{"total":151,"rows":[{"id":"2102.05379","title":"Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions","created":"2021-02-10","cited_by_count":574,"area":"diffusion"},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183,"area":null},{"id":"2503.08026","title":"In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents","created":"2025-03-11","cited_by_count":106,"area":"agents"},{"id":"2104.03466","title":"Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT","created":"2021-04-08","cited_by_count":104,"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":"2109.06870","title":"Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition","created":"2021-09-14","cited_by_count":68,"area":null},{"id":"2208.05003","title":"Wavelet Score-Based Generative Modeling","created":"2022-08-09","cited_by_count":62,"area":"diffusion"},{"id":"2407.21243","title":"Informed Correctors for Discrete Diffusion Models","created":"2024-07-30","cited_by_count":57,"area":"diffusion"},{"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":"2108.04657","title":"Differentiable Subset Pruning of Transformer Heads","created":"2021-08-10","cited_by_count":47,"area":null},{"id":"2303.06424","title":"Regularized Vector Quantization for Tokenized Image Synthesis","created":"2023-03-11","cited_by_count":46,"area":null},{"id":"2209.08790","title":"D&D: Learning Human Dynamics from Dynamic Camera","created":"2022-09-19","cited_by_count":41,"area":null},{"id":"2307.01778","title":"Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling","created":"2023-07-04","cited_by_count":41,"area":null},{"id":"2312.06173","title":"Concrete Subspace Learning based Interference Elimination for Multi-task Model Fusion","created":"2023-12-11","cited_by_count":37,"area":null},{"id":"2106.12059","title":"Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning","created":"2021-06-22","cited_by_count":36,"area":null},{"id":"2110.12805","title":"Algorithms for the Communication of Samples","created":"2021-10-25","cited_by_count":34,"area":null},{"id":"2210.01941","title":"SIMPLE: A Gradient Estimator for $k$-Subset Sampling","created":"2022-10-04","cited_by_count":34,"area":null},{"id":"2403.15180","title":"Self-Improvement for Neural Combinatorial Optimization: Sample without Replacement, but Improvement","created":"2024-03-22","cited_by_count":34,"area":"deeprl"},{"id":"2106.02898","title":"Dynamic Resolution Network","created":"2021-06-05","cited_by_count":31,"area":null},{"id":"2304.08612","title":"Bridging Discrete and Backpropagation: Straight-Through and Beyond","created":"2023-04-17","cited_by_count":31,"area":null},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25,"area":null},{"id":"2305.19185","title":"Compression with Bayesian Implicit Neural Representations","created":"2023-05-30","cited_by_count":25,"area":null},{"id":"2110.00280","title":"Generalizable Human Pose Triangulation","created":"2021-10-01","cited_by_count":24,"area":null},{"id":"2110.08229","title":"Influencing Towards Stable Multi-Agent Interactions","created":"2021-10-05","cited_by_count":24,"area":null},{"id":"2105.08481","title":"Parallel Attention Network with Sequence Matching for Video Grounding","created":"2021-05-18","cited_by_count":22,"area":null},{"id":"2107.00110","title":"Classical Planning in Deep Latent Space","created":"2021-06-30","cited_by_count":22,"area":null},{"id":"2304.01541","title":"Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2304.14593","title":"Deep Graph Reprogramming","created":"2023-04-28","cited_by_count":22,"area":null},{"id":"2106.00967","title":"Multiresolution Equivariant Graph Variational Autoencoder","created":"2021-06-02","cited_by_count":20,"area":null},{"id":"2111.07603","title":"Counterfactual Temporal Point Processes","created":"2021-11-15","cited_by_count":20,"area":null},{"id":"2402.09444","title":"Multimodal Action Quality Assessment","created":"2024-01-31","cited_by_count":20,"area":null},{"id":"2111.07265","title":"Linear, or Non-Linear, That is the Question!","created":"2021-11-14","cited_by_count":19,"area":null},{"id":"2107.04689","title":"Lifelong Teacher-Student Network Learning","created":"2021-07-09","cited_by_count":18,"area":"distill"},{"id":"2102.07298","title":"A Deep Adversarial Model for Suffix and Remaining Time Prediction of Event Sequences","created":"2021-02-15","cited_by_count":17,"area":null},{"id":"2310.00811","title":"Sparse Backpropagation for MoE Training","created":"2023-10-01","cited_by_count":17,"area":"moe"},{"id":"2111.06888","title":"Learning Generalized Gumbel-max Causal