{"total":1033,"rows":[{"id":"2405.14734","title":"SimPO: Simple Preference Optimization with a Reference-Free Reward","created":"2024-05-23","cited_by_count":963,"area":"alignment"},{"id":"2306.01708","title":"TIES-Merging: Resolving Interference When Merging Models","created":"2023-06-02","cited_by_count":818,"area":null},{"id":"2501.09732","title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","created":"2025-01-16","cited_by_count":234,"area":"lr"},{"id":"2206.09426","title":"ADBench: Anomaly Detection Benchmark","created":"2022-06-19","cited_by_count":232,"area":null},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179,"area":null},{"id":"2110.11773","title":"Sinkformers: Transformers with Doubly Stochastic Attention","created":"2021-10-22","cited_by_count":138,"area":null},{"id":"2306.09782","title":"Full Parameter Fine-tuning for Large Language Models with Limited Resources","created":"2023-06-16","cited_by_count":134,"area":null},{"id":"2104.12325","title":"Efficient training of physics-informed neural networks via importance sampling","created":"2021-04-26","cited_by_count":110,"area":null},{"id":"2204.05255","title":"Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information","created":"2022-04-11","cited_by_count":103,"area":null},{"id":"2203.11834","title":"Improving Generalization in Federated Learning by Seeking Flat Minima","created":"2022-03-22","cited_by_count":98,"area":null},{"id":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90,"area":null},{"id":"2110.13100","title":"Parameter Prediction for Unseen Deep Architectures","created":"2021-10-25","cited_by_count":89,"area":null},{"id":"2210.00875","title":"Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection","created":"2022-09-27","cited_by_count":86,"area":null},{"id":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81,"area":null},{"id":"2410.01463","title":"Selective Aggregation for Low-Rank Adaptation in Federated Learning","created":"2024-10-02","cited_by_count":80,"area":null},{"id":"2109.05211","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","created":"2021-09-11","cited_by_count":79,"area":null},{"id":"2208.03111","title":"Data-free Backdoor Removal based on Channel Lipschitzness","created":"2022-08-05","cited_by_count":79,"area":null},{"id":"2208.06102","title":"Zeus: Understanding and Optimizing GPU Energy Consumption of DNN Training","created":"2022-08-12","cited_by_count":79,"area":null},{"id":"2403.13117","title":"Optimal Flow Matching: Learning Straight Trajectories in Just One Step","created":"2024-03-19","cited_by_count":78,"area":"diffusion"},{"id":"2105.08059","title":"Unsupervised MRI Reconstruction via Zero-Shot Learned Adversarial Transformers","created":"2021-05-15","cited_by_count":77,"area":null},{"id":"2303.11313","title":"CLIP goes 3D: Leveraging Prompt Tuning for Language Grounded 3D Recognition","created":"2023-03-20","cited_by_count":77,"area":"mllm"},{"id":"2207.09238","title":"Formal Algorithms for Transformers","created":"2022-07-19","cited_by_count":72,"area":null},{"id":"2203.16209","title":"Fair Contrastive Learning for Facial Attribute Classification","created":"2022-03-30","cited_by_count":71,"area":null},{"id":"2301.04545","title":"AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers","created":"2023-01-11","cited_by_count":67,"area":null},{"id":"2305.16037","title":"GenerateCT: Text-Conditional Generation of 3D Chest CT Volumes","created":"2023-05-25","cited_by_count":64,"area":"diffusion"},{"id":"2104.07715","title":"Quantum Architecture Search via Deep Reinforcement Learning","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2312.02902","title":"HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting","created":"2023-12-05","cited_by_count":60,"area":null},{"id":"2602.20133","title":"AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization","created":"2026-02-23","cited_by_count":60,"area":null},{"id":"2204.13207","title":"Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework","created":"2022-04-27","cited_by_count":59,"area":null},{"id":"2201.09679","title":"A Review of Deep Transfer Learning and Recent Advancements","created":"2022-01-19","cited_by_count":57,"area":null},{"id":"2409.03137","title":"The AdEMAMix Optimizer: Better, Faster, Older","created":"2024-09-05","cited_by_count":54,"area":null},{"id":"2203.03972","title":"GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality","created":"2022-03-08","cited_by_count":52,"area":null},{"id":"2511.06449","title":"FLEX: Continuous Agent Evolution via Forward Learning from Experience","created":"2025-11-09","cited_by_count":52,"area":"lr"},{"id":"2101.08747","title":"Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs","created":"2021-01-21","cited_by_count":51,"area":null},{"id":"2105.07561","title":"Layerwise