{"total":1148,"rows":[{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288,"area":null},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375,"area":null},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531,"area":null},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487,"area":null},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288,"area":"offlinerl"},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252,"area":null},{"id":"2111.15668","title":"AdaViT: Adaptive Vision Transformers for Efficient Image Recognition","created":"2021-11-30","cited_by_count":228,"area":null},{"id":"2103.02582","title":"D'ya like DAGs? A Survey on Structure Learning and Causal Discovery","created":"2021-03-03","cited_by_count":211,"area":null},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210,"area":null},{"id":"2103.03098","title":"Accounting for Variance in Machine Learning Benchmarks","created":"2021-03-01","cited_by_count":201,"area":null},{"id":"2106.05819","title":"Adversarial Graph Augmentation to Improve Graph Contrastive Learning","created":"2021-06-10","cited_by_count":200,"area":null},{"id":"2307.03838","title":"RADAR: Robust AI-Text Detection via Adversarial Learning","created":"2023-07-07","cited_by_count":190,"area":null},{"id":"2204.05454","title":"Are Multimodal Transformers Robust to Missing Modality?","created":"2022-04-12","cited_by_count":186,"area":null},{"id":"2311.01460","title":"Implicit Chain of Thought Reasoning via Knowledge Distillation","created":"2023-11-02","cited_by_count":176,"area":"lr"},{"id":"2207.09353","title":"Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communications","created":"2022-07-19","cited_by_count":175,"area":null},{"id":"2105.01288","title":"Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis","created":"2021-05-04","cited_by_count":172,"area":null},{"id":"2101.06861","title":"Discrete Graph Structure Learning for Forecasting Multiple Time Series","created":"2021-01-18","cited_by_count":171,"area":null},{"id":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160,"area":null},{"id":"2506.10892","title":"The Diffusion Duality","created":"2025-06-12","cited_by_count":135,"area":"diffusion"},{"id":"2105.08919","title":"Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation","created":"2021-05-19","cited_by_count":134,"area":"distill"},{"id":"2204.08770","title":"GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning","created":"2022-04-19","cited_by_count":128,"area":null},{"id":"2403.09054","title":"Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference","created":"2024-03-14","cited_by_count":126,"area":"inference"},{"id":"2206.09113","title":"Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting","created":"2022-06-18","cited_by_count":117,"area":null},{"id":"2106.03760","title":"DSelect-k: Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning","created":"2021-06-07","cited_by_count":115,"area":"moe"},{"id":"2105.11839","title":"DiBS: Differentiable Bayesian Structure Learning","created":"2021-05-25","cited_by_count":106,"area":null},{"id":"2311.01017","title":"Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion","created":"2023-11-02","cited_by_count":106,"area":"wm"},{"id":"1807.09936","title":"Multi-Agent Generative Adversarial Imitation Learning","created":"2018-07-26","cited_by_count":100,"area":"offlinerl"},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100,"area":null},{"id":"2206.07746","title":"Condensing Graphs via One-Step Gradient Matching","created":"2022-06-15","cited_by_count":100,"area":null},{"id":"2107.04562","title":"The Bayesian Learning Rule","created":"2021-07-09","cited_by_count":99,"area":null},{"id":"2204.01613","title":"SPECTRE: Spectral Conditioning Helps to Overcome the Expressivity Limits of One-shot Graph Generators","created":"2022-04-04","cited_by_count":99,"area":null},{"id":"2106.01798","title":"Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions","created":"2021-06-03","cited_by_count":98,"area":null},{"id":"2202.02195","title":"Deep End-to-end Causal Inference","created":"2022-02-04","cited_by_count":95,"area":null},{"id":"2102.04509","title":"Oops I Took A Gradient: Scalable Sampling for Discrete Distributions","created":"2021-02-08","cited_by_count":92,"area":null},{"id":"2306.03745","title":"Soft Merging of Experts with Adaptive Routing","created":"2023-06-06","cited_by_count":90,"area":"moe"},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87,"area":null},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"area":null},{"id":"2309.04669","title":"Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization","created":"2023-09-09","cited_by_count":87,"area":"lr"},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2110.01515","title":"A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning","created":"2021-10-04","cited_by_count":82,"area":null},{"id":"2202.06533","title":"An Introduction to Neural Data Compression","created":"2022-02-14","cited_by_count":79,"area":null},{"id":"2410.13643","title":"Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design","created":"2024-10-17","cited_by_count":79,"area":"diffusion"},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78,"area":null},{"id":"2210.04142","title":"Deep Clustering: A Comprehensive Survey","created":"2022-10-09","cited_by_count":78,"area":null},{"id":"2211.09761","title":"Efficient Transformers with Dynamic Token Pooling","created":"2022-11-17","cited_by_count":76,"area":null},{"id":"2202.13257","title":"Controllable Natural Language Generation with Contrastive Prefixes","created":"2022-02-27","cited_by_count":75,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2507.07955","title":"Dynamic Chunking for End-to-End Hierarchical Sequence Modeling","created":"2025-07-10","cited_by_count":72,"area":null},{"id":"2104.13874","title":"Exploring Relational Context for Multi-Task Dense Prediction","created":"2021-04-28","cited_by_count":71,"area":null},{"id":"2111.12701","title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","created":"2021-11-24","cited_by_count":71,"area":"diffusion"},{"id":"2205.07547","title":"SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization","created":"2022-05-16","cited_by_count":68,"area":null},{"id":"2210.08277","title":"Deep Differentiable Logic Gate