Mechanisms","created":"2021-11-11","cited_by_count":16,"area":null},{"id":"1805.02481","title":"MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation","created":"2018-05-07","cited_by_count":15,"area":"moe"},{"id":"2203.00281","title":"Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation","created":"2022-03-01","cited_by_count":15,"area":null},{"id":"2305.08706","title":"Understanding and Bridging the Modality Gap for Speech Translation","created":"2023-05-15","cited_by_count":15,"area":null},{"id":"2305.15877","title":"Exponential Smoothing for Off-Policy Learning","created":"2023-05-25","cited_by_count":15,"area":null},{"id":"2203.08653","title":"Counterfactual Inference of Second Opinions","created":"2022-03-16","cited_by_count":14,"area":null},{"id":"2411.07180","title":"Gumbel Counterfactual Generation From Language Models","created":"2024-11-11","cited_by_count":14,"area":null},{"id":"2108.13178","title":"Modular Meta-Learning for Power Control via Random Edge Graph Neural Networks","created":"2021-08-04","cited_by_count":13,"area":null},{"id":"2507.06928","title":"Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement","created":"2025-07-09","cited_by_count":13,"area":null},{"id":"2110.08825","title":"Localization with Sampling-Argmax","created":"2021-10-17","cited_by_count":11,"area":null},{"id":"2205.14831","title":"Temporal Multiresolution Graph Neural Networks For Epidemic Prediction","created":"2022-05-30","cited_by_count":11,"area":null},{"id":"2404.03323","title":"Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning","created":"2024-04-04","cited_by_count":11,"area":null},{"id":"2109.11817","title":"Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts","created":"2021-09-24","cited_by_count":10,"area":"moe"},{"id":"2210.03543","title":"A2: Efficient Automated Attacker for Boosting Adversarial Training","created":"2022-10-07","cited_by_count":10,"area":null},{"id":"2210.03822","title":"Is margin all you need? An extensive empirical study of active learning on tabular data","created":"2022-10-07","cited_by_count":10,"area":null},{"id":"2510.04525","title":"Demystifying MaskGIT Sampler and Beyond: Adaptive Order Selection in Masked Diffusion","created":"2025-10-06","cited_by_count":10,"area":"diffusion"},{"id":"2207.10776","title":"Auto-regressive Image Synthesis with Integrated Quantization","created":"2022-07-21","cited_by_count":9,"area":null},{"id":"2206.03362","title":"Building Robust Ensembles via Margin Boosting","created":"2022-06-07","cited_by_count":8,"area":null},{"id":"2405.20782","title":"Universal Exact Compression of Differentially Private Mechanisms","created":"2024-05-28","cited_by_count":8,"area":null},{"id":"2105.10626","title":"Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound","created":"2021-05-22","cited_by_count":7,"area":null},{"id":"2210.16838","title":"Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues","created":"2022-10-30","cited_by_count":7,"area":null},{"id":"2302.11875","title":"Improved Training of Mixture-of-Experts Language GANs","created":"2023-02-23","cited_by_count":7,"area":"moe"},{"id":"2306.01108","title":"Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2105.14209","title":"Grammatical Error Correction as GAN-like Sequence Labeling","created":"2021-05-29","cited_by_count":6,"area":null},{"id":"2108.07538","title":"O-HAS: Optical Hardware Accelerator Search for Boosting Both Acceleration Performance and Development Speed","created":"2021-08-17","cited_by_count":6,"area":null},{"id":"2210.09556","title":"Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation","created":"2022-10-18","cited_by_count":6,"area":null},{"id":"2305.07731","title":"Predicting COVID-19 pandemic by spatio-temporal graph neural networks: A New Zealand's study","created":"2023-05-12","cited_by_count":6,"area":null},{"id":"2408.07978","title":"Coupling without Communication and Drafter-Invariant Speculative Decoding","created":"2024-08-15","cited_by_count":6,"area":null},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2104.04692","title":"Not All Attention Is All You Need","created":"2021-04-10","cited_by_count":5,"area":null},{"id":"2203.01629","title":"Learning Group Importance using the Differentiable Hypergeometric Distribution","created":"2022-03-03","cited_by_count":5,"area":null},{"id":"2402.08514","title":"Counterfactual Influence in Markov Decision Processes","created":"2024-02-13","cited_by_count":5,"area":null},{"id":"2501.10814","title":"No More Sliding Window: Efficient 3D Medical Image Segmentation with Differentiable Top-k Patch Sampling","created":"2025-01-18","cited_by_count":5,"area":null},{"id":"2509.08383","title":"Efficient Decoding Methods for Language Models on Encrypted