Optimization by Gradient Decomposition for Continual Learning","created":"2021-05-17","cited_by_count":51,"area":null},{"id":"2107.07201","title":"Neighbor-view Enhanced Model for Vision and Language Navigation","created":"2021-07-15","cited_by_count":50,"area":null},{"id":"2112.09686","title":"Efficient Visual Tracking with Exemplar Transformers","created":"2021-12-17","cited_by_count":48,"area":null},{"id":"2402.11359","title":"Offline Training of Language Model Agents with Functions as Learnable Weights","created":"2024-02-17","cited_by_count":48,"area":"agents"},{"id":"2406.08705","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search","created":"2024-06-13","cited_by_count":47,"area":"safety"},{"id":"2304.11846","title":"Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions","created":"2023-04-24","cited_by_count":43,"area":null},{"id":"2410.04350","title":"TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights","created":"2024-10-06","cited_by_count":42,"area":"alignment"},{"id":"2301.00437","title":"Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data","created":"2023-01-01","cited_by_count":40,"area":null},{"id":"2310.13283","title":"pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning","created":"2023-10-20","cited_by_count":40,"area":null},{"id":"2308.06879","title":"Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization","created":"2023-08-14","cited_by_count":39,"area":null},{"id":"2403.05286","title":"LLM4Decompile: Decompiling Binary Code with Large Language Models","created":"2024-03-08","cited_by_count":39,"area":null},{"id":"2404.09451","title":"Contrastive Mean-Shift Learning for Generalized Category Discovery","created":"2024-04-15","cited_by_count":39,"area":null},{"id":"2102.07870","title":"Momentum Residual Neural Networks","created":"2021-02-15","cited_by_count":37,"area":null},{"id":"2106.07032","title":"Category Theory in Machine Learning","created":"2021-06-13","cited_by_count":36,"area":null},{"id":"2110.05922","title":"Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)","created":"2021-10-12","cited_by_count":35,"area":null},{"id":"2306.06569","title":"Policy Regularization with Dataset Constraint for Offline Reinforcement Learning","created":"2023-06-11","cited_by_count":34,"area":"offlinerl"},{"id":"2310.10776","title":"Correcting model misspecification in physics-informed neural networks (PINNs)","created":"2023-10-16","cited_by_count":33,"area":null},{"id":"2101.10861","title":"A Review on Deep Learning in UAV Remote Sensing","created":"2021-01-22","cited_by_count":32,"area":null},{"id":"2203.11860","title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","created":"2022-03-22","cited_by_count":32,"area":null},{"id":"2311.11501","title":"MultiLoRA: Democratizing LoRA for Better Multi-Task Learning","created":"2023-11-20","cited_by_count":32,"area":null},{"id":"2409.18153","title":"Most Influential Subset Selection: Challenges, Promises, and Beyond","created":"2024-09-25","cited_by_count":32,"area":null},{"id":"2103.06232","title":"Quantum machine learning with differential privacy","created":"2021-03-10","cited_by_count":31,"area":null},{"id":"2306.04815","title":"Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning","created":"2023-06-07","cited_by_count":31,"area":null},{"id":"2309.01020","title":"On the training and generalization of deep operator networks","created":"2023-09-02","cited_by_count":31,"area":null},{"id":"2310.10195","title":"AdaLomo: Low-memory Optimization with Adaptive Learning Rate","created":"2023-10-16","cited_by_count":31,"area":null},{"id":"2203.04279","title":"Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences","created":"2022-03-08","cited_by_count":30,"area":null},{"id":"2311.04902","title":"Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models","created":"2023-11-08","cited_by_count":30,"area":null},{"id":"2103.12531","title":"CLIP: Cheap Lipschitz Training of Neural Networks","created":"2021-03-23","cited_by_count":29,"area":null},{"id":"2205.04749","title":"Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild","created":"2022-05-10","cited_by_count":29,"area":null},{"id":"2304.05818","title":"Gradient-Free Textual Inversion","created":"2023-04-12","cited_by_count":29,"area":null},{"id":"2402.04823","title":"How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data","created":"2024-02-07","cited_by_count":29,"area":null},{"id":"2108.09373","title":"Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training","created":"2021-08-20","cited_by_count":28,"area":null},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28,"area":null},{"id":"2303.13325","title":"DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices","created":"2023-03-23","cited_by_count":28,"area":null},{"id":"2408.00483","title":"A