Deep Learning on Implicit Neural Representations of Shapes","created":"2023-02-10","cited_by_count":63,"area":null},{"id":"2403.12143","title":"Graph Neural Networks for Learning Equivariant Representations of Neural Networks","created":"2024-03-18","cited_by_count":59,"area":null},{"id":"2312.04501","title":"Graph Metanetworks for Processing Diverse Neural Architectures","created":"2023-12-07","cited_by_count":57,"area":null},{"id":"2305.13546","title":"Neural Functional Transformers","created":"2023-05-22","cited_by_count":52,"area":null},{"id":"2402.13144","title":"Neural Network Diffusion","created":"2024-02-20","cited_by_count":42,"area":"diffusion"},{"id":"2406.09997","title":"Towards Scalable and Versatile Weight Space Learning","created":"2024-06-14","cited_by_count":41,"area":null},{"id":"2209.14764","title":"Model Zoos: A Dataset of Diverse Populations of Neural Network Models","created":"2022-09-29","cited_by_count":39,"area":null},{"id":"2402.18153","title":"Diffusion-Based Neural Network Weights Generation","created":"2024-02-28","cited_by_count":39,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2303.04143","title":"Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2207.11719","title":"Gradient-based Bi-level Optimization for Deep Learning: A Survey","created":"2022-07-24","cited_by_count":26,"area":null},{"id":"2406.10685","title":"Scale Equivariant Graph Metanetworks","created":"2024-06-15","cited_by_count":24,"area":null},{"id":"2210.13148","title":"Transformers over Directed Acyclic Graphs","created":"2022-10-24","cited_by_count":23,"area":null},{"id":"2201.08459","title":"Federated Learning with Heterogeneous Architectures using Graph HyperNetworks","created":"2022-01-20","cited_by_count":19,"area":null},{"id":"2305.18738","title":"Generating Behaviorally Diverse Policies with Latent Diffusion Models","created":"2023-05-30","cited_by_count":19,"area":"diffusion"},{"id":"2409.11697","title":"Monomial Matrix Group Equivariant Neural Functional Networks","created":"2024-09-18","cited_by_count":17,"area":null},{"id":"2408.01415","title":"Conditional LoRA Parameter Generation","created":"2024-08-02","cited_by_count":16,"area":null},{"id":"2212.13554","title":"NeRN -- Learning Neural Representations for Neural Networks","created":"2022-12-27","cited_by_count":14,"area":null},{"id":"2506.07998","title":"Generative Modeling of Weights: Generalization or Memorization?","created":"2025-06-09","cited_by_count":14,"area":null},{"id":"2207.10951","title":"Hyper-Representations for Pre-Training and Transfer Learning","created":"2022-07-22","cited_by_count":12,"area":"distill"},{"id":"2306.09819","title":"Amortized Inference for Gaussian Process Hyperparameters of Structured Kernels","created":"2023-06-16","cited_by_count":10,"area":null},{"id":"2401.08139","title":"Transferring Core Knowledge via Learngenes","created":"2024-01-16","cited_by_count":10,"area":null},{"id":"2207.01570","title":"Goal-Conditioned Generators of Deep Policies","created":"2022-07-04","cited_by_count":9,"area":null},{"id":"2311.00915","title":"Task-Agnostic Low-Rank Adapters for Unseen English Dialects","created":"2023-11-02","cited_by_count":9,"area":null},{"id":"2202.04104","title":"Teaching Networks to Solve Optimization Problems","created":"2022-02-08","cited_by_count":7,"area":null},{"id":"2301.05860","title":"State of the Art and Potentialities of Graph-level Learning","created":"2023-01-14","cited_by_count":6,"area":null},{"id":"2307.10529","title":"Fast Unsupervised Deep Outlier Model Selection with Hypernetworks","created":"2023-07-20","cited_by_count":6,"area":null},{"id":"2404.07993","title":"Connecting NeRFs, Images, and Text","created":"2024-04-11","cited_by_count":6,"area":null},{"id":"2406.11840","title":"LLaNA: Large Language and NeRF Assistant","created":"2024-06-17","cited_by_count":6,"area":"mllm"},{"id":"2503.17138","title":"Structure Is Not Enough: Leveraging Behavior for Neural Network Weight Reconstruction","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2605.18632","title":"Position: Weight Space Should Be a First-Class Generative AI Modality","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2312.13277","title":"Deep Learning on Object-centric 3D Neural Fields","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2409.19289","title":"FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models","created":"2024-09-28","cited_by_count":5,"area":"diffusion"},{"id":"2412.15554","title":"Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation","created":"2024-12-20","cited_by_count":5,"area":null},{"id":"2511.00543","title":"Learning an Efficient Optimizer via Hybrid-Policy Sub-Trajectory Balance","created":"2025-11-01","cited_by_count":5,"area":null},{"id":"2601.05052","title":"DeepWeightFlow: Re-Basined Flow Matching for Generating Neural Network Weights","created":"2026-01-08","cited_by_count":5,"area":"diffusion"},{"id":"2210.00140","title":"Efficiently Learning Small Policies for Locomotion and Manipulation","created":"2022-09-30","cited_by_count":4,"area":null},{"id":"2212.13970","title":"Breaking the Architecture Barrier: A Method for Efficient Knowledge Transfer Across Networks","created":"2022-12-28","cited_by_count":4,"area":null},{"id":"2309.16663","title":"HyperPPO: A scalable method for finding small policies for robotic control","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2410.11878","title":"Neural Metamorphosis","created":"2024-10-10","cited_by_count":4,"area":null},{"id":"2502.01117","title":"Learning to Learn Weight Generation via Local Consistency Diffusion","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2510.02096","title":"Learning Model Representations Using Publicly Available Model