{"total":174,"rows":[{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2211.10658","title":"EDGE: Editable Dance Generation From Music","created":"2022-11-19","cited_by_count":287,"area":null},{"id":"2303.14389","title":"MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer","created":"2023-03-25","cited_by_count":262,"area":"lr"},{"id":"2402.02544","title":"LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model","created":"2024-02-04","cited_by_count":138,"area":"mllm"},{"id":"2408.00761","title":"Tamper-Resistant Safeguards for Open-Weight LLMs","created":"2024-08-01","cited_by_count":138,"area":"safety"},{"id":"2406.16793","title":"Adam-mini: Use Fewer Learning Rates To Gain More","created":"2024-06-24","cited_by_count":137,"area":null},{"id":"2403.08551","title":"GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting","created":"2024-03-13","cited_by_count":99,"area":null},{"id":"2310.02994","title":"Multiple Physics Pretraining for Physical Surrogate Models","created":"2023-10-04","cited_by_count":98,"area":null},{"id":"2506.15054","title":"Muon Optimizes Under Spectral Norm Constraints","created":"2025-06-18","cited_by_count":86,"area":null},{"id":"2411.10438","title":"MARS: Unleashing the Power of Variance Reduction for Training Large Models","created":"2024-11-15","cited_by_count":64,"area":null},{"id":"2403.10518","title":"Lodge: A Coarse to Fine Diffusion Network for Long Dance Generation Guided by the Characteristic Dance Primitives","created":"2024-03-15","cited_by_count":61,"area":null},{"id":"2401.09050","title":"Consistent3D: Towards Consistent High-Fidelity Text-to-3D Generation with Deterministic Sampling Prior","created":"2024-01-17","cited_by_count":60,"area":null},{"id":"2306.10619","title":"Towards Stability of Autoregressive Neural Operators","created":"2023-06-18","cited_by_count":59,"area":null},{"id":"2404.10343","title":"The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report","created":"2024-04-16","cited_by_count":57,"area":null},{"id":"2403.12350","title":"Friendly Sharpness-Aware Minimization","created":"2024-03-19","cited_by_count":53,"area":null},{"id":"2305.08386","title":"PLIP: Language-Image Pre-training for Person Representation Learning","created":"2023-05-15","cited_by_count":49,"area":null},{"id":"2304.09670","title":"CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding","created":"2023-04-19","cited_by_count":48,"area":null},{"id":"2411.16085","title":"Cautious Optimizers: Improving Training with One Line of Code","created":"2024-11-25","cited_by_count":47,"area":null},{"id":"2301.01100","title":"Understanding Imbalanced Semantic Segmentation Through Neural Collapse","created":"2023-01-03","cited_by_count":46,"area":null},{"id":"2304.06544","title":"DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos","created":"2023-04-13","cited_by_count":42,"area":null},{"id":"2411.19509","title":"Ditto: Motion-Space Diffusion for Controllable Realtime Talking Head Synthesis","created":"2024-11-29","cited_by_count":41,"area":"diffusion"},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2310.17998","title":"Closing the Gap Between the Upper Bound and the Lower Bound of Adam's Iteration Complexity","created":"2023-10-27","cited_by_count":38,"area":null},{"id":"2410.16103","title":"LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics","created":"2024-10-21","cited_by_count":38,"area":null},{"id":"2404.01862","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","created":"2024-04-02","cited_by_count":35,"area":"diffusion"},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31,"area":null},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31,"area":null},{"id":"2502.19002","title":"The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training","created":"2025-02-26","cited_by_count":30,"area":null},{"id":"2402.18152","title":"Boosting Neural Representations for Videos with a Conditional Decoder","created":"2024-02-28","cited_by_count":29,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","cited_by_count":26,"area":null},{"id":"2504.10686","title":"The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report","created":"2025-04-14","cited_by_count":26,"area":null},{"id":"2403.15679","title":"DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes","created":"2024-03-23","cited_by_count":25,"area":null},{"id":"2305.12475","title":"Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods","created":"2023-05-21","cited_by_count":23,"area":null},{"id":"2307.04787","title":"Collaborative Score Distillation for Consistent Visual Synthesis","created":"2023-07-04","cited_by_count":23,"area":"diffusion"},{"id":"2410.03730","title":"Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs","created":"2024-09-30","cited_by_count":22,"area":null},{"id":"2404.04562","title":"Diffusion