Networks","created":"2022-10-15","cited_by_count":67,"area":null},{"id":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2205.15967","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","created":"2022-05-31","cited_by_count":63,"area":"offlinerl"},{"id":"2403.10427","title":"SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians","created":"2024-03-15","cited_by_count":61,"area":null},{"id":"2103.01890","title":"Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations","created":"2021-03-02","cited_by_count":59,"area":null},{"id":"2104.13400","title":"FrameExit: Conditional Early Exiting for Efficient Video Recognition","created":"2021-04-27","cited_by_count":59,"area":null},{"id":"2111.09189","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","created":"2021-10-15","cited_by_count":58,"area":null},{"id":"2206.11168","title":"Ordered Subgraph Aggregation Networks","created":"2022-06-22","cited_by_count":57,"area":null},{"id":"2211.14065","title":"Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating","created":"2022-11-25","cited_by_count":57,"area":null},{"id":"2210.07795","title":"EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning","created":"2022-10-14","cited_by_count":56,"area":"mllm"},{"id":"2301.00557","title":"Learning to Maximize Mutual Information for Dynamic Feature Selection","created":"2023-01-02","cited_by_count":56,"area":null},{"id":"2309.01017","title":"Contrastive Grouping with Transformer for Referring Image Segmentation","created":"2023-09-02","cited_by_count":54,"area":null},{"id":"2303.11911","title":"Time Series Contrastive Learning with Information-Aware Augmentations","created":"2023-03-21","cited_by_count":52,"area":null},{"id":"2303.17056","title":"Audio-Visual Grouping Network for Sound Localization from Mixtures","created":"2023-03-29","cited_by_count":52,"area":null},{"id":"2405.15179","title":"VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks","created":"2024-05-24","cited_by_count":52,"area":null},{"id":"2106.11232","title":"Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering","created":"2021-06-21","cited_by_count":51,"area":null},{"id":"2406.19272","title":"Stochastic Concept Bottleneck Models","created":"2024-06-27","cited_by_count":51,"area":null},{"id":"2104.14575","title":"Unsupervised Layered Image Decomposition into Object Prototypes","created":"2021-04-29","cited_by_count":50,"area":null},{"id":"2302.12721","title":"LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version","created":"2023-02-24","cited_by_count":50,"area":null},{"id":"2306.07050","title":"Revisiting Token Pruning for Object Detection and Instance Segmentation","created":"2023-06-12","cited_by_count":50,"area":"inference"},{"id":"2410.15618","title":"Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation","created":"2024-10-21","cited_by_count":50,"area":"diffusion"},{"id":"2108.11179","title":"Recall@k Surrogate Loss with Large Batches and Similarity Mixup","created":"2021-08-25","cited_by_count":49,"area":null},{"id":"2106.02874","title":"RDA: Robust Domain Adaptation via Fourier Adversarial Attacking","created":"2021-06-05","cited_by_count":48,"area":null},{"id":"2405.08550","title":"Learning Multi-Agent Communication from Graph Modeling Perspective","created":"2024-05-14","cited_by_count":48,"area":null},{"id":"2108.04657","title":"Differentiable Subset Pruning of Transformer Heads","created":"2021-08-10","cited_by_count":47,"area":null},{"id":"2206.07824","title":"Large-Scale Differentiable Causal Discovery of Factor Graphs","created":"2022-06-15","cited_by_count":47,"area":null},{"id":"2207.02127","title":"A survey of multimodal deep generative models","created":"2022-07-05","cited_by_count":47,"area":null},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47,"area":null},{"id":"2102.12871","title":"SparseBERT: Rethinking the Importance Analysis in Self-attention","created":"2021-02-25","cited_by_count":46,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2105.01571","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","created":"2021-05-03","cited_by_count":45,"area":null},{"id":"2110.10211","title":"Learning Partial Equivariances from Data","created":"2021-10-19","cited_by_count":45,"area":null},{"id":"2201.09119","title":"A Causal Lens for Controllable Text Generation","created":"2022-01-22","cited_by_count":45,"area":null},{"id":"2111.01564","title":"MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks","created":"2021-11-02","cited_by_count":44,"area":null},{"id":"2207.09953","title":"Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction","created":"2022-07-20","cited_by_count":44,"area":null},{"id":"2402.10309","title":"Discrete Probabilistic Inference as Control in Multi-path Environments","created":"2024-02-15","cited_by_count":44,"area":null},{"id":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42,"area":null},{"id":"2203.16708","title":"Task Adaptive Parameter Sharing for Multi-Task Learning","created":"2022-03-30","cited_by_count":42,"area":null},{"id":"2210.00482","title":"Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language","created":"2022-10-02","cited_by_count":42,"area":null},{"id":"2306.02109","title":"Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency","created":"2023-06-03","cited_by_count":42,"area":null},{"id":"2212.10368","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","created":"2022-12-20","cited_by_count":41,"area":null},{"id":"2405.09055","title":"A safety realignment framework via subspace-oriented model fusion for large language models","created":"2024-05-15","cited_by_count":41,"area":"safety"},{"id":"2112.01799","title":"Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generation","created":"2021-12-03","cited_by_count":40,"area":"diffusion"},{"id":"2103.00742","title":"Automated Machine Learning on Graphs: A Survey","created":"2021-03-01","cited_by_count":39,"area":null},{"id":"2202.00155","title":"Fortuitous Forgetting in Connectionist Networks","created":"2022-02-01","cited_by_count":39,"area":null},{"id":"2106.01908","title":"You Never Cluster Alone","created":"2021-06-03","cited_by_count":38,"area":null},{"id":"2111.02552","title":"Is Bang-Bang Control All You Need? Solving Continuous Control with Bernoulli Policies","created":"2021-11-03","cited_by_count":38,"area":null}],"next_cursor":"100"}