{"total":264,"rows":[{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681,"area":null},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616,"area":null},{"id":"2106.07998","title":"Revisiting the Calibration of Modern Neural Networks","created":"2021-06-15","cited_by_count":390,"area":null},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183,"area":null},{"id":"2112.10684","title":"Efficient Large Scale Language Modeling with Mixtures of Experts","created":"2021-12-20","cited_by_count":175,"area":"moe"},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145,"area":null},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"area":"safety"},{"id":"2110.06914","title":"What Happens after SGD Reaches Zero Loss? --A Mathematical Framework","created":"2021-10-13","cited_by_count":107,"area":null},{"id":"2307.15337","title":"Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation","created":"2023-07-28","cited_by_count":105,"area":"lr"},{"id":"2205.10287","title":"On the SDEs and Scaling Rules for Adaptive Gradient Algorithms","created":"2022-05-20","cited_by_count":104,"area":null},{"id":"2211.07740","title":"Denoising diffusion models for out-of-distribution detection","created":"2022-11-14","cited_by_count":104,"area":"diffusion"},{"id":"2411.02265","title":"Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent","created":"2024-11-04","cited_by_count":90,"area":"moe"},{"id":"2108.02385","title":"ACE: Ally Complementary Experts for Solving Long-Tailed Recognition in One-Shot","created":"2021-08-05","cited_by_count":86,"area":null},{"id":"2102.07988","title":"TeraPipe: Token-Level Pipeline Parallelism for Training Large-Scale Language Models","created":"2021-02-16","cited_by_count":75,"area":null},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75,"area":null},{"id":"2106.07820","title":"On Large-Cohort Training for Federated Learning","created":"2021-06-15","cited_by_count":74,"area":null},{"id":"2211.01201","title":"Human alignment of neural network representations","created":"2022-11-02","cited_by_count":74,"area":null},{"id":"2102.12470","title":"On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs)","created":"2021-02-24","cited_by_count":73,"area":null},{"id":"2107.06925","title":"Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines","created":"2021-07-14","cited_by_count":68,"area":null},{"id":"2306.15969","title":"Separable Physics-Informed Neural Networks","created":"2023-06-28","cited_by_count":66,"area":null},{"id":"2304.03322","title":"Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models","created":"2023-04-06","cited_by_count":61,"area":"diffusion"},{"id":"2301.11913","title":"SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient","created":"2023-01-27","cited_by_count":59,"area":null},{"id":"2206.10654","title":"On the Maximum Hessian Eigenvalue and Generalization","created":"2022-06-21","cited_by_count":57,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2105.11118","title":"Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads","created":"2021-05-24","cited_by_count":51,"area":null},{"id":"2204.12013","title":"Bamboo: Making Preemptible Instances Resilient for Affordable Training of Large DNNs","created":"2022-04-26","cited_by_count":49,"area":null},{"id":"2205.10683","title":"Scalable and Efficient Training of Large Convolutional Neural Networks with Differential Privacy","created":"2022-05-21","cited_by_count":48,"area":null},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2203.10983","title":"BNS-GCN: Efficient Full-Graph Training of Graph Convolutional Networks with Partition-Parallelism and Random Boundary Node Sampling","created":"2022-03-21","cited_by_count":43,"area":null},{"id":"2505.13738","title":"Power Lines: Scaling Laws for Weight Decay and Batch Size in LLM Pre-training","created":"2025-05-19","cited_by_count":43,"area":null},{"id":"2312.08361","title":"Distributed Inference and Fine-tuning of Large Language Models Over The Internet","created":"2023-12-13","cited_by_count":42,"area":null},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2306.04507","title":"Improving neural network representations using human similarity judgments","created":"2023-06-07","cited_by_count":38,"area":null},{"id":"2201.11736","title":"Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives","created":"2022-01-27","cited_by_count":37,"area":null},{"id":"2306.03241","title":"Early Weight Averaging meets High Learning Rates for LLM Pre-training","created":"2023-06-05","cited_by_count":37,"area":null},{"id":"2301.03198","title":"The Algonauts Project 2023 Challenge: How the Human Brain Makes Sense of Natural Scenes","created":"2023-01-09","cited_by_count":36,"area":null},{"id":"2410.16770","title":"The