Time-step Curriculum for One Image to 3D Generation","created":"2024-04-06","cited_by_count":21,"area":null},{"id":"2410.20389","title":"Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patterns","created":"2024-10-27","cited_by_count":21,"area":null},{"id":"2504.19496","title":"DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction","created":"2025-04-28","cited_by_count":21,"area":null},{"id":"2311.00941","title":"Gaussian Mixture Solvers for Diffusion Models","created":"2023-11-02","cited_by_count":18,"area":"diffusion"},{"id":"2309.13646","title":"ILNet: Low-level Matters for Salient Infrared Small Target Detection","created":"2023-09-24","cited_by_count":17,"area":null},{"id":"2409.19128","title":"Pruning then Reweighting: Towards Data-Efficient Training of Diffusion Models","created":"2024-09-27","cited_by_count":17,"area":"diffusion"},{"id":"2603.28254","title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","created":"2026-03-30","cited_by_count":17,"area":null},{"id":"2406.04322","title":"DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data","created":"2024-06-06","cited_by_count":15,"area":"diffusion"},{"id":"2405.20763","title":"Improving Generalization and Convergence by Enhancing Implicit Regularization","created":"2024-05-31","cited_by_count":14,"area":null},{"id":"2501.04782","title":"GaussianVideo: Efficient Video Representation via Hierarchical Gaussian Splatting","created":"2025-01-08","cited_by_count":13,"area":null},{"id":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2310.05375","title":"IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Prompts","created":"2023-10-09","cited_by_count":11,"area":"diffusion"},{"id":"2411.07724","title":"Convergence Rate Analysis of LION","created":"2024-11-12","cited_by_count":11,"area":null},{"id":"2403.19144","title":"MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation","created":"2024-03-28","cited_by_count":10,"area":"diffusion"},{"id":"2309.14600","title":"Progressive Text-to-3D Generation for Automatic 3D Prototyping","created":"2023-09-26","cited_by_count":9,"area":null},{"id":"2402.09240","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","created":"2024-02-14","cited_by_count":9,"area":null},{"id":"2407.14340","title":"Large Kernel Distillation Network for Efficient Single Image Super-Resolution","created":"2024-07-19","cited_by_count":9,"area":null},{"id":"2410.02130","title":"MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generation","created":"2024-10-03","cited_by_count":9,"area":"diffusion"},{"id":"2503.15029","title":"DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modeling","created":"2025-03-19","cited_by_count":9,"area":null},{"id":"2602.04669","title":"Delving into Muon and Beyond: Deep Analysis and Extensions","created":"2026-02-04","cited_by_count":9,"area":null},{"id":"2310.14809","title":"Learning spatio-temporal patterns with Neural Cellular Automata","created":"2023-10-23","cited_by_count":8,"area":null},{"id":"2403.13667","title":"DanceCamera3D: 3D Camera Movement Synthesis with Music and Dance","created":"2024-03-20","cited_by_count":8,"area":null},{"id":"2410.09841","title":"Symmetry Discovery for Different Data Types","created":"2024-10-13","cited_by_count":8,"area":null},{"id":"2503.04333","title":"GaussianVideo: Efficient Video Representation and Compression by Gaussian Splatting","created":"2025-03-06","cited_by_count":8,"area":null},{"id":"2505.11840","title":"On the $O(\\frac{\\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\\ell_1$ Norm","created":"2025-05-17","cited_by_count":8,"area":null},{"id":"2505.24275","title":"GradPower: Powering Gradients for Faster Language Model Pre-Training","created":"2025-05-30","cited_by_count":8,"area":null},{"id":"2510.15830","title":"SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients","created":"2025-10-17","cited_by_count":8,"area":null},{"id":"2602.22681","title":"Accelerating LLM Pre-Training through Flat-Direction Dynamics Enhancement","created":"2026-02-26","cited_by_count":8,"area":null},{"id":"2312.07971","title":"LMD: Faster Image Reconstruction with Latent Masking Diffusion","created":"2023-12-13","cited_by_count":7,"area":"diffusion"},{"id":"2501.12060","title":"GSVC: Efficient Video Representation and Compression Through 2D Gaussian Splatting","created":"2025-01-21","cited_by_count":7,"area":null},{"id":"2512.16598","title":"Muon is Provably Faster with Momentum Variance Reduction","created":"2025-12-18","cited_by_count":7,"area":null},{"id":"2404.12386","title":"SOHES: Self-supervised Open-world Hierarchical