{"total":194,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723,"area":null},{"id":"2402.02592","title":"Unified Training of Universal Time Series Forecasting Transformers","created":"2024-02-04","cited_by_count":614,"area":null},{"id":"2203.08913","title":"Memorizing Transformers","created":"2022-03-16","cited_by_count":226,"area":null},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189,"area":null},{"id":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150,"area":null},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","cited_by_count":133,"area":null},{"id":"2602.04770","title":"Generative Modeling via Drifting","created":"2026-02-04","cited_by_count":116,"area":null},{"id":"2203.07852","title":"Block-Recurrent Transformers","created":"2022-03-11","cited_by_count":110,"area":null},{"id":"2503.15451","title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","created":"2025-03-19","cited_by_count":86,"area":null},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77,"area":null},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70,"area":null},{"id":"2410.03981","title":"A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languages","created":"2024-10-04","cited_by_count":66,"area":null},{"id":"2311.17132","title":"TransNeXt: Robust Foveal Visual Perception for Vision Transformers","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2604.12946","title":"Parcae: Scaling Laws For Stable Looped Language Models","created":"2026-04-14","cited_by_count":55,"area":null},{"id":"2506.07918","title":"CausalPFN: Amortized Causal Effect Estimation via In-Context Learning","created":"2025-06-09","cited_by_count":49,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46,"area":null},{"id":"2202.03670","title":"How to Understand Masked Autoencoders","created":"2022-02-08","cited_by_count":38,"area":null},{"id":"2312.17482","title":"MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining","created":"2023-12-29","cited_by_count":34,"area":null},{"id":"2404.14408","title":"SpaceByte: Towards Deleting Tokenization from Large Language Modeling","created":"2024-04-22","cited_by_count":34,"area":null},{"id":"2605.20119","title":"Toto 2.0: Time Series Forecasting Enters the Scaling Era","created":"2026-05-19","cited_by_count":30,"area":null},{"id":"2111.05498","title":"Attention Approximates Sparse Distributed Memory","created":"2021-11-10","cited_by_count":29,"area":null},{"id":"2505.19377","title":"Absolute Coordinates Make Motion Generation Easy","created":"2025-05-26","cited_by_count":29,"area":null},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28,"area":null},{"id":"2501.18512","title":"Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch","created":"2025-01-30","cited_by_count":28,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2512.22382","title":"Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration","created":"2025-12-26","cited_by_count":27,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2512.12167","title":"Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings","created":"2025-12-13","cited_by_count":26,"area":null},{"id":"2412.07730","title":"STIV: Scalable Text and Image Conditioned Video Generation","created":"2024-12-10","cited_by_count":25,"area":null},{"id":"2504.04011","title":"Foundation Models for Time Series: A Survey","created":"2025-04-05","cited_by_count":23,"area":null},{"id":"2505.21925","title":"RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination","created":"2025-05-28","cited_by_count":23,"area":null},{"id":"2512.16922","title":"Next-Embedding Prediction Makes Strong Vision Learners","created":"2025-12-18","cited_by_count":23,"area":null},{"id":"2402.17016","title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","created":"2024-02-26","cited_by_count":21,"area":null},{"id":"2512.16919","title":"DVGT: Driving Visual Geometry Transformer","created":"2025-12-18","cited_by_count":21,"area":null},{"id":"2601.22813","title":"Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation","created":"2026-01-30","cited_by_count":21,"area":null},{"id":"2507.13338","title":"Training Transformers with Enforced Lipschitz Constants","created":"2025-07-17","cited_by_count":20,"area":null},{"id":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2509.24200","title":"UniVid: The Open-Source Unified Video Model","created":"2025-09-29","cited_by_count":19,"area":null},{"id":"2501.18972","title":"BCAT: A Block Causal Transformer for PDE Foundation Models for Fluid Dynamics","created":"2025-01-31","cited_by_count":18,"area":null},{"id":"2601.22156","title":"Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts","created":"2026-01-29","cited_by_count":18,"area":null},{"id":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18,"area":null},{"id":"2603.09697","title":"Mousse: Rectifying the Geometry of Muon with Curvature-Aware Preconditioning","created":"2026-03-10","cited_by_count":17,"area":null},{"id":"2305.05179","title":"Simplicial Hopfield networks","created":"2023-05-09","cited_by_count":16,"area":null},{"id":"2502.00919","title":"Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings","created":"2025-02-02","cited_by_count":16,"area":null},{"id":"2503.04598","title":"HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization","created":"2025-03-06","cited_by_count":16,"area":null},{"id":"2606.16899","title":"Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization","created":"2026-06-15","cited_by_count":16,"area":null},{"id":"2604.15239","title":"TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens","created":"2026-04-16","cited_by_count":15,"area":null},{"id":"2505.08175","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","created":"2025-05-13","cited_by_count":14,"area":null},{"id":"2410.16682","title":"Methods of improving LLM training stability","created":"2024-10-22","cited_by_count":13,"area":null},{"id":"2505.18392","title":"Applications of Modular Co-Design for De Novo 3D