Scene Language: Representing Scenes with Programs, Words, and Embeddings","created":"2024-10-22","cited_by_count":36,"area":null},{"id":"2502.15938","title":"Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs","created":"2025-02-21","cited_by_count":35,"area":null},{"id":"2402.11139","title":"LiGNN: Graph Neural Networks at LinkedIn","created":"2024-02-17","cited_by_count":31,"area":null},{"id":"2205.09702","title":"Parallel and Distributed Graph Neural Networks: An In-Depth Concurrency Analysis","created":"2022-05-19","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":"2303.01215","title":"Why (and When) does Local SGD Generalize Better than SGD?","created":"2023-03-02","cited_by_count":26,"area":null},{"id":"2101.05471","title":"Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration","created":"2021-01-14","cited_by_count":25,"area":null},{"id":"2510.01180","title":"BroRL: Scaling Reinforcement Learning via Broadened Exploration","created":"2025-10-01","cited_by_count":25,"area":"lr"},{"id":"2102.10809","title":"Local Calibration: Metrics and Recalibration","created":"2021-02-22","cited_by_count":24,"area":null},{"id":"2307.13813","title":"How to Scale Your EMA","created":"2023-07-25","cited_by_count":24,"area":null},{"id":"2112.05929","title":"Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning","created":"2021-12-11","cited_by_count":23,"area":null},{"id":"2302.02573","title":"Topology-aware Federated Learning in Edge Computing: A Comprehensive Survey","created":"2023-02-06","cited_by_count":23,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2211.11153","title":"Unifying Vision-Language Representation Space with Single-tower Transformer","created":"2022-11-21","cited_by_count":22,"area":null},{"id":"2405.14578","title":"Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling","created":"2024-05-23","cited_by_count":22,"area":null},{"id":"2103.16940","title":"Learning with Memory-based Virtual Classes for Deep Metric Learning","created":"2021-03-31","cited_by_count":21,"area":null},{"id":"2211.11092","title":"Q-Ensemble for Offline RL: Don't Scale the Ensemble, Scale the Batch Size","created":"2022-11-20","cited_by_count":21,"area":"offlinerl"},{"id":"2312.05386","title":"Model Extraction Attacks Revisited","created":"2023-12-08","cited_by_count":21,"area":null},{"id":"2201.12023","title":"Alpa: Automating Inter- and Intra-Operator Parallelism for Distributed Deep Learning","created":"2022-01-28","cited_by_count":20,"area":null},{"id":"2306.10015","title":"Just One Byte (per gradient): A Note on Low-Bandwidth Decentralized Language Model Finetuning Using Shared Randomness","created":"2023-06-16","cited_by_count":18,"area":null},{"id":"2211.09771","title":"Boosting Object Representation Learning via Motion and Object Continuity","created":"2022-11-16","cited_by_count":17,"area":null},{"id":"2103.02695","title":"Shift Invariance Can Reduce Adversarial Robustness","created":"2021-03-03","cited_by_count":16,"area":null},{"id":"2305.18169","title":"LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning","created":"2023-05-29","cited_by_count":16,"area":null},{"id":"2406.11836","title":"RetinaGS: Scalable Training for Dense Scene Rendering with Billion-Scale 3D Gaussians","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2201.11865","title":"FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clients","created":"2022-01-28","cited_by_count":15,"area":null},{"id":"2301.09830","title":"Optimus-CC: Efficient Large NLP Model Training with 3D Parallelism Aware Communication Compression","created":"2023-01-24","cited_by_count":15,"area":null},{"id":"2306.02913","title":"Decentralized SGD and Average-direction SAM are Asymptotically Equivalent","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2403.06664","title":"Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System","created":"2024-03-11","cited_by_count":15,"area":null},{"id":"2412.04508","title":"Video Quality Assessment: A Comprehensive Survey","created":"2024-12-04","cited_by_count":15,"area":null},{"id":"2502.04327","title":"Value-Based Deep RL Scales Predictably","created":"2025-02-06","cited_by_count":15,"area":"deeprl"},{"id":"2105.10762","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","created":"2021-05-22","cited_by_count":14,"area":null},{"id":"2205.14657","title":"COFS: Controllable Furniture layout Synthesis","created":"2022-05-29","cited_by_count":14,"area":null},{"id":"2309.12821","title":"A Spectral Theory of Neural Prediction and Alignment","created":"2023-09-22","cited_by_count":14,"area":null},{"id":"2402.02791","title":"PanGu-$\\pi$ Pro:Rethinking Optimization