Hubs","created":"2025-10-02","cited_by_count":4,"area":null},{"id":"2604.11446","title":"Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration","created":"2026-04-13","cited_by_count":4,"area":null},{"id":"2312.03051","title":"Generating Interpretable Networks using Hypernetworks","created":"2023-12-05","cited_by_count":3,"area":"mechinterp"},{"id":"2406.15132","title":"Younger: The First Dataset for Artificial Intelligence-Generated Neural Network Architecture","created":"2024-06-20","cited_by_count":3,"area":null},{"id":"2504.02012","title":"Instruction-Guided Autoregressive Neural Network Parameter Generation","created":"2025-04-02","cited_by_count":3,"area":null},{"id":"2504.10231","title":"A Model Zoo of Vision Transformers","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2504.18072","title":"A Model Zoo on Phase Transitions in Neural Networks","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2603.00180","title":"NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2206.03661","title":"One Hyper-Initializer for All Network Architectures in Medical Image Analysis","created":"2022-06-08","cited_by_count":2,"area":null},{"id":"2210.01973","title":"Meta-Ensemble Parameter Learning","created":"2022-10-05","cited_by_count":2,"area":"distill"},{"id":"2306.06852","title":"Rethink DARTS Search Space and Renovate a New Benchmark","created":"2023-06-12","cited_by_count":2,"area":null},{"id":"2501.01601","title":"Few-shot Implicit Function Generation via Equivariance","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2504.15323","title":"HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2207.10049","title":"Pretraining a Neural Network before Knowing Its Architecture","created":"2022-07-20","cited_by_count":1,"area":null},{"id":"2208.12489","title":"GHN-Q: Parameter Prediction for Unseen Quantized Convolutional Architectures via Graph Hypernetworks","created":"2022-08-26","cited_by_count":1,"area":null},{"id":"2310.17737","title":"ArchBERT: Bi-Modal Understanding of Neural Architectures and Natural Languages","created":"2023-10-26","cited_by_count":1,"area":"mllm"},{"id":"2405.16287","title":"LoGAH: Predicting 774-Million-Parameter Transformers using Graph HyperNetworks with 1/100 Parameters","created":"2024-05-25","cited_by_count":1,"area":null},{"id":"2408.06486","title":"Implicit Neural Representation For Accurate CFD Flow Field Prediction","created":"2024-08-12","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":"2506.10463","title":"Starting Positions Matter: A Study on Better Weight Initialization for Neural Network Quantization","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2507.10623","title":"Flows and Diffusions on the Neural Manifold","created":"2025-07-14","cited_by_count":1,"area":null},{"id":"2507.20110","title":"NeuroVoxel-LM: Language-Aligned 3D Perception via Dynamic Voxelization and Meta-Embedding","created":"2025-07-27","cited_by_count":1,"area":"mllm"},{"id":"2509.10535","title":"Semantic-guided LoRA Parameters Generation","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2604.12096","title":"LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.07217","title":"Robotic Policy Adaptation via Weight-Space Meta-Learning","created":"2026-06-05","cited_by_count":1,"area":"vla"},{"id":"2204.11838","title":"Automating Neural Architecture Design without Search","created":"2022-04-21","cited_by_count":0,"area":null},{"id":"2205.15555","title":"Graph-level Neural Networks: Current Progress and Future Directions","created":"2022-05-31","cited_by_count":0,"area":null},{"id":"2309.13773","title":"GHN-QAT: Training Graph Hypernetworks to Predict Quantization-Robust Parameters of Unseen Limited Precision Neural Networks","created":"2023-09-24","cited_by_count":0,"area":null},{"id":"2310.11862","title":"Learning to Generate Parameters of ConvNets for Unseen Image Data","created":"2023-10-18","cited_by_count":0,"area":null},{"id":"2310.16695","title":"From Pointwise to Powerhouse: Initialising Neural Networks with Generative Models","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2410.05107","title":"Hyper-Representations: Learning from Populations of Neural Networks","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2501.02007","title":"TART: Token-based Architecture Transformer for Neural Network Performance Prediction","created":"2025-01-02","cited_by_count":0,"area":null},{"id":"2504.13995","title":"Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Training","created":"2025-04-18","cited_by_count":0,"area":"mllm"},{"id":"2506.05641","title":"Projectable Models: One-Shot Generation of Small Specialized Transformers from Large Ones","created":"2025-06-06","cited_by_count":0,"area":null},{"id":"2507.15869","title":"An open dataset of neural networks for hypernetwork research","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2509.07373","title":"SBS: Enhancing Parameter-Efficiency of Neural Representations for Neural Networks via Spectral Bias Suppression","created":"2025-09-09","cited_by_count":0,"area":null},{"id":"2510.08300","title":"Symmetry-Aware Fully-Amortized Optimization with Scale Equivariant Graph Metanetworks","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2601.19694","title":"Self-Supervised Weight Templates for Scalable Vision Model Initialization","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2607.11475","title":"HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models","created":"2026-07-13","cited_by_count":0,"area":"alignment"},{"id":"2609.19915","title":"Amortizing Physics-Informed Neural Solvers via Graph Hypernetworks","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.01649","title":"CrossGMN: Graph Metanetworks for Cross-Architecture Weight-Space Transformations","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}