{"total":70,"rows":[{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329,"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":"2106.01798","title":"Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions","created":"2021-06-03","cited_by_count":98,"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":"2104.03059","title":"Differentiable Patch Selection for Image Recognition","created":"2021-04-07","cited_by_count":68,"area":null},{"id":"2312.13236","title":"Diffusion Models With Learned Adaptive Noise","created":"2023-12-20","cited_by_count":51,"area":"diffusion"},{"id":"2108.04657","title":"Differentiable Subset Pruning of Transformer Heads","created":"2021-08-10","cited_by_count":47,"area":null},{"id":"2410.11820","title":"Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws","created":"2024-10-15","cited_by_count":47,"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":"2205.15213","title":"Backpropagation through Combinatorial Algorithms: Identity with Projection Works","created":"2022-05-30","cited_by_count":29,"area":"lr"},{"id":"2205.15319","title":"AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning","created":"2022-05-30","cited_by_count":28,"area":null},{"id":"2310.02156","title":"Probabilistically Rewired Message-Passing Neural Networks","created":"2023-10-03","cited_by_count":26,"area":null},{"id":"2108.11883","title":"DSKReG: Differentiable Sampling on Knowledge Graph for Recommendation with Relational GNN","created":"2021-08-26","cited_by_count":19,"area":null},{"id":"2407.15047","title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling","created":"2024-07-21","cited_by_count":19,"area":null},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2306.09104","title":"On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation","created":"2023-06-15","cited_by_count":16,"area":null},{"id":"2503.16870","title":"Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMs","created":"2025-03-21","cited_by_count":16,"area":"distill"},{"id":"2302.10607","title":"Differentiable Multi-Target Causal Bayesian Experimental Design","created":"2023-02-21","cited_by_count":15,"area":null},{"id":"2405.17311","title":"Probabilistic Graph Rewiring via Virtual Nodes","created":"2024-05-27","cited_by_count":15,"area":null},{"id":"2209.04862","title":"Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models","created":"2022-09-11","cited_by_count":12,"area":null},{"id":"2203.10623","title":"Calibration of Machine Reading Systems at Scale","created":"2022-03-20","cited_by_count":11,"area":null},{"id":"2502.09443","title":"Relational Conformal Prediction for Correlated Time Series","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2202.02193","title":"Stochastic smoothing of the top-K calibrated hinge loss for deep imbalanced classification","created":"2022-02-04","cited_by_count":10,"area":null},{"id":"2504.10174","title":"LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification","created":"2025-04-14","cited_by_count":9,"area":null},{"id":"2102.00466","title":"Adversarial Contrastive Pre-training for Protein Sequences","created":"2021-01-31","cited_by_count":8,"area":null},{"id":"2110.15072","title":"Leveraging Recursive Gumbel-Max Trick for Approximate Inference in Combinatorial Spaces","created":"2021-10-28","cited_by_count":7,"area":null},{"id":"2407.18930","title":"Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2210.02159","title":"Differentiable Mathematical Programming for Object-Centric Representation Learning","created":"2022-10-05","cited_by_count":6,"area":null},{"id":"2105.12686","title":"Dynamic Probabilistic Pruning: A general framework for hardware-constrained pruning at different granularities","created":"2021-05-26","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":"2301.12277","title":"Node Injection for Class-specific Network Poisoning","created":"2023-01-28","cited_by_count":5,"area":null},{"id":"2505.18051","title":"LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision","created":"2025-05-23","cited_by_count":5,"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":"2303.06522","title":"Token Sparsification for Faster Medical Image Segmentation","created":"2023-03-11","cited_by_count":4,"area":"inference"},{"id":"2307.09296","title":"Rumor Detection with Diverse Counterfactual Evidence","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2503.13707","title":"Long-VMNet: Accelerating Long-Form Video Understanding via Fixed Memory","created":"2025-03-17","cited_by_count":4,"area":null},{"id":"2110.03218","title":"Joint optimization of system design and reconstruction in MIMO radar imaging","created":"2021-10-07","cited_by_count":3,"area":null},{"id":"2305.16841","title":"Differentiable Random Partition