Data","created":"2025-09-10","cited_by_count":5,"area":null},{"id":"2510.03944","title":"On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2607.08400","title":"TRACE: A Two-Channel Robust Attribution Watermark via Complementary Embeddings for LLM-Agent Trajectories","created":"2026-07-09","cited_by_count":5,"area":"agents"},{"id":"2101.11353","title":"Variational Nested Dropout","created":"2021-01-27","cited_by_count":4,"area":null},{"id":"2104.04000","title":"Software/Hardware Co-design for Multi-modal Multi-task Learning in Autonomous Systems","created":"2021-04-08","cited_by_count":4,"area":null},{"id":"2201.09522","title":"Accelerated Intravascular Ultrasound Imaging using Deep Reinforcement Learning","created":"2022-01-24","cited_by_count":4,"area":null},{"id":"2204.07023","title":"Composite Code Sparse Autoencoders for first stage retrieval","created":"2022-04-14","cited_by_count":4,"area":"mechinterp"},{"id":"2204.13765","title":"Probabilistic Permutation Graph Search: Black-Box Optimization for Fairness in Ranking","created":"2022-04-28","cited_by_count":4,"area":null},{"id":"2405.04363","title":"Some Notes on the Sample Complexity of Approximate Channel Simulation","created":"2024-05-07","cited_by_count":4,"area":null},{"id":"2405.12203","title":"Accelerating Relative Entropy Coding with Space Partitioning","created":"2024-05-20","cited_by_count":4,"area":null},{"id":"2105.09856","title":"High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling","created":"2021-05-20","cited_by_count":3,"area":null},{"id":"2109.08512","title":"Soft Actor-Critic With Integer Actions","created":"2021-09-17","cited_by_count":3,"area":null},{"id":"2111.09029","title":"Towards Interpretable and Reliable Reading Comprehension: A Pipeline Model with Unanswerability Prediction","created":"2021-11-17","cited_by_count":3,"area":null},{"id":"2207.10017","title":"Predictive Object-Centric Process Monitoring","created":"2022-07-20","cited_by_count":3,"area":null},{"id":"2208.05482","title":"Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables","created":"2022-08-10","cited_by_count":3,"area":null},{"id":"2309.03508","title":"Dynamic Frame Interpolation in Wavelet Domain","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2404.07351","title":"A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videos","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2506.15975","title":"Multi-use LLM Watermarking and the False Detection Problem","created":"2025-06-19","cited_by_count":3,"area":"safety"},{"id":"2603.15854","title":"FlashSampling: Fast and Memory-Efficient Exact Sampling","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2607.06763","title":"Trees from Marginals: Autoregressive drafting with factorized priors","created":"2026-07-07","cited_by_count":3,"area":"inference"},{"id":"2105.08643","title":"ASM2TV: An Adaptive Semi-Supervised Multi-Task Multi-View Learning Framework for Human Activity Recognition","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2111.02569","title":"RT-RCG: Neural Network and Accelerator Search Towards Effective and Real-time ECG Reconstruction from Intracardiac Electrograms","created":"2021-11-04","cited_by_count":2,"area":null},{"id":"2201.00490","title":"Learning with Latent Structures in Natural Language Processing: A Survey","created":"2022-01-03","cited_by_count":2,"area":null},{"id":"2208.07818","title":"Training Latent Variable Models with Auto-encoding Variational Bayes: A Tutorial","created":"2022-08-16","cited_by_count":2,"area":null},{"id":"2406.07812","title":"To be Continuous, or to be Discrete, Those are Bits of Questions","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2410.08207","title":"DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models","created":"2024-10-10","cited_by_count":2,"area":"diffusion"},{"id":"2506.02946","title":"Abstract Counterfactuals for Language Model Agents","created":"2025-06-03","cited_by_count":2,"area":"agents"},{"id":"2602.19775","title":"Exact Discrete Stochastic Simulation with Deep-Learning-Scale Gradient Optimization","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2603.10302","title":"How to make the most of your masked language model for protein engineering","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2606.08357","title":"Forward-Free Diffusion Language Models with BPTT-Free Looped Refinement","created":"2026-06-06","cited_by_count":2,"area":"diffusion"},{"id":"2607.29684","title":"Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark","created":"2026-07-31","cited_by_count":2,"area":null},{"id":"2609.17691","title":"Accelerating Diffusion Sampling via Speculative Draft Trees","created":"2026-09-15","cited_by_count":2,"area":"diffusion"}],"next_cursor":"100"}