and Architecture for Tiny Language Models","created":"2024-02-05","cited_by_count":14,"area":"lr"},{"id":"2405.14009","title":"ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation","created":"2024-05-22","cited_by_count":14,"area":null},{"id":"2110.14769","title":"Detecting Dementia from Speech and Transcripts using Transformers","created":"2021-10-27","cited_by_count":13,"area":null},{"id":"2202.11423","title":"Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions","created":"2022-02-23","cited_by_count":13,"area":null},{"id":"2406.17642","title":"Banishing LLM Hallucinations Requires Rethinking Generalization","created":"2024-06-25","cited_by_count":13,"area":"lr"},{"id":"2204.03772","title":"Multi-objective optimization determines when, which and how to fuse deep networks: an application to predict COVID-19 outcomes","created":"2022-04-07","cited_by_count":12,"area":null},{"id":"2211.10155","title":"Structured Pruning Adapters","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2307.15878","title":"Explaining Full-disk Deep Learning Model for Solar Flare Prediction using Attribution Methods","created":"2023-07-29","cited_by_count":12,"area":null},{"id":"2105.02315","title":"Scalable Graph Neural Network Training: The Case for Sampling","created":"2021-05-05","cited_by_count":11,"area":null},{"id":"2105.07371","title":"Expressive Explanations of DNNs by Combining Concept Analysis with ILP","created":"2021-05-16","cited_by_count":11,"area":null},{"id":"2209.01610","title":"Generalization in Neural Networks: A Broad Survey","created":"2022-09-04","cited_by_count":11,"area":null},{"id":"2302.04032","title":"A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions","created":"2023-02-08","cited_by_count":11,"area":null},{"id":"2406.07145","title":"Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models","created":"2024-06-11","cited_by_count":11,"area":null},{"id":"2602.17616","title":"Stable Asynchrony: Variance-Controlled Off-Policy RL for LLMs","created":"2026-02-19","cited_by_count":11,"area":null},{"id":"2102.06025","title":"Large-Scale Training System for 100-Million Classification at Alibaba","created":"2021-02-09","cited_by_count":10,"area":null},{"id":"2107.05855","title":"Automated Learning Rate Scheduler for Large-batch Training","created":"2021-07-13","cited_by_count":10,"area":null},{"id":"2111.00856","title":"Large-Scale Deep Learning Optimizations: A Comprehensive Survey","created":"2021-11-01","cited_by_count":10,"area":null},{"id":"2206.01102","title":"A temporal chrominance trigger for clean-label backdoor attack against anti-spoof rebroadcast detection","created":"2022-06-02","cited_by_count":10,"area":null},{"id":"2508.19529","title":"Blockwise SFT for Diffusion Language Models: Reconciling Bidirectional Attention and Autoregressive Decoding","created":"2025-08-27","cited_by_count":10,"area":"diffusion"},{"id":"2105.06727","title":"Verification of Size Invariance in DNN Activations using Concept Embeddings","created":"2021-05-14","cited_by_count":9,"area":null},{"id":"2110.10165","title":"NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters","created":"2021-10-19","cited_by_count":9,"area":null},{"id":"2206.06257","title":"Distributed Adversarial Training to Robustify Deep Neural Networks at Scale","created":"2022-06-13","cited_by_count":9,"area":null},{"id":"2206.09265","title":"SAViR-T: Spatially Attentive Visual Reasoning with Transformers","created":"2022-06-18","cited_by_count":9,"area":"lr"},{"id":"2303.04393","title":"Imbalanced Open Set Domain Adaptation via Moving-threshold Estimation and Gradual Alignment","created":"2023-03-08","cited_by_count":9,"area":null},{"id":"2406.17145","title":"GraphPipe: Improving Performance and Scalability of DNN Training with Graph Pipeline Parallelism","created":"2024-06-24","cited_by_count":9,"area":null},{"id":"2407.04538","title":"PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers","created":"2024-07-05","cited_by_count":9,"area":null},{"id":"2501.08415","title":"Cross-Modal Transferable Image-to-Video Attack on Video Quality Metrics","created":"2025-01-14","cited_by_count":9,"area":null},{"id":"2305.00936","title":"Generating Texture for 3D Human Avatar from a Single Image using Sampling and Refinement Networks","created":"2023-05-01","cited_by_count":8,"area":null},{"id":"2402.09050","title":"End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training","created":"2024-02-14","cited_by_count":8,"area":null},{"id":"2406.10743","title":"Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?","created":"2024-06-15","cited_by_count":8,"area":null},{"id":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"}],"next_cursor":"100"}