Entity Segmentation","created":"2024-04-18","cited_by_count":6,"area":null},{"id":"2407.04480","title":"LoCo: Low-Bit Communication Adaptor for Large-scale Model Training","created":"2024-07-05","cited_by_count":6,"area":null},{"id":"2410.01591","title":"Imaging foundation model for universal enhancement of non-ideal measurement CT","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2510.01855","title":"Explicit Discovery of Nonlinear Symmetries from Dynamic Data","created":"2025-10-02","cited_by_count":6,"area":null},{"id":"2409.01522","title":"Lagrangian Motion Fields for Long-term Motion Generation","created":"2024-09-03","cited_by_count":5,"area":null},{"id":"2410.05140","title":"Tuning-Free Bilevel Optimization: New Algorithms and Convergence Analysis","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2410.23788","title":"EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching","created":"2024-10-31","cited_by_count":5,"area":"diffusion"},{"id":"2505.10930","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2507.08472","title":"Pre-Training LLMs on a budget: A comparison of three optimizers","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2509.24218","title":"Conda: Column-Normalized Adam for Training Large Language Models Faster","created":"2025-09-29","cited_by_count":5,"area":null},{"id":"2604.15297","title":"Benchmarking Optimizers for MLPs in Tabular Deep Learning","created":"2026-04-16","cited_by_count":5,"area":null},{"id":"2605.03769","title":"Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer","created":"2026-05-05","cited_by_count":5,"area":null},{"id":"2311.02394","title":"NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications","created":"2023-11-04","cited_by_count":4,"area":null},{"id":"2405.10988","title":"Flow Score Distillation for Diverse Text-to-3D Generation","created":"2024-05-16","cited_by_count":4,"area":"diffusion"},{"id":"2410.00435","title":"Incorporating Arbitrary Matrix Group Equivariance into KANs","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2412.17107","title":"Grams: Gradient Descent with Adaptive Momentum Scaling","created":"2024-12-22","cited_by_count":4,"area":null},{"id":"2504.05248","title":"PINNverse: Accurate parameter estimation in differential equations from noisy data with constrained physics-informed neural networks","created":"2025-04-07","cited_by_count":4,"area":null},{"id":"2303.12992","title":"A Survey of Historical Learning: Learning Models with Learning History","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2312.00407","title":"CoLLiE: Collaborative Training of Large Language Models in an Efficient Way","created":"2023-12-01","cited_by_count":3,"area":null},{"id":"2408.06614","title":"ViMo: Generating Motions from Casual Videos","created":"2024-08-13","cited_by_count":3,"area":null},{"id":"2410.06373","title":"Unveiling the Backbone-Optimizer Coupling Bias in Visual Representation Learning","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2410.08457","title":"Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2510.27153","title":"Exploring Landscapes for Better Minima along Valleys","created":"2025-10-31","cited_by_count":3,"area":null},{"id":"2604.07904","title":"Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2305.05675","title":"UAdam: Unified Adam-Type Algorithmic Framework for Non-Convex Stochastic Optimization","created":"2023-05-09","cited_by_count":2,"area":null},{"id":"2403.11791","title":"PAON: A New Neuron Model using Pad\\'e Approximants","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2406.13041","title":"Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2411.06685","title":"High-Frequency Enhanced Hybrid Neural Representation for Video Compression","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2412.10663","title":"Memory-Efficient 4-bit Preconditioned Stochastic Optimization","created":"2024-12-14","cited_by_count":2,"area":null},{"id":"2502.10784","title":"Preconditioned Inexact Stochastic ADMM for Deep Model","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2503.09576","title":"Manify: A Python Library for Learning Non-Euclidean Representations","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2504.12899","title":"Tree-NeRV: A Tree-Structured Neural Representation for Efficient Non-Uniform Video Encoding","created":"2025-04-17","cited_by_count":2,"area":null},{"id":"2505.23612","title":"Autoregressive Meta-Actions for Unified Controllable Trajectory Generation","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.04432","title":"KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products","created":"2025-06-04","cited_by_count":2,"area":null}],"next_cursor":"100"}