Systematic Review on Long-Tailed Learning","created":"2024-08-01","cited_by_count":28,"area":null},{"id":"2202.04736","title":"Coarsening the Granularity: Towards Structurally Sparse Lottery Tickets","created":"2022-02-09","cited_by_count":27,"area":null},{"id":"2212.05709","title":"HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Design","created":"2022-12-12","cited_by_count":27,"area":null},{"id":"2306.11589","title":"Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent","created":"2023-06-20","cited_by_count":27,"area":null},{"id":"2101.11948","title":"Choice modelling in the age of machine learning -- discussion paper","created":"2021-01-28","cited_by_count":26,"area":null},{"id":"2112.02548","title":"Generative Modeling of Turbulence","created":"2021-12-05","cited_by_count":26,"area":null},{"id":"2204.10549","title":"JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction","created":"2022-04-22","cited_by_count":26,"area":null},{"id":"2204.12965","title":"Particle algorithms for maximum likelihood training of latent variable models","created":"2022-04-27","cited_by_count":26,"area":null},{"id":"2206.12395","title":"Data Leakage in Federated Averaging","created":"2022-06-24","cited_by_count":26,"area":null},{"id":"2305.11252","title":"Brain-inspired learning in artificial neural networks: a review","created":"2023-05-18","cited_by_count":26,"area":null},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26,"area":null},{"id":"2503.04992","title":"Wanda++: Pruning Large Language Models via Regional Gradients","created":"2025-03-06","cited_by_count":26,"area":"inference"},{"id":"2207.09812","title":"The Anatomy of Video Editing: A Dataset and Benchmark Suite for AI-Assisted Video Editing","created":"2022-07-20","cited_by_count":25,"area":null},{"id":"2107.02248","title":"A comparison of LSTM and GRU networks for learning symbolic sequences","created":"2021-07-05","cited_by_count":24,"area":null},{"id":"2107.04187","title":"A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognition","created":"2021-07-09","cited_by_count":24,"area":null},{"id":"2203.16462","title":"Convergence of gradient descent for deep neural networks","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2402.01350","title":"pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning","created":"2024-02-02","cited_by_count":24,"area":"moe"},{"id":"2406.00510","title":"Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection","created":"2024-06-01","cited_by_count":24,"area":null},{"id":"2411.00625","title":"Toward Automated Algorithm Design: A Survey and Practical Guide to Meta-Black-Box-Optimization","created":"2024-11-01","cited_by_count":24,"area":null},{"id":"2312.14126","title":"Entropic Open-set Active Learning","created":"2023-12-21","cited_by_count":23,"area":null},{"id":"2209.00355","title":"Gait Recognition in the Wild with Multi-hop Temporal Switch","created":"2022-09-01","cited_by_count":22,"area":null},{"id":"2308.03594","title":"FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision","created":"2023-08-07","cited_by_count":22,"area":null},{"id":"2406.05478","title":"Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis","created":"2024-06-08","cited_by_count":22,"area":"diffusion"},{"id":"2101.06189","title":"Hybrid Quantum-Classical Graph Convolutional Network","created":"2021-01-15","cited_by_count":21,"area":null},{"id":"2108.12006","title":"When and how epochwise double descent happens","created":"2021-08-26","cited_by_count":21,"area":null},{"id":"2111.01628","title":"Human Attention in Fine-grained Classification","created":"2021-11-02","cited_by_count":21,"area":null},{"id":"2204.02738","title":"Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network","created":"2022-04-06","cited_by_count":21,"area":null},{"id":"2210.12547","title":"SurCo: Learning Linear Surrogates For Combinatorial Nonlinear Optimization Problems","created":"2022-10-22","cited_by_count":21,"area":null},{"id":"2303.00565","title":"AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks","created":"2023-03-01","cited_by_count":21,"area":null},{"id":"2305.00666","title":"Part Aware Contrastive Learning for Self-Supervised Action Recognition","created":"2023-05-01","cited_by_count":21,"area":null},{"id":"2305.02424","title":"Backdoor Learning on Sequence to Sequence Models","created":"2023-05-03","cited_by_count":21,"area":null},{"id":"2308.09160","title":"FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning","created":"2023-08-17","cited_by_count":21,"area":null}],"next_cursor":"100"}