Molecule Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2402.10644","title":"Linear Transformers with Learnable Kernel Functions are Better In-Context Models","created":"2024-02-16","cited_by_count":11,"area":null},{"id":"2502.12996","title":"Eager Updates For Overlapped Communication and Computation in DiLoCo","created":"2025-02-18","cited_by_count":11,"area":null},{"id":"2505.20524","title":"Towards Fully FP8 GEMM LLM Training at Scale","created":"2025-05-26","cited_by_count":11,"area":null},{"id":"2506.02863","title":"CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2405.19279","title":"Understanding and Minimising Outlier Features in Neural Network Training","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2502.21318","title":"How far can we go with ImageNet for Text-to-Image generation?","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2602.08064","title":"SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm","created":"2026-02-08","cited_by_count":10,"area":null},{"id":"2505.21910","title":"Taming Transformer Without Using Learning Rate Warmup","created":"2025-05-28","cited_by_count":9,"area":null},{"id":"2505.23660","title":"D-AR: Diffusion via Autoregressive Models","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2511.17388","title":"Selective Rotary Position Embedding","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2603.20176","title":"LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2302.00612","title":"Clinical Decision Transformer: Intended Treatment Recommendation through Goal Prompting","created":"2023-02-01","cited_by_count":8,"area":null},{"id":"2603.02170","title":"SageBwd: A Trainable Low-bit Attention","created":"2026-03-02","cited_by_count":8,"area":null},{"id":"2605.15336","title":"HoloMotion-1 Technical Report","created":"2026-05-14","cited_by_count":8,"area":null},{"id":"2503.05122","title":"EDM: Efficient Deep Feature Matching","created":"2025-03-07","cited_by_count":7,"area":null},{"id":"2512.07806","title":"Multi-view Pyramid Transformer: Look Coarser to See Broader","created":"2025-12-08","cited_by_count":7,"area":null},{"id":"2605.10468","title":"Can Muon Fine-tune Adam-Pretrained Models?","created":"2026-05-11","cited_by_count":7,"area":null},{"id":"2201.06126","title":"Control of Dual-Sourcing Inventory Systems using Recurrent Neural Networks","created":"2022-01-16","cited_by_count":6,"area":null},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2502.15856","title":"A Critical Assessment of Modern Generative Models' Ability to Replicate Artistic Styles","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2505.22014","title":"Learning in Compact Spaces with Approximately Normalized Transformer","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2509.09009","title":"Open-sci-ref-0.01: open and reproducible reference baselines for language model and dataset comparison","created":"2025-09-10","cited_by_count":6,"area":null},{"id":"2509.23500","title":"Beyond Outliers: A Study of Optimizers Under Quantization","created":"2025-09-27","cited_by_count":6,"area":null},{"id":"2510.22777","title":"SeeDNorm: Self-Rescaled Dynamic Normalization","created":"2025-10-26","cited_by_count":6,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2605.18797","title":"Simply Stabilizing the Loop via Fully Looped Transformer","created":"2026-05-11","cited_by_count":6,"area":null},{"id":"2607.25357","title":"Raven: High-Recall Sequence Modeling with Sparse Memory Routing","created":"2026-07-28","cited_by_count":6,"area":null},{"id":"2412.10743","title":"NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models","created":"2024-12-14","cited_by_count":5,"area":null},{"id":"2503.14698","title":"Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2505.08736","title":"Towards Foundation Models for Experimental Readout Systems Combining Discrete and Continuous Data","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2602.01605","title":"Universal Redundancies in Time Series Foundation Models","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2602.11761","title":"MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2306.00700","title":"On the Weight Dynamics of Deep Normalized Networks","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2410.18962","title":"Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2412.18525","title":"Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization","created":"2024-12-24","cited_by_count":4,"area":null},{"id":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2506.20752","title":"Characterization and Mitigation of Training Instabilities in Microscaling Formats","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2508.03118","title":"H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2512.10267","title":"Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2603.11611","title":"Fractional Rotation, Full Potential? Investigating Performance and Convergence of Partial RoPE","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2604.19609","title":"Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding","created":"2026-04-21","cited_by_count":4,"area":null},{"id":"2604.21681","title":"Sapiens2","created":"2026-04-23","cited_by_count":4,"area":null},{"id":"2606.12921","title":"LoRA-Muon: Spectral Steepest Descent on the Low-Rank Manifold","created":"2026-06-11","cited_by_count":4,"area":null},{"id":"2310.15672","title":"How Much Context Does My Attention-Based ASR System Need?","created":"2023-10-24","cited_by_count":3,"area":null},{"id":"2505.15353","title":"Establishing a Scale for Kullback-Leibler Divergence in Language Models Across Various Settings","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2511.21377","title":"Controlling changes to attention logits","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2604.07350","title":"Fast Spatial Memory with Elastic Test-Time Training","created":"2026-04-08","cited_by_count":3,"area":null}],"next_cursor":"100"}