Models","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2306.10606","title":"Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces","created":"2023-06-18","cited_by_count":3,"area":null},{"id":"2402.05946","title":"Unveiling Latent Causal Rules: A Temporal Point Process Approach for Abnormal Event Explanation","created":"2024-02-03","cited_by_count":3,"area":null},{"id":"2607.29401","title":"OSEF: One-Step Evidence Fusion for Cross-Video Scene Procedure Planning","created":"2026-07-31","cited_by_count":3,"area":null},{"id":"2203.12873","title":"Weakly-Supervised End-to-End CAD Retrieval to Scan Objects","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2308.00549","title":"Copula for Instance-wise Feature Selection and Ranking","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2308.15614","title":"Everything Perturbed All at Once: Enabling Differentiable Graph Attacks","created":"2023-08-29","cited_by_count":2,"area":null},{"id":"2310.18827","title":"All Things Considered: Detecting Partisan Events from News Media with Cross-Article Comparison","created":"2023-10-28","cited_by_count":2,"area":null},{"id":"2502.11116","title":"Gumbel Reranking: Differentiable End-to-End Reranker Optimization","created":"2025-02-16","cited_by_count":2,"area":"rag"},{"id":"2207.14106","title":"MarkerMap: nonlinear marker selection for single-cell studies","created":"2022-07-28","cited_by_count":1,"area":null},{"id":"2212.03131","title":"Explainability as statistical inference","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2301.02275","title":"Language as a Latent Sequence: deep latent variable models for semi-supervised paraphrase generation","created":"2023-01-05","cited_by_count":1,"area":null},{"id":"2407.16058","title":"Revisiting Score Function Estimators for $k$-Subset Sampling","created":"2024-07-22","cited_by_count":1,"area":null},{"id":"2412.17338","title":"Enhancing Topic Interpretability for Neural Topic Modeling through Topic-wise Contrastive Learning","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2501.12592","title":"FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling","created":"2025-01-22","cited_by_count":1,"area":null},{"id":"2502.05416","title":"Deep Generative Models with Hard Linear Equality Constraints","created":"2025-02-08","cited_by_count":1,"area":null},{"id":"2502.07862","title":"ADMN: A Layer-Wise Adaptive Multimodal Network for Dynamic Input Noise and Compute Resources","created":"2025-02-11","cited_by_count":1,"area":null},{"id":"2508.11925","title":"Optimizing Token Choice for Code Watermarking: An RL Approach","created":"2025-08-16","cited_by_count":1,"area":"safety"},{"id":"2608.00053","title":"Fast Trainable Multilinear Bases for Image Compression","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2310.04159","title":"Amortized Network Intervention to Steer the Excitatory Point Processes","created":"2023-10-06","cited_by_count":0,"area":null},{"id":"2310.10772","title":"Unsupervised Lead Sheet Generation via Semantic Compression","created":"2023-10-16","cited_by_count":0,"area":null},{"id":"2405.16726","title":"Edge Probability Graph Models Beyond Edge Independency: Concepts, Analyses, and Algorithms","created":"2024-05-26","cited_by_count":0,"area":null},{"id":"2503.13304","title":"AutoNFS: Automatic Neural Feature Selection","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2601.18917","title":"GraIP: A Benchmarking Framework For Neural Graph Inverse Problems","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2601.22531","title":"Learn from A Rationalist: Distilling Intermediate Interpretable Rationales","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.25127","title":"PQDT: Pseudo-Query Dual Transformer for Robust Point Cloud Restoration","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2607.11146","title":"Rank-Conditioned Sample Reuse for the Plackett--Luce Best-of-$K$ Objective","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.17351","title":"DeeperRadar: End-to-End MIMO Radar Design and Multi-Modal Fusion for Autonomous Vehicle Perception","created":"2026-07-19","cited_by_count":0,"area":"driving"},{"id":"2608.04057","title":"LaPrune: Controllable Differentiable Sparsity at Million Scale","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.23048","title":"Reservoir of Importance: Learning Semi-Structured Sparsity with Differentiable Subset Sampling","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.03085","title":"Solving the Needle-in-a-Haystack Problem in Mammography Vision-Language Model with Differentiable Subset Sampling","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.18909","title":"Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2610.04017","title":"Slaying the Hydra: Interaction-Aware Circuit